diff --git "a/depthanything_vitl_u4k/patchfusion/20240315_175237.log" "b/depthanything_vitl_u4k/patchfusion/20240315_175237.log"
new file mode 100644--- /dev/null
+++ "b/depthanything_vitl_u4k/patchfusion/20240315_175237.log"
@@ -0,0 +1,1604 @@
+2024/03/15 17:52:47 - 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
+------------------------------------------------------------
+
+2024/03/15 17:52:48 - 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',
+        depth_anything=True,
+        distributed=True,
+        do_resize=False,
+        force_keep_ar=True,
+        freeze_midas_bn=True,
+        gpu='NULL',
+        img_size=[
+            392,
+            518,
+        ],
+        inverse_midas=False,
+        log_images_every=0.1,
+        max_depth=80,
+        max_temp=50.0,
+        max_translation=100,
+        memory_efficient=True,
+        midas_model_type='vitl',
+        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/DepthAnything_vitl.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='DA-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',
+        depth_anything=True,
+        distributed=True,
+        do_resize=False,
+        force_keep_ar=True,
+        freeze_midas_bn=True,
+        gpu='NULL',
+        img_size=[
+            392,
+            518,
+        ],
+        inverse_midas=False,
+        log_images_every=0.1,
+        max_depth=80,
+        max_temp=50.0,
+        max_translation=100,
+        memory_efficient=True,
+        midas_model_type='vitl',
+        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/DepthAnything_vitl.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='DA-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,
+        in_channels=[
+            32,
+            256,
+            256,
+            256,
+            256,
+            256,
+        ],
+        n_channels=5,
+        num_patches=[
+            203056,
+            66304,
+            16576,
+            4144,
+            1036,
+            266,
+        ],
+        patch_process_shape=(
+            392,
+            518,
+        ),
+        type='GuidedFusionPatchFusion'),
+    max_depth=80,
+    min_depth=0.001,
+    patch_process_shape=(
+        392,
+        518,
+    ),
+    pretrain_model=[
+        './work_dir/depthanything_vitl_u4k/coarse_pretrain/checkpoint_24.pth',
+        './work_dir/depthanything_vitl_u4k/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',
+    'da',
+    'vitl',
+]
+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=50,
+    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',
+        resize_mode='depth-anything',
+        split='./data/u4k/splits/train.txt',
+        transform_cfg=dict(
+            degree=1.0, network_process_size=[
+                392,
+                518,
+            ], 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',
+        resize_mode='depth-anything',
+        split='./data/u4k/splits/val.txt',
+        transform_cfg=dict(degree=1.0, network_process_size=[
+            392,
+            518,
+        ]),
+        type='UnrealStereo4kDataset'),
+    num_workers=2)
+work_dir = './work_dir/depthanything_vitl_u4k/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',
+    depth_anything=True,
+    distributed=True,
+    do_resize=False,
+    force_keep_ar=True,
+    freeze_midas_bn=True,
+    gpu='NULL',
+    img_size=[
+        392,
+        518,
+    ],
+    inverse_midas=False,
+    log_images_every=0.1,
+    max_depth=80,
+    max_temp=50.0,
+    max_translation=100,
+    memory_efficient=True,
+    midas_model_type='vitl',
+    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/DepthAnything_vitl.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='DA-ZoeDepth',
+    uid='NULL',
+    use_amp=False,
+    use_pretrained_midas=True,
+    use_shared_dict=False,
+    validate_every=0.25,
+    version_name='v1',
+    workers=16)
+
+2024/03/15 17:52:52 - patchstitcher - INFO - Loading deepnet from local::./work_dir/DepthAnything_vitl.pt
+2024/03/15 17:52:52 - patchstitcher - INFO - Current zoedepth.core.prep.resizer is <class 'torch.nn.modules.linear.Identity'>
+2024/03/15 17:52:52 - patchstitcher - INFO - Loading coarse_branch from ./work_dir/depthanything_vitl_u4k/coarse_pretrain/checkpoint_24.pth
+2024/03/15 17:52:53 - patchstitcher - INFO - <All keys matched successfully>
+2024/03/15 17:52:57 - patchstitcher - INFO - Loading deepnet from local::./work_dir/DepthAnything_vitl.pt
+2024/03/15 17:52:58 - patchstitcher - INFO - Current zoedepth.core.prep.resizer is <class 'torch.nn.modules.linear.Identity'>
+2024/03/15 17:52:58 - patchstitcher - INFO - Loading fine_branch from ./work_dir/depthanything_vitl_u4k/fine_pretrain/checkpoint_24.pth
+2024/03/15 17:52:58 - patchstitcher - INFO - <All keys matched successfully>
+2024/03/15 17:52:59 - patchstitcher - INFO - DistributedDataParallel(
+  (module): PatchFusion(
+    (coarse_branch): ZoeDepth(
+      (core): DepthAnythingCore(
+        (core): DPT_DINOv2(
+          (pretrained): DinoVisionTransformer(
+            (patch_embed): PatchEmbed(
+              (proj): Conv2d(3, 1024, kernel_size=(14, 14), stride=(14, 14))
+              (norm): Identity()
+            )
+            (blocks): ModuleList(
+              (0-23): 24 x NestedTensorBlock(
+                (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
+                (attn): MemEffAttention(
+                  (qkv): Linear(in_features=1024, out_features=3072, bias=True)
+                  (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)
+                )
+                (ls1): LayerScale()
+                (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')
+                  (fc2): Linear(in_features=4096, out_features=1024, bias=True)
+                  (drop): Dropout(p=0.0, inplace=False)
+                )
+                (ls2): LayerScale()
+                (drop_path2): Identity()
+              )
+            )
+            (norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
+            (head): Identity()
+          )
+          (depth_head): DPTHead(
+            (projects): ModuleList(
+              (0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
+              (1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1))
+              (2-3): 2 x Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1))
+            )
+            (resize_layers): ModuleList(
+              (0): ConvTranspose2d(256, 256, kernel_size=(4, 4), stride=(4, 4))
+              (1): ConvTranspose2d(512, 512, kernel_size=(2, 2), stride=(2, 2))
+              (2): Identity()
+              (3): 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(
+                (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+                (resConfUnit1): ResidualConvUnit(
+                  (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(
+                  (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(
+                (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+                (resConfUnit1): ResidualConvUnit(
+                  (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(
+                  (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(
+                (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+                (resConfUnit1): ResidualConvUnit(
+                  (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(
+                  (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(
+                (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+                (resConfUnit1): ResidualConvUnit(
+                  (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(
+                  (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_conv1): Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              (output_conv2): Sequential(
+                (0): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
+                (3): ReLU(inplace=True)
+                (4): 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): DepthAnythingCore(
+        (core): DPT_DINOv2(
+          (pretrained): DinoVisionTransformer(
+            (patch_embed): PatchEmbed(
+              (proj): Conv2d(3, 1024, kernel_size=(14, 14), stride=(14, 14))
+              (norm): Identity()
+            )
+            (blocks): ModuleList(
+              (0-23): 24 x NestedTensorBlock(
+                (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
+                (attn): MemEffAttention(
+                  (qkv): Linear(in_features=1024, out_features=3072, bias=True)
+                  (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)
