diff --git "a/zoedepth_u4k/patchfusion/20240314_171340.log" "b/zoedepth_u4k/patchfusion/20240314_171340.log"
new file mode 100644--- /dev/null
+++ "b/zoedepth_u4k/patchfusion/20240314_171340.log"
@@ -0,0 +1,1650 @@
+2024/03/14 17:13:51 - patchstitcher - INFO - 
+------------------------------------------------------------
+System environment:
+    sys.platform: linux
+    Python: 3.8.18 | packaged by conda-forge | (default, Oct 10 2023, 15:44:36) [GCC 12.3.0]
+    CUDA available: True
+    numpy_random_seed: 621
+    GPU 0,1,2,3: NVIDIA A100-SXM4-80GB
+    CUDA_HOME: /sw/rl9g/cuda/11.8/rl9_binary
+    NVCC: Cuda compilation tools, release 11.8, V11.8.89
+    GCC: gcc (GCC) 11.3.1 20220421 (Red Hat 11.3.1-2)
+    PyTorch: 2.1.2
+    PyTorch compiling details: PyTorch built with:
+  - GCC 9.3
+  - C++ Version: 201703
+  - Intel(R) oneAPI Math Kernel Library Version 2022.1-Product Build 20220311 for Intel(R) 64 architecture applications
+  - Intel(R) MKL-DNN v3.1.1 (Git Hash 64f6bcbcbab628e96f33a62c3e975f8535a7bde4)
+  - OpenMP 201511 (a.k.a. OpenMP 4.5)
+  - LAPACK is enabled (usually provided by MKL)
+  - NNPACK is enabled
+  - CPU capability usage: AVX2
+  - CUDA Runtime 11.8
+  - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_90,code=sm_90;-gencode;arch=compute_37,code=compute_37
+  - CuDNN 8.7
+  - Magma 2.6.1
+  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.8, CUDNN_VERSION=8.7.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-invalid-partial-specialization -Wno-unused-private-field -Wno-aligned-allocation-unavailable -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.1.2, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 
+
+    TorchVision: 0.16.2
+    OpenCV: 4.8.1
+    MMEngine: 0.10.2
+
+Runtime environment:
+    cudnn_benchmark: True
+    mp_cfg: {'mp_start_method': 'forkserver'}
+    dist_cfg: {'backend': 'nccl'}
+    seed: 621
+    Distributed launcher: pytorch
+    Distributed training: True
+    GPU number: 4
+------------------------------------------------------------
+
+2024/03/14 17:13:51 - patchstitcher - INFO - Config:
+collect_input_args = [
+    'image_lr',
+    'crops_image_hr',
+    'depth_gt',
+    'crop_depths',
+    'bboxs',
+    'image_hr',
+]
+convert_syncbn = True
+debug = False
+env_cfg = dict(
+    cudnn_benchmark=True,
+    dist_cfg=dict(backend='nccl'),
+    mp_cfg=dict(mp_start_method='forkserver'))
+find_unused_parameters = True
+general_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        dataset_name='', gt_dir=None, rgb_image_dir='', type='ImageDataset'),
+    num_workers=2)
+launcher = 'pytorch'
+log_name = 'patchfusion'
+max_depth = 80
+min_depth = 0.001
+model = dict(
+    coarse_branch=dict(
+        attractor_alpha=1000,
+        attractor_gamma=2,
+        attractor_kind='mean',
+        attractor_type='inv',
+        aug=True,
+        bin_centers_type='softplus',
+        bin_embedding_dim=128,
+        clip_grad=0.1,
+        dataset='nyu',
+        distributed=True,
+        do_resize=False,
+        force_keep_ar=True,
+        freeze_midas_bn=True,
+        gpu='NULL',
+        img_size=[
+            384,
+            512,
+        ],
+        inverse_midas=False,
+        log_images_every=0.1,
+        max_depth=80,
+        max_temp=50.0,
+        max_translation=100,
+        memory_efficient=True,
+        midas_model_type='DPT_BEiT_L_384',
+        min_depth=0.001,
+        min_temp=0.0212,
+        model='zoedepth',
+        n_attractors=[
+            16,
+            8,
+            4,
+            1,
+        ],
+        n_bins=64,
+        name='ZoeDepth',
+        notes='',
+        output_distribution='logbinomial',
+        prefetch=False,
+        pretrained_resource='local::./work_dir/ZoeDepthv1.pt',
+        print_losses=False,
+        project='ZoeDepth',
+        random_crop=False,
+        random_translate=False,
+        root='.',
+        save_dir='',
+        shared_dict='NULL',
+        tags='',
+        train_midas=True,
+        translate_prob=0.2,
+        type='ZoeDepth',
+        uid='NULL',
+        use_amp=False,
+        use_pretrained_midas=True,
+        use_shared_dict=False,
+        validate_every=0.25,
+        version_name='v1',
+        workers=16),
+    fine_branch=dict(
+        attractor_alpha=1000,
+        attractor_gamma=2,
+        attractor_kind='mean',
+        attractor_type='inv',
+        aug=True,
+        bin_centers_type='softplus',
+        bin_embedding_dim=128,
+        clip_grad=0.1,
+        dataset='nyu',
+        distributed=True,
+        do_resize=False,
+        force_keep_ar=True,
+        freeze_midas_bn=True,
+        gpu='NULL',
+        img_size=[
+            384,
+            512,
+        ],
+        inverse_midas=False,
+        log_images_every=0.1,
+        max_depth=80,
+        max_temp=50.0,
+        max_translation=100,
+        memory_efficient=True,
+        midas_model_type='DPT_BEiT_L_384',
+        min_depth=0.001,
+        min_temp=0.0212,
+        model='zoedepth',
+        n_attractors=[
+            16,
+            8,
+            4,
+            1,
+        ],
+        n_bins=64,
+        name='ZoeDepth',
+        notes='',
+        output_distribution='logbinomial',
+        prefetch=False,
+        pretrained_resource='local::./work_dir/ZoeDepthv1.pt',
+        print_losses=False,
+        project='ZoeDepth',
+        random_crop=False,
+        random_translate=False,
+        root='.',
+        save_dir='',
+        shared_dict='NULL',
+        tags='',
+        train_midas=True,
+        translate_prob=0.2,
+        type='ZoeDepth',
+        uid='NULL',
+        use_amp=False,
+        use_pretrained_midas=True,
+        use_shared_dict=False,
+        validate_every=0.25,
+        version_name='v1',
+        workers=16),
+    guided_fusion=dict(g2l=True, n_channels=5, type='GuidedFusionPatchFusion'),
+    max_depth=80,
+    min_depth=0.001,
+    pretrain_model=[
+        './work_dir/coarse_pretrain/checkpoint_24.pth',
+        './work_dir/fine_pretrain/checkpoint_24.pth',
+    ],
+    sigloss=dict(type='SILogLoss'),
+    type='PatchFusion')
+optim_wrapper = dict(
+    clip_grad=dict(max_norm=0.1, norm_type=2, type='norm'),
+    optimizer=dict(lr=0.0001, type='AdamW', weight_decay=0.001),
+    paramwise_cfg=dict(bypass_duplicate=True, custom_keys=dict()))
+param_scheduler = dict(
+    base_momentum=0.85,
+    cycle_momentum=True,
+    div_factor=10,
+    final_div_factor=10000,
+    max_momentum=0.95,
+    pct_start=0.25,
+    three_phase=False)
+project = 'patchfusion'
+tags = [
+    'patchfusion',
+]
+test_in_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        data_root='./data/u4k',
+        max_depth=80,
+        min_depth=0.001,
+        mode='infer',
+        split='./data/u4k/splits/test.txt',
+        transform_cfg=dict(network_process_size=[
+            384,
+            512,
+        ]),
+        type='UnrealStereo4kDataset'),
+    num_workers=2)
+test_out_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        data_root='./data/u4k',
+        max_depth=80,
+        min_depth=0.001,
+        mode='infer',
+        split='./data/u4k/splits/test_out.txt',
+        transform_cfg=dict(network_process_size=[
+            384,
+            512,
+        ]),
+        type='UnrealStereo4kDataset'),
+    num_workers=2)
+train_cfg = dict(
+    eval_start=0,
+    log_interval=100,
+    max_epochs=16,
+    save_checkpoint_interval=16,
+    train_log_img_interval=500,
+    val_interval=2,
+    val_log_img_interval=10,
+    val_type='epoch_base')
+train_dataloader = dict(
+    batch_size=4,
+    dataset=dict(
+        data_root='./data/u4k',
+        max_depth=80,
+        min_depth=0.001,
+        mode='train',
+        split='./data/u4k/splits/train.txt',
+        transform_cfg=dict(
+            degree=1.0, network_process_size=[
+                384,
+                512,
+            ], random_crop=True),
+        type='UnrealStereo4kDataset'),
+    num_workers=4)
+val_dataloader = dict(
+    batch_size=1,
+    dataset=dict(
+        data_root='./data/u4k',
+        max_depth=80,
+        min_depth=0.001,
+        mode='infer',
+        split='./data/u4k/splits/val.txt',
+        transform_cfg=dict(network_process_size=[
+            384,
+            512,
+        ]),
+        type='UnrealStereo4kDataset'),
+    num_workers=2)
+work_dir = './work_dir/patchfusion'
+zoe_depth_config = dict(
+    attractor_alpha=1000,
+    attractor_gamma=2,
+    attractor_kind='mean',
+    attractor_type='inv',
+    aug=True,
+    bin_centers_type='softplus',
+    bin_embedding_dim=128,
+    clip_grad=0.1,
+    dataset='nyu',
+    distributed=True,
+    do_resize=False,
+    force_keep_ar=True,
+    freeze_midas_bn=True,
+    gpu='NULL',
+    img_size=[
+        384,
+        512,
+    ],
+    inverse_midas=False,
+    log_images_every=0.1,
+    max_depth=80,
+    max_temp=50.0,
+    max_translation=100,
+    memory_efficient=True,
+    midas_model_type='DPT_BEiT_L_384',
+    min_depth=0.001,
+    min_temp=0.0212,
+    model='zoedepth',
+    n_attractors=[
+        16,
+        8,
+        4,
+        1,
+    ],
+    n_bins=64,
+    name='ZoeDepth',
+    notes='',
+    output_distribution='logbinomial',
+    prefetch=False,
+    pretrained_resource='local::./work_dir/ZoeDepthv1.pt',
+    print_losses=False,
+    project='ZoeDepth',
+    random_crop=False,
+    random_translate=False,
+    root='.',
+    save_dir='',
+    shared_dict='NULL',
+    tags='',
+    train_midas=True,
+    translate_prob=0.2,
+    type='ZoeDepth',
+    uid='NULL',
+    use_amp=False,
+    use_pretrained_midas=True,
+    use_shared_dict=False,
+    validate_every=0.25,
+    version_name='v1',
+    workers=16)
+
+2024/03/14 17:13:56 - patchstitcher - INFO - Loading deepnet from local::./work_dir/ZoeDepthv1.pt
+2024/03/14 17:13:57 - patchstitcher - INFO - Current zoedepth.core.prep.resizer is <class 'torch.nn.modules.linear.Identity'>
+2024/03/14 17:13:57 - patchstitcher - INFO - Loading coarse_branch from ./work_dir/coarse_pretrain/checkpoint_24.pth
+2024/03/14 17:13:58 - patchstitcher - INFO - <All keys matched successfully>
+2024/03/14 17:14:02 - patchstitcher - INFO - Loading deepnet from local::./work_dir/ZoeDepthv1.pt
+2024/03/14 17:14:03 - patchstitcher - INFO - Current zoedepth.core.prep.resizer is <class 'torch.nn.modules.linear.Identity'>
+2024/03/14 17:14:03 - patchstitcher - INFO - Loading fine_branch from ./work_dir/fine_pretrain/checkpoint_24.pth
+2024/03/14 17:14:03 - patchstitcher - INFO - <All keys matched successfully>
+2024/03/14 17:14:04 - patchstitcher - INFO - DistributedDataParallel(
+  (module): PatchFusion(
+    (coarse_branch): ZoeDepth(
+      (core): MidasCore(
+        (core): DPTDepthModel(
+          (pretrained): Module(
+            (model): Beit(
+              (patch_embed): PatchEmbed(
+                (proj): Conv2d(3, 1024, kernel_size=(16, 16), stride=(16, 16))
+                (norm): Identity()
+              )
+              (pos_drop): Dropout(p=0.0, inplace=False)
+              (blocks): ModuleList(
+                (0-23): 24 x Block(
+                  (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
+                  (attn): Attention(
+                    (qkv): Linear(in_features=1024, out_features=3072, bias=False)
+                    (attn_drop): Dropout(p=0.0, inplace=False)
+                    (proj): Linear(in_features=1024, out_features=1024, bias=True)
+                    (proj_drop): Dropout(p=0.0, inplace=False)
+                  )
+                  (drop_path1): Identity()
+                  (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
+                  (mlp): Mlp(
+                    (fc1): Linear(in_features=1024, out_features=4096, bias=True)
+                    (act): GELU(approximate='none')
+                    (drop1): Dropout(p=0.0, inplace=False)
+                    (norm): Identity()
+                    (fc2): Linear(in_features=4096, out_features=1024, bias=True)
+                    (drop2): Dropout(p=0.0, inplace=False)
+                  )
+                  (drop_path2): Identity()
+                )
+              )
+              (norm): Identity()
+              (fc_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
+              (head_drop): Dropout(p=0.0, inplace=False)
+              (head): Linear(in_features=1024, out_features=1000, bias=True)
+            )
+            (act_postprocess1): Sequential(
+              (0): ProjectReadout(
+                (project): Sequential(
+                  (0): Linear(in_features=2048, out_features=1024, bias=True)
+                  (1): GELU(approximate='none')
+                )
+              )
+              (1): Transpose()
+              (2): Unflatten(dim=2, unflattened_size=torch.Size([24, 24]))
+              (3): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
+              (4): ConvTranspose2d(256, 256, kernel_size=(4, 4), stride=(4, 4))
+            )
+            (act_postprocess2): Sequential(
+              (0): ProjectReadout(
+                (project): Sequential(
+                  (0): Linear(in_features=2048, out_features=1024, bias=True)
+                  (1): GELU(approximate='none')
+                )
+              )
+              (1): Transpose()
+              (2): Unflatten(dim=2, unflattened_size=torch.Size([24, 24]))
+              (3): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1))
+              (4): ConvTranspose2d(512, 512, kernel_size=(2, 2), stride=(2, 2))
+            )
+            (act_postprocess3): Sequential(
+              (0): ProjectReadout(
+                (project): Sequential(
+                  (0): Linear(in_features=2048, out_features=1024, bias=True)
+                  (1): GELU(approximate='none')
+                )
+              )
+              (1): Transpose()
+              (2): Unflatten(dim=2, unflattened_size=torch.Size([24, 24]))
+              (3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1))
+            )
+            (act_postprocess4): Sequential(
+              (0): ProjectReadout(
+                (project): Sequential(
+                  (0): Linear(in_features=2048, out_features=1024, bias=True)
+                  (1): GELU(approximate='none')
+                )
+              )
+              (1): Transpose()
+              (2): Unflatten(dim=2, unflattened_size=torch.Size([24, 24]))
+              (3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1))
+              (4): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
+            )
+          )
+          (scratch): Module(
+            (layer1_rn): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (layer2_rn): Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (layer3_rn): Conv2d(1024, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (layer4_rn): Conv2d(1024, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (refinenet1): FeatureFusionBlock_custom(
+              (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+              (resConfUnit1): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (resConfUnit2): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (skip_add): FloatFunctional(
+                (activation_post_process): Identity()
+              )
+            )
+            (refinenet2): FeatureFusionBlock_custom(
+              (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+              (resConfUnit1): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (resConfUnit2): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (skip_add): FloatFunctional(
+                (activation_post_process): Identity()
+              )
+            )
+            (refinenet3): FeatureFusionBlock_custom(
+              (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+              (resConfUnit1): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (resConfUnit2): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (skip_add): FloatFunctional(
+                (activation_post_process): Identity()
+              )
+            )
+            (refinenet4): FeatureFusionBlock_custom(
+              (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+              (resConfUnit1): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (resConfUnit2): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (skip_add): FloatFunctional(
+                (activation_post_process): Identity()
+              )
+            )
+            (output_conv): Sequential(
+              (0): Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              (1): Interpolate()
+              (2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              (3): ReLU(inplace=True)
+              (4): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
+              (5): ReLU(inplace=True)
+              (6): Identity()
+            )
+          )
+        )
+      )