+                )
+                (ls1): LayerScale()
+                (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')
+                  (fc2): Linear(in_features=4096, out_features=1024, bias=True)
+                  (drop): Dropout(p=0.0, inplace=False)
+                )
+                (ls2): LayerScale()
+                (drop_path2): Identity()
+              )
+            )
+            (norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
+            (head): Identity()
+          )
+          (depth_head): DPTHead(
+            (projects): ModuleList(
+              (0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
+              (1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1))
+              (2-3): 2 x Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1))
+            )
+            (resize_layers): ModuleList(
+              (0): ConvTranspose2d(256, 256, kernel_size=(4, 4), stride=(4, 4))
+              (1): ConvTranspose2d(512, 512, kernel_size=(2, 2), stride=(2, 2))
+              (2): Identity()
+              (3): 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(
+                (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+                (resConfUnit1): ResidualConvUnit(
+                  (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(
+                  (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(
+                (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+                (resConfUnit1): ResidualConvUnit(
+                  (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(
+                  (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(
+                (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+                (resConfUnit1): ResidualConvUnit(
+                  (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(
+                  (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(
+                (out_conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+                (resConfUnit1): ResidualConvUnit(
+                  (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(
+                  (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_conv1): Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              (output_conv2): Sequential(
+                (0): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
+                (3): ReLU(inplace=True)
+                (4): 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)
+      )
+    )
+  )
+)
+2024/03/15 17:53:06 - patchstitcher - INFO - successfully init trainer
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.fusion_conv_list.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.fusion_conv_list.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.fusion_conv_list.1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.fusion_conv_list.1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.fusion_conv_list.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.fusion_conv_list.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.fusion_conv_list.3.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.fusion_conv_list.3.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.fusion_conv_list.4.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.fusion_conv_list.4.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.fusion_conv_list.5.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.fusion_conv_list.5.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.inc.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.inc.double_conv.1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.inc.double_conv.1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.inc.double_conv.3.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.inc.double_conv.4.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.inc.double_conv.4.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.0.maxpool_conv.1.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.0.maxpool_conv.1.double_conv.1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.0.maxpool_conv.1.double_conv.1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.0.maxpool_conv.1.double_conv.3.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.0.maxpool_conv.1.double_conv.4.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.0.maxpool_conv.1.double_conv.4.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.1.maxpool_conv.1.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.1.maxpool_conv.1.double_conv.1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.1.maxpool_conv.1.double_conv.1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.1.maxpool_conv.1.double_conv.3.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.1.maxpool_conv.1.double_conv.4.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.1.maxpool_conv.1.double_conv.4.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.2.maxpool_conv.1.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.2.maxpool_conv.1.double_conv.1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.2.maxpool_conv.1.double_conv.1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.2.maxpool_conv.1.double_conv.3.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.2.maxpool_conv.1.double_conv.4.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.2.maxpool_conv.1.double_conv.4.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.3.maxpool_conv.1.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.3.maxpool_conv.1.double_conv.1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.3.maxpool_conv.1.double_conv.1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.3.maxpool_conv.1.double_conv.3.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.3.maxpool_conv.1.double_conv.4.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.3.maxpool_conv.1.double_conv.4.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.4.maxpool_conv.1.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.4.maxpool_conv.1.double_conv.1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.4.maxpool_conv.1.double_conv.1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.4.maxpool_conv.1.double_conv.3.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.4.maxpool_conv.1.double_conv.4.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.down_conv_list.4.maxpool_conv.1.double_conv.4.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.0.conv.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.0.conv.double_conv.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.0.conv.double_conv.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.0.conv.double_conv.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.1.conv.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.1.conv.double_conv.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.1.conv.double_conv.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.1.conv.double_conv.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.2.conv.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.2.conv.double_conv.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.2.conv.double_conv.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.2.conv.double_conv.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.3.conv.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.3.conv.double_conv.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.3.conv.double_conv.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.3.conv.double_conv.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.4.conv.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.4.conv.double_conv.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.4.conv.double_conv.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.up_conv_list.4.conv.double_conv.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.absolute_pos_embed
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.0.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.1.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.2.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer.blocks.3.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer_norm.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.g2l_layer_norm.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.embed_proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.0.embed_proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.absolute_pos_embed