+      (conv2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+      (seed_bin_regressor): SeedBinRegressorUnnormed(
+        (_net): Sequential(
+          (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+          (1): ReLU(inplace=True)
+          (2): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1))
+          (3): Softplus(beta=1, threshold=20)
+        )
+      )
+      (seed_projector): Projector(
+        (_net): Sequential(
+          (0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
+          (1): ReLU(inplace=True)
+          (2): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+        )
+      )
+      (projectors): ModuleList(
+        (0-3): 4 x Projector(
+          (_net): Sequential(
+            (0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
+            (1): ReLU(inplace=True)
+            (2): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+          )
+        )
+      )
+      (attractors): ModuleList(
+        (0): AttractorLayerUnnormed(
+          (_net): Sequential(
+            (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+            (1): ReLU(inplace=True)
+            (2): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1))
+            (3): Softplus(beta=1, threshold=20)
+          )
+        )
+        (1): AttractorLayerUnnormed(
+          (_net): Sequential(
+            (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+            (1): ReLU(inplace=True)
+            (2): Conv2d(128, 8, kernel_size=(1, 1), stride=(1, 1))
+            (3): Softplus(beta=1, threshold=20)
+          )
+        )
+        (2): AttractorLayerUnnormed(
+          (_net): Sequential(
+            (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+            (1): ReLU(inplace=True)
+            (2): Conv2d(128, 4, kernel_size=(1, 1), stride=(1, 1))
+            (3): Softplus(beta=1, threshold=20)
+          )
+        )
+        (3): AttractorLayerUnnormed(
+          (_net): Sequential(
+            (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+            (1): ReLU(inplace=True)
+            (2): Conv2d(128, 1, kernel_size=(1, 1), stride=(1, 1))
+            (3): Softplus(beta=1, threshold=20)
+          )
+        )
+      )
+      (conditional_log_binomial): ConditionalLogBinomial(
+        (log_binomial_transform): LogBinomial()
+        (mlp): Sequential(
+          (0): Conv2d(161, 80, kernel_size=(1, 1), stride=(1, 1))
+          (1): GELU(approximate='none')
+          (2): Conv2d(80, 4, kernel_size=(1, 1), stride=(1, 1))
+          (3): Softplus(beta=1, threshold=20)
+        )
+      )
+    )
+    (fine_branch): ZoeDepth(
+      (core): MidasCore(
+        (core): DPTDepthModel(
+          (pretrained): Module(
+            (model): Beit(
+              (patch_embed): PatchEmbed(
+                (proj): Conv2d(3, 1024, kernel_size=(16, 16), stride=(16, 16))
+                (norm): Identity()
+              )
+              (pos_drop): Dropout(p=0.0, inplace=False)
+              (blocks): ModuleList(
+                (0-23): 24 x Block(
+                  (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
+                  (attn): Attention(
+                    (qkv): Linear(in_features=1024, out_features=3072, bias=False)
+                    (attn_drop): Dropout(p=0.0, inplace=False)
+                    (proj): Linear(in_features=1024, out_features=1024, bias=True)
+                    (proj_drop): Dropout(p=0.0, inplace=False)
+                  )
+                  (drop_path1): Identity()
+                  (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
+                  (mlp): Mlp(
+                    (fc1): Linear(in_features=1024, out_features=4096, bias=True)
+                    (act): GELU(approximate='none')
+                    (drop1): Dropout(p=0.0, inplace=False)
+                    (norm): Identity()
+                    (fc2): Linear(in_features=4096, out_features=1024, bias=True)
+                    (drop2): Dropout(p=0.0, inplace=False)
+                  )
+                  (drop_path2): Identity()
+                )
+              )
+              (norm): Identity()
+              (fc_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
+              (head_drop): Dropout(p=0.0, inplace=False)
+              (head): Linear(in_features=1024, out_features=1000, bias=True)
+            )
+            (act_postprocess1): Sequential(
+              (0): ProjectReadout(
+                (project): Sequential(
+                  (0): Linear(in_features=2048, out_features=1024, bias=True)
+                  (1): GELU(approximate='none')
+                )
+              )
+              (1): Transpose()
+              (2): Unflatten(dim=2, unflattened_size=torch.Size([24, 24]))
+              (3): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
+              (4): ConvTranspose2d(256, 256, kernel_size=(4, 4), stride=(4, 4))
+            )
+            (act_postprocess2): Sequential(
+              (0): ProjectReadout(
+                (project): Sequential(
+                  (0): Linear(in_features=2048, out_features=1024, bias=True)
+                  (1): GELU(approximate='none')
+                )
+              )
+              (1): Transpose()
+              (2): Unflatten(dim=2, unflattened_size=torch.Size([24, 24]))
+              (3): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1))
+              (4): ConvTranspose2d(512, 512, kernel_size=(2, 2), stride=(2, 2))
+            )
+            (act_postprocess3): Sequential(
+              (0): ProjectReadout(
+                (project): Sequential(
+                  (0): Linear(in_features=2048, out_features=1024, bias=True)
+                  (1): GELU(approximate='none')
+                )
+              )
+              (1): Transpose()
+              (2): Unflatten(dim=2, unflattened_size=torch.Size([24, 24]))
+              (3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1))
+            )
+            (act_postprocess4): Sequential(
+              (0): ProjectReadout(
+                (project): Sequential(
+                  (0): Linear(in_features=2048, out_features=1024, bias=True)
+                  (1): GELU(approximate='none')
+                )
+              )
+              (1): Transpose()
+              (2): Unflatten(dim=2, unflattened_size=torch.Size([24, 24]))
+              (3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1))
+              (4): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
+            )
+          )
+          (scratch): Module(
+            (layer1_rn): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (layer2_rn): Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (layer3_rn): Conv2d(1024, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (layer4_rn): Conv2d(1024, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (refinenet1): FeatureFusionBlock_custom(
+              (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+              (resConfUnit1): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (resConfUnit2): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (skip_add): FloatFunctional(
+                (activation_post_process): Identity()
+              )
+            )
+            (refinenet2): FeatureFusionBlock_custom(
+              (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+              (resConfUnit1): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (resConfUnit2): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (skip_add): FloatFunctional(
+                (activation_post_process): Identity()
+              )
+            )
+            (refinenet3): FeatureFusionBlock_custom(
+              (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+              (resConfUnit1): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (resConfUnit2): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (skip_add): FloatFunctional(
+                (activation_post_process): Identity()
+              )
+            )
+            (refinenet4): FeatureFusionBlock_custom(
+              (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+              (resConfUnit1): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (resConfUnit2): ResidualConvUnit_custom(
+                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (activation): ReLU()
+                (skip_add): FloatFunctional(
+                  (activation_post_process): Identity()
+                )
+              )
+              (skip_add): FloatFunctional(
+                (activation_post_process): Identity()
+              )
+            )
+            (output_conv): Sequential(
+              (0): Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              (1): Interpolate()
+              (2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              (3): ReLU(inplace=True)
+              (4): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
+              (5): ReLU(inplace=True)
+              (6): Identity()
+            )
+          )
+        )
+      )
+      (conv2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+      (seed_bin_regressor): SeedBinRegressorUnnormed(
+        (_net): Sequential(
+          (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+          (1): ReLU(inplace=True)
+          (2): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1))
+          (3): Softplus(beta=1, threshold=20)
+        )
+      )
+      (seed_projector): Projector(
+        (_net): Sequential(
+          (0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
+          (1): ReLU(inplace=True)
+          (2): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+        )
+      )
+      (projectors): ModuleList(
+        (0-3): 4 x Projector(
+          (_net): Sequential(
+            (0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
+            (1): ReLU(inplace=True)
+            (2): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+          )
+        )
+      )
+      (attractors): ModuleList(
+        (0): AttractorLayerUnnormed(
+          (_net): Sequential(
+            (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+            (1): ReLU(inplace=True)
+            (2): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1))
+            (3): Softplus(beta=1, threshold=20)
+          )
+        )
+        (1): AttractorLayerUnnormed(
+          (_net): Sequential(
+            (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+            (1): ReLU(inplace=True)
+            (2): Conv2d(128, 8, kernel_size=(1, 1), stride=(1, 1))
+            (3): Softplus(beta=1, threshold=20)
+          )
+        )
+        (2): AttractorLayerUnnormed(
+          (_net): Sequential(
+            (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+            (1): ReLU(inplace=True)
+            (2): Conv2d(128, 4, kernel_size=(1, 1), stride=(1, 1))
+            (3): Softplus(beta=1, threshold=20)
+          )
+        )
+        (3): AttractorLayerUnnormed(
+          (_net): Sequential(
+            (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+            (1): ReLU(inplace=True)
+            (2): Conv2d(128, 1, kernel_size=(1, 1), stride=(1, 1))
+            (3): Softplus(beta=1, threshold=20)
+          )
+        )
+      )
+      (conditional_log_binomial): ConditionalLogBinomial(
+        (log_binomial_transform): LogBinomial()
+        (mlp): Sequential(
+          (0): Conv2d(161, 80, kernel_size=(1, 1), stride=(1, 1))
+          (1): GELU(approximate='none')
+          (2): Conv2d(80, 4, kernel_size=(1, 1), stride=(1, 1))
+          (3): Softplus(beta=1, threshold=20)
+        )
+      )
+    )
+    (sigloss): SILogLoss()
+    (fusion_conv_list): ModuleList(
+      (0-4): 5 x Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      (5): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    )
+    (guided_fusion): GuidedFusionPatchFusion(
+      (inc): DoubleConv(
+        (double_conv): Sequential(
+          (0): Conv2d(5, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+          (1): SyncBatchNorm(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          (2): ReLU(inplace=True)
+          (3): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+          (4): SyncBatchNorm(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          (5): ReLU(inplace=True)
+        )
+      )
+      (down_conv_list): ModuleList(
+        (0): Down(
+          (maxpool_conv): Sequential(
+            (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
+            (1): DoubleConv(
+              (double_conv): Sequential(
+                (0): Conv2d(32, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+                (1): SyncBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+                (2): ReLU(inplace=True)
+                (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+                (4): SyncBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+                (5): ReLU(inplace=True)
+              )
+            )
+          )
+        )
+        (1-4): 4 x Down(
+          (maxpool_conv): Sequential(
+            (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
+            (1): DoubleConv(
+              (double_conv): Sequential(
+                (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+                (1): SyncBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+                (2): ReLU(inplace=True)
+                (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+                (4): SyncBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+                (5): ReLU(inplace=True)
+              )
+            )
+          )
+        )
+      )
+      (up_conv_list): ModuleList(
+        (0-3): 4 x Upv1(
+          (conv): DoubleConvWOBN(
+            (double_conv): Sequential(
+              (0): Conv2d(768, 768, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              (1): ReLU(inplace=True)
+              (2): Conv2d(768, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              (3): ReLU(inplace=True)
+            )
+          )
+        )
+        (4): Upv1(
+          (conv): DoubleConvWOBN(
+            (double_conv): Sequential(
+              (0): Conv2d(544, 544, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              (1): ReLU(inplace=True)
+              (2): Conv2d(544, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              (3): ReLU(inplace=True)
+            )
+          )
+        )
+      )
+      (g2l_att): ModuleList()
+      (g2l_list): ModuleList(
+        (0-1): 2 x G2LFusion(
+          (g2l_layer): G2LBasicLayer(
+            (blocks): ModuleList(
+              (0-3): 4 x SwinTransformerBlock(
+                (norm1): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
+                (attn): WindowAttention(
+                  dim=256, window_size=(12, 12), num_heads=32
+                  (qkv): Linear(in_features=256, out_features=768, bias=True)
+                  (attn_drop): Dropout(p=0.0, inplace=False)
+                  (proj): Linear(in_features=256, out_features=256, bias=True)
+                  (proj_drop): Dropout(p=0.0, inplace=False)
+                  (softmax): Softmax(dim=-1)
+                )
+                (drop_path): Identity()
+                (norm2): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
+                (mlp): Mlp(
+                  (fc1): Linear(in_features=256, out_features=1024, bias=True)
+                  (act): GELU(approximate='none')
+                  (fc2): Linear(in_features=1024, out_features=256, bias=True)
+                  (drop): Dropout(p=0.0, inplace=False)
+                )
+              )
+            )
+          )
+          (g2l_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
+          (embed_proj): Conv2d(1, 256, kernel_size=(1, 1), stride=(1, 1))
+        )
+        (2-3): 2 x G2LFusion(
+          (g2l_layer): G2LBasicLayer(
+            (blocks): ModuleList(
+              (0-2): 3 x SwinTransformerBlock(
+                (norm1): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
+                (attn): WindowAttention(
+                  dim=256, window_size=(12, 12), num_heads=16
+                  (qkv): Linear(in_features=256, out_features=768, bias=True)
+                  (attn_drop): Dropout(p=0.0, inplace=False)
+                  (proj): Linear(in_features=256, out_features=256, bias=True)
+                  (proj_drop): Dropout(p=0.0, inplace=False)
+                  (softmax): Softmax(dim=-1)
+                )
+                (drop_path): Identity()
+                (norm2): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
+                (mlp): Mlp(
+                  (fc1): Linear(in_features=256, out_features=1024, bias=True)
+                  (act): GELU(approximate='none')
+                  (fc2): Linear(in_features=1024, out_features=256, bias=True)
+                  (drop): Dropout(p=0.0, inplace=False)
+                )
+              )
+            )
+          )
+          (g2l_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
+          (embed_proj): Conv2d(1, 256, kernel_size=(1, 1), stride=(1, 1))
+        )
+        (4): G2LFusion(
+          (g2l_layer): G2LBasicLayer(
+            (blocks): ModuleList(
+              (0-1): 2 x SwinTransformerBlock(
+                (norm1): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
+                (attn): WindowAttention(
+                  dim=256, window_size=(12, 12), num_heads=8
+                  (qkv): Linear(in_features=256, out_features=768, bias=True)
+                  (attn_drop): Dropout(p=0.0, inplace=False)
+                  (proj): Linear(in_features=256, out_features=256, bias=True)
+                  (proj_drop): Dropout(p=0.0, inplace=False)
+                  (softmax): Softmax(dim=-1)
+                )
+                (drop_path): Identity()
+                (norm2): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
+                (mlp): Mlp(
+                  (fc1): Linear(in_features=256, out_features=1024, bias=True)
+                  (act): GELU(approximate='none')
+                  (fc2): Linear(in_features=1024, out_features=256, bias=True)
+                  (drop): Dropout(p=0.0, inplace=False)
+                )
+              )
+            )
+          )
+          (g2l_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
+          (embed_proj): Conv2d(1, 256, kernel_size=(1, 1), stride=(1, 1))
+        )
+        (5): G2LFusion(
+          (g2l_layer): G2LBasicLayer(
+            (blocks): ModuleList(
+              (0-1): 2 x SwinTransformerBlock(
+                (norm1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
+                (attn): WindowAttention(
+                  dim=32, window_size=(12, 12), num_heads=8
+                  (qkv): Linear(in_features=32, out_features=96, bias=True)
+                  (attn_drop): Dropout(p=0.0, inplace=False)
+                  (proj): Linear(in_features=32, out_features=32, bias=True)
+                  (proj_drop): Dropout(p=0.0, inplace=False)
+                  (softmax): Softmax(dim=-1)
+                )
+                (drop_path): Identity()
+                (norm2): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
+                (mlp): Mlp(
+                  (fc1): Linear(in_features=32, out_features=128, bias=True)
+                  (act): GELU(approximate='none')
+                  (fc2): Linear(in_features=128, out_features=32, bias=True)
+                  (drop): Dropout(p=0.0, inplace=False)
+                )
+              )
+            )
+          )
+          (g2l_layer_norm): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
+          (embed_proj): Conv2d(1, 32, kernel_size=(1, 1), stride=(1, 1))
+        )
+      )
+      (convs): ModuleList(
+        (0-4): 5 x DoubleConvWOBN(
+          (double_conv): Sequential(
+            (0): Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+            (1): ReLU(inplace=True)
+            (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+            (3): ReLU(inplace=True)
+          )
+        )
+        (5): DoubleConvWOBN(
+          (double_conv): Sequential(
+            (0): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+            (1): ReLU(inplace=True)
+            (2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+            (3): ReLU(inplace=True)
+          )
+        )
+      )
+    )
+    (seed_bin_regressor): SeedBinRegressorUnnormed(
+      (_net): Sequential(
+        (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+        (1): ReLU(inplace=True)
+        (2): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1))
+        (3): Softplus(beta=1, threshold=20)
+      )
+    )
+    (seed_projector): Projector(
+      (_net): Sequential(
+        (0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
+        (1): ReLU(inplace=True)
+        (2): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+      )
+    )
+    (projectors): ModuleList(
+      (0-3): 4 x Projector(
+        (_net): Sequential(
+          (0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
+          (1): ReLU(inplace=True)
+          (2): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+        )
+      )
+    )
+    (attractors): ModuleList(
+      (0): AttractorLayerUnnormed(
+        (_net): Sequential(
+          (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+          (1): ReLU(inplace=True)
+          (2): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1))
+          (3): Softplus(beta=1, threshold=20)
+        )
+      )
+      (1): AttractorLayerUnnormed(
+        (_net): Sequential(
+          (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+          (1): ReLU(inplace=True)
+          (2): Conv2d(128, 8, kernel_size=(1, 1), stride=(1, 1))
+          (3): Softplus(beta=1, threshold=20)
+        )
+      )
+      (2): AttractorLayerUnnormed(
+        (_net): Sequential(
+          (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+          (1): ReLU(inplace=True)
+          (2): Conv2d(128, 4, kernel_size=(1, 1), stride=(1, 1))
+          (3): Softplus(beta=1, threshold=20)
+        )
+      )
+      (3): AttractorLayerUnnormed(
+        (_net): Sequential(
+          (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
+          (1): ReLU(inplace=True)
+          (2): Conv2d(128, 1, kernel_size=(1, 1), stride=(1, 1))
+          (3): Softplus(beta=1, threshold=20)
+        )
+      )
+    )
+    (conditional_log_binomial): ConditionalLogBinomial(
+      (log_binomial_transform): LogBinomial()
+      (mlp): Sequential(
+        (0): Conv2d(161, 80, kernel_size=(1, 1), stride=(1, 1))
+        (1): GELU(approximate='none')
+        (2): Conv2d(80, 4, kernel_size=(1, 1), stride=(1, 1))
+        (3): Softplus(beta=1, threshold=20)
+      )
+    )
+  )
+)
+2024/03/14 17:14:11 - patchstitcher - INFO - successfully init trainer
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.fusion_conv_list.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.fusion_conv_list.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.fusion_conv_list.1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.fusion_conv_list.1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.fusion_conv_list.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.fusion_conv_list.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.fusion_conv_list.3.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.fusion_conv_list.3.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.fusion_conv_list.4.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.fusion_conv_list.4.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.fusion_conv_list.5.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.fusion_conv_list.5.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.inc.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.inc.double_conv.1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.inc.double_conv.1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.inc.double_conv.3.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.inc.double_conv.4.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.inc.double_conv.4.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.0.maxpool_conv.1.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.0.maxpool_conv.1.double_conv.1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.0.maxpool_conv.1.double_conv.1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.0.maxpool_conv.1.double_conv.3.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.0.maxpool_conv.1.double_conv.4.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.0.maxpool_conv.1.double_conv.4.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.1.maxpool_conv.1.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.1.maxpool_conv.1.double_conv.1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.1.maxpool_conv.1.double_conv.1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.1.maxpool_conv.1.double_conv.3.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.1.maxpool_conv.1.double_conv.4.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.1.maxpool_conv.1.double_conv.4.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.2.maxpool_conv.1.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.2.maxpool_conv.1.double_conv.1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.2.maxpool_conv.1.double_conv.1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.2.maxpool_conv.1.double_conv.3.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.2.maxpool_conv.1.double_conv.4.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.2.maxpool_conv.1.double_conv.4.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.3.maxpool_conv.1.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.3.maxpool_conv.1.double_conv.1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.3.maxpool_conv.1.double_conv.1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.3.maxpool_conv.1.double_conv.3.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.3.maxpool_conv.1.double_conv.4.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.3.maxpool_conv.1.double_conv.4.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.4.maxpool_conv.1.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.4.maxpool_conv.1.double_conv.1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.4.maxpool_conv.1.double_conv.1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.4.maxpool_conv.1.double_conv.3.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.4.maxpool_conv.1.double_conv.4.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.4.maxpool_conv.1.double_conv.4.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.0.conv.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.0.conv.double_conv.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.0.conv.double_conv.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.0.conv.double_conv.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.1.conv.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.1.conv.double_conv.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.1.conv.double_conv.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.1.conv.double_conv.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.2.conv.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.2.conv.double_conv.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.2.conv.double_conv.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.2.conv.double_conv.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.3.conv.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.3.conv.double_conv.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.3.conv.double_conv.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.3.conv.double_conv.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.4.conv.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.4.conv.double_conv.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.4.conv.double_conv.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.4.conv.double_conv.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.absolute_pos_embed
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer_norm.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer_norm.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.embed_proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.embed_proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.absolute_pos_embed
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer_norm.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer_norm.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.embed_proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.embed_proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.absolute_pos_embed
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer_norm.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer_norm.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.embed_proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.embed_proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.absolute_pos_embed
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer_norm.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer_norm.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.embed_proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.embed_proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.absolute_pos_embed
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer_norm.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer_norm.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.embed_proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.embed_proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.absolute_pos_embed
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.norm1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.norm1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.attn.relative_position_bias_table
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.attn.qkv.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.attn.qkv.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.attn.proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.attn.proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.norm2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.norm2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.mlp.fc1.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.mlp.fc1.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.mlp.fc2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.mlp.fc2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer_norm.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer_norm.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.embed_proj.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.embed_proj.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.0.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.0.double_conv.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.0.double_conv.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.0.double_conv.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.1.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.1.double_conv.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.1.double_conv.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.1.double_conv.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.2.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.2.double_conv.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.2.double_conv.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.2.double_conv.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.3.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.3.double_conv.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.3.double_conv.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.3.double_conv.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.4.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.4.double_conv.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.4.double_conv.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.4.double_conv.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.5.double_conv.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.5.double_conv.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.5.double_conv.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.guided_fusion.convs.5.double_conv.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.seed_bin_regressor._net.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.seed_bin_regressor._net.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.seed_bin_regressor._net.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.seed_bin_regressor._net.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.seed_projector._net.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.seed_projector._net.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.seed_projector._net.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.seed_projector._net.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.0._net.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.0._net.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.0._net.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.0._net.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.1._net.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.1._net.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.1._net.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.1._net.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.2._net.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.2._net.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.2._net.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.2._net.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.3._net.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.3._net.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.3._net.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.projectors.3._net.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.0._net.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.0._net.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.0._net.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.0._net.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.1._net.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.1._net.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.1._net.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.1._net.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.2._net.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.2._net.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.2._net.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.2._net.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.3._net.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.3._net.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.3._net.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.attractors.3._net.2.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.conditional_log_binomial.mlp.0.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.conditional_log_binomial.mlp.0.bias
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.conditional_log_binomial.mlp.2.weight
+2024/03/14 17:14:11 - patchstitcher - INFO - training param: module.conditional_log_binomial.mlp.2.bias
+2024/03/14 17:18:02 - patchstitcher - INFO - Epoch: [01/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 5.812175750732422 - sig_loss: 5.812175750732422
+2024/03/14 17:20:49 - patchstitcher - INFO - Epoch: [01/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 4.757198810577393 - sig_loss: 4.757198810577393
+2024/03/14 17:23:35 - patchstitcher - INFO - Epoch: [01/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 4.406374931335449 - sig_loss: 4.406374931335449
+2024/03/14 17:26:22 - patchstitcher - INFO - Epoch: [01/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 4.167110919952393 - sig_loss: 4.167110919952393
+2024/03/14 17:31:55 - patchstitcher - INFO - Epoch: [02/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 1.177768588066101 - sig_loss: 1.177768588066101
+2024/03/14 17:34:42 - patchstitcher - INFO - Epoch: [02/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 1.2987905740737915 - sig_loss: 1.2987905740737915
+2024/03/14 17:37:29 - patchstitcher - INFO - Epoch: [02/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 1.2379343509674072 - sig_loss: 1.2379343509674072
+2024/03/14 17:40:16 - patchstitcher - INFO - Epoch: [02/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 3.784421443939209 - sig_loss: 3.784421443939209
+2024/03/14 17:43:19 - patchstitcher - INFO - Evaluation Summary: 
++-----------+-----------+-----------+-----------+-----------+-----------+-----------+------------+----------+----------+
+|     a1    |     a2    |     a3    |  abs_rel  |    rmse   |   log_10  |  rmse_log |   silog    |  sq_rel  |   see    |
++-----------+-----------+-----------+-----------+-----------+-----------+-----------+------------+----------+----------+
+| 0.9329284 | 0.9885241 | 0.9960132 | 0.0993076 | 2.1293075 | 0.0410439 | 0.1289805 | 10.5232363 | 0.277949 | 1.483049 |
++-----------+-----------+-----------+-----------+-----------+-----------+-----------+------------+----------+----------+
+2024/03/14 17:46:10 - patchstitcher - INFO - Epoch: [03/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 1.455110788345337 - sig_loss: 1.455110788345337
+2024/03/14 17:48:56 - patchstitcher - INFO - Epoch: [03/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.8667159080505371 - sig_loss: 0.8667159080505371
+2024/03/14 17:51:43 - patchstitcher - INFO - Epoch: [03/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.34603792428970337 - sig_loss: 0.34603792428970337
+2024/03/14 17:54:29 - patchstitcher - INFO - Epoch: [03/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.7164655923843384 - sig_loss: 0.7164655923843384
+2024/03/14 17:59:23 - patchstitcher - INFO - Epoch: [04/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.920989453792572 - sig_loss: 0.920989453792572
+2024/03/14 18:02:09 - patchstitcher - INFO - Epoch: [04/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.41945281624794006 - sig_loss: 0.41945281624794006
+2024/03/14 18:04:55 - patchstitcher - INFO - Epoch: [04/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 1.0151278972625732 - sig_loss: 1.0151278972625732
+2024/03/14 18:07:42 - patchstitcher - INFO - Epoch: [04/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.37428972125053406 - sig_loss: 0.37428972125053406
+2024/03/14 18:10:32 - patchstitcher - INFO - Evaluation Summary: 
++-----------+-----------+-----------+-----------+-----------+-----------+----------+----------+-----------+-----------+
+|     a1    |     a2    |     a3    |  abs_rel  |    rmse   |   log_10  | rmse_log |  silog   |   sq_rel  |    see    |
++-----------+-----------+-----------+-----------+-----------+-----------+----------+----------+-----------+-----------+
+| 0.9792663 | 0.9946408 | 0.9979739 | 0.0648644 | 1.1818094 | 0.0272512 | 0.086467 | 7.100818 | 0.1072941 | 0.9891314 |
++-----------+-----------+-----------+-----------+-----------+-----------+----------+----------+-----------+-----------+
+2024/03/14 18:13:23 - patchstitcher - INFO - Epoch: [05/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.6358187198638916 - sig_loss: 0.6358187198638916
+2024/03/14 18:16:09 - patchstitcher - INFO - Epoch: [05/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.4720376431941986 - sig_loss: 0.4720376431941986
+2024/03/14 18:18:55 - patchstitcher - INFO - Epoch: [05/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.8008860349655151 - sig_loss: 0.8008860349655151
+2024/03/14 18:21:41 - patchstitcher - INFO - Epoch: [05/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.5053590536117554 - sig_loss: 0.5053590536117554
+2024/03/14 18:26:37 - patchstitcher - INFO - Epoch: [06/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 1.635500192642212 - sig_loss: 1.635500192642212
+2024/03/14 18:29:23 - patchstitcher - INFO - Epoch: [06/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.8267055749893188 - sig_loss: 0.8267055749893188
+2024/03/14 18:32:09 - patchstitcher - INFO - Epoch: [06/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.49443477392196655 - sig_loss: 0.49443477392196655
+2024/03/14 18:34:55 - patchstitcher - INFO - Epoch: [06/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.34171706438064575 - sig_loss: 0.34171706438064575
+2024/03/14 18:37:45 - patchstitcher - INFO - Evaluation Summary: 
++----------+-----------+-----------+-----------+-----------+-----------+----------+----------+-----------+-----------+
+|    a1    |     a2    |     a3    |  abs_rel  |    rmse   |   log_10  | rmse_log |  silog   |   sq_rel  |    see    |
++----------+-----------+-----------+-----------+-----------+-----------+----------+----------+-----------+-----------+
+| 0.981504 | 0.9946188 | 0.9979614 | 0.0618421 | 1.1922652 | 0.0263535 | 0.084107 | 7.024505 | 0.0983676 | 0.9141212 |
++----------+-----------+-----------+-----------+-----------+-----------+----------+----------+-----------+-----------+
+2024/03/14 18:40:36 - patchstitcher - INFO - Epoch: [07/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.39282920956611633 - sig_loss: 0.39282920956611633
+2024/03/14 18:43:22 - patchstitcher - INFO - Epoch: [07/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.7669318318367004 - sig_loss: 0.7669318318367004
+2024/03/14 18:46:08 - patchstitcher - INFO - Epoch: [07/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.4042762517929077 - sig_loss: 0.4042762517929077
+2024/03/14 18:48:54 - patchstitcher - INFO - Epoch: [07/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.30873197317123413 - sig_loss: 0.30873197317123413
+2024/03/14 18:53:48 - patchstitcher - INFO - Epoch: [08/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.6158128380775452 - sig_loss: 0.6158128380775452
+2024/03/14 18:56:34 - patchstitcher - INFO - Epoch: [08/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.39382457733154297 - sig_loss: 0.39382457733154297
+2024/03/14 18:59:20 - patchstitcher - INFO - Epoch: [08/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.41618794202804565 - sig_loss: 0.41618794202804565
+2024/03/14 19:02:06 - patchstitcher - INFO - Epoch: [08/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.8896353840827942 - sig_loss: 0.8896353840827942
+2024/03/14 19:04:55 - patchstitcher - INFO - Evaluation Summary: 
++-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+-----------+-----------+
+|     a1    |     a2    |     a3    | abs_rel  |    rmse   |   log_10  |  rmse_log |   silog   |   sq_rel  |    see    |
++-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+-----------+-----------+
+| 0.9833737 | 0.9949664 | 0.9980009 | 0.045181 | 1.1046772 | 0.0194044 | 0.0714313 | 6.6380505 | 0.0959126 | 0.9399157 |
++-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+-----------+-----------+
+2024/03/14 19:07:48 - patchstitcher - INFO - Epoch: [09/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.6397521495819092 - sig_loss: 0.6397521495819092
+2024/03/14 19:10:34 - patchstitcher - INFO - Epoch: [09/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 1.6051456928253174 - sig_loss: 1.6051456928253174
+2024/03/14 19:13:19 - patchstitcher - INFO - Epoch: [09/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.3201293647289276 - sig_loss: 0.3201293647289276
+2024/03/14 19:16:06 - patchstitcher - INFO - Epoch: [09/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.6634743213653564 - sig_loss: 0.6634743213653564
+2024/03/14 19:21:01 - patchstitcher - INFO - Epoch: [10/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.2229178249835968 - sig_loss: 0.2229178249835968
+2024/03/14 19:23:47 - patchstitcher - INFO - Epoch: [10/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.877116322517395 - sig_loss: 0.877116322517395
+2024/03/14 19:26:32 - patchstitcher - INFO - Epoch: [10/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 1.0112898349761963 - sig_loss: 1.0112898349761963
+2024/03/14 19:29:18 - patchstitcher - INFO - Epoch: [10/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.6741850972175598 - sig_loss: 0.6741850972175598
+2024/03/14 19:32:09 - patchstitcher - INFO - Evaluation Summary: 
++-----------+-----------+-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+
+|     a1    |     a2    |     a3    |  abs_rel  |    rmse   |  log_10  |  rmse_log |   silog   |   sq_rel  |    see    |
++-----------+-----------+-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+
+| 0.9843725 | 0.9950381 | 0.9979867 | 0.0407497 | 1.0524275 | 0.017678 | 0.0683858 | 6.3216866 | 0.0864915 | 0.8803844 |
++-----------+-----------+-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+
+2024/03/14 19:35:01 - patchstitcher - INFO - Epoch: [11/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.6309881210327148 - sig_loss: 0.6309881210327148
+2024/03/14 19:37:46 - patchstitcher - INFO - Epoch: [11/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.8504288792610168 - sig_loss: 0.8504288792610168
+2024/03/14 19:40:32 - patchstitcher - INFO - Epoch: [11/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.8164891004562378 - sig_loss: 0.8164891004562378
+2024/03/14 19:43:18 - patchstitcher - INFO - Epoch: [11/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.30577215552330017 - sig_loss: 0.30577215552330017
+2024/03/14 19:48:14 - patchstitcher - INFO - Epoch: [12/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.1830076426267624 - sig_loss: 0.1830076426267624
+2024/03/14 19:51:00 - patchstitcher - INFO - Epoch: [12/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.2162061333656311 - sig_loss: 0.2162061333656311
+2024/03/14 19:53:45 - patchstitcher - INFO - Epoch: [12/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.8629785776138306 - sig_loss: 0.8629785776138306
+2024/03/14 19:56:31 - patchstitcher - INFO - Epoch: [12/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.5271719098091125 - sig_loss: 0.5271719098091125
+2024/03/14 19:59:21 - patchstitcher - INFO - Evaluation Summary: 
++-----------+-----------+-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+
+|     a1    |     a2    |     a3    |  abs_rel  |    rmse   |  log_10  |  rmse_log |   silog   |   sq_rel  |    see    |
++-----------+-----------+-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+
+| 0.9847101 | 0.9951344 | 0.9980653 | 0.0441533 | 1.0483991 | 0.018937 | 0.0693115 | 6.1576749 | 0.0839564 | 0.8453737 |
++-----------+-----------+-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+
+2024/03/14 20:02:13 - patchstitcher - INFO - Epoch: [13/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.7731367349624634 - sig_loss: 0.7731367349624634
+2024/03/14 20:04:58 - patchstitcher - INFO - Epoch: [13/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.6552368402481079 - sig_loss: 0.6552368402481079
+2024/03/14 20:07:44 - patchstitcher - INFO - Epoch: [13/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.7564448118209839 - sig_loss: 0.7564448118209839
+2024/03/14 20:10:30 - patchstitcher - INFO - Epoch: [13/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.3794470429420471 - sig_loss: 0.3794470429420471
+2024/03/14 20:15:26 - patchstitcher - INFO - Epoch: [14/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.2090621292591095 - sig_loss: 0.2090621292591095
+2024/03/14 20:18:12 - patchstitcher - INFO - Epoch: [14/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.2970404624938965 - sig_loss: 0.2970404624938965
+2024/03/14 20:20:58 - patchstitcher - INFO - Epoch: [14/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.5380522012710571 - sig_loss: 0.5380522012710571
+2024/03/14 20:23:44 - patchstitcher - INFO - Epoch: [14/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.24963898956775665 - sig_loss: 0.24963898956775665
+2024/03/14 20:26:34 - patchstitcher - INFO - Evaluation Summary: 
++-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+
+|     a1    |     a2    |     a3    |  abs_rel  |    rmse   |   log_10  |  rmse_log |   silog   |   sq_rel  |    see    |
++-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+
+| 0.9852025 | 0.9951096 | 0.9979956 | 0.0371256 | 1.0237473 | 0.0161318 | 0.0648659 | 6.0501739 | 0.0805912 | 0.8384724 |
++-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+
+2024/03/14 20:29:26 - patchstitcher - INFO - Epoch: [15/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.36880093812942505 - sig_loss: 0.36880093812942505
+2024/03/14 20:32:12 - patchstitcher - INFO - Epoch: [15/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.43111652135849 - sig_loss: 0.43111652135849
+2024/03/14 20:34:58 - patchstitcher - INFO - Epoch: [15/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.933661937713623 - sig_loss: 0.933661937713623
+2024/03/14 20:37:43 - patchstitcher - INFO - Epoch: [15/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.12166339159011841 - sig_loss: 0.12166339159011841
+2024/03/14 20:42:38 - patchstitcher - INFO - Epoch: [16/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.4756861925125122 - sig_loss: 0.4756861925125122
+2024/03/14 20:45:24 - patchstitcher - INFO - Epoch: [16/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.41710591316223145 - sig_loss: 0.41710591316223145
+2024/03/14 20:48:10 - patchstitcher - INFO - Epoch: [16/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.5144650340080261 - sig_loss: 0.5144650340080261
+2024/03/14 20:50:56 - patchstitcher - INFO - Epoch: [16/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.5541351437568665 - sig_loss: 0.5541351437568665
+2024/03/14 20:53:46 - patchstitcher - INFO - Evaluation Summary: 
++---------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+----------+----------+
+|    a1   |     a2    |     a3    |  abs_rel  |    rmse   |   log_10  |  rmse_log |   silog   |  sq_rel  |   see    |
++---------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+----------+----------+
+| 0.98514 | 0.9951155 | 0.9980332 | 0.0368642 | 1.0230569 | 0.0160214 | 0.0646421 | 6.0060532 | 0.079927 | 0.829542 |
++---------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+----------+----------+
+2024/03/14 20:53:46 - patchstitcher - INFO - Saving ckp, but use the inner get_save_dict fuction to get model_dict
+2024/03/14 20:53:46 - patchstitcher - INFO - For saving space. Would you like to save base model several times? :>
+2024/03/14 20:53:47 - patchstitcher - INFO - save checkpoint_16.pth at ./work_dir/patchfusion