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.0.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.1.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.2.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer.blocks.3.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer_norm.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.g2l_layer_norm.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.embed_proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.1.embed_proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.absolute_pos_embed
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.0.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.1.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer.blocks.2.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer_norm.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.g2l_layer_norm.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.embed_proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.2.embed_proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.absolute_pos_embed
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.0.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.1.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer.blocks.2.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer_norm.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.g2l_layer_norm.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.embed_proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.3.embed_proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.absolute_pos_embed
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.0.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer.blocks.1.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer_norm.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.g2l_layer_norm.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.embed_proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.4.embed_proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.absolute_pos_embed
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.0.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.norm1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.norm1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.attn.relative_position_bias_table
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.attn.qkv.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.attn.qkv.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.attn.proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.attn.proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.norm2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.norm2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.mlp.fc1.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.mlp.fc1.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.mlp.fc2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer.blocks.1.mlp.fc2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer_norm.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.g2l_layer_norm.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.embed_proj.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.g2l_list.5.embed_proj.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.0.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.0.double_conv.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.0.double_conv.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.0.double_conv.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.1.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.1.double_conv.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.1.double_conv.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.1.double_conv.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.2.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.2.double_conv.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.2.double_conv.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.2.double_conv.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.3.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.3.double_conv.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.3.double_conv.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.3.double_conv.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.4.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.4.double_conv.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.4.double_conv.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.4.double_conv.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.5.double_conv.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.5.double_conv.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.5.double_conv.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.guided_fusion.convs.5.double_conv.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.seed_bin_regressor._net.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.seed_bin_regressor._net.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.seed_bin_regressor._net.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.seed_bin_regressor._net.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.seed_projector._net.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.seed_projector._net.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.seed_projector._net.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.seed_projector._net.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.0._net.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.0._net.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.0._net.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.0._net.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.1._net.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.1._net.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.1._net.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.1._net.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.2._net.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.2._net.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.2._net.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.2._net.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.3._net.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.3._net.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.3._net.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.projectors.3._net.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.0._net.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.0._net.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.0._net.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.0._net.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.1._net.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.1._net.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.1._net.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.1._net.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.2._net.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.2._net.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.2._net.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.2._net.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.3._net.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.3._net.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.3._net.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.attractors.3._net.2.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.conditional_log_binomial.mlp.0.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.conditional_log_binomial.mlp.0.bias
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.conditional_log_binomial.mlp.2.weight
+2024/03/15 17:53:06 - patchstitcher - INFO - training param: module.conditional_log_binomial.mlp.2.bias
+2024/03/15 17:57:49 - patchstitcher - INFO - Epoch: [01/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 6.651620864868164 - sig_loss: 6.651620864868164
+2024/03/15 18:01:09 - patchstitcher - INFO - Epoch: [01/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 3.1729226112365723 - sig_loss: 3.1729226112365723
+2024/03/15 18:04:30 - patchstitcher - INFO - Epoch: [01/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 6.4036359786987305 - sig_loss: 6.4036359786987305
+2024/03/15 18:07:51 - patchstitcher - INFO - Epoch: [01/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 1.5950872898101807 - sig_loss: 1.5950872898101807
+2024/03/15 18:14:41 - patchstitcher - INFO - Epoch: [02/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.5556060075759888 - sig_loss: 0.5556060075759888
+2024/03/15 18:18:02 - patchstitcher - INFO - Epoch: [02/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 1.4476476907730103 - sig_loss: 1.4476476907730103
+2024/03/15 18:21:23 - patchstitcher - INFO - Epoch: [02/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.7769662141799927 - sig_loss: 0.7769662141799927
+2024/03/15 18:24:44 - patchstitcher - INFO - Epoch: [02/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 1.0473182201385498 - sig_loss: 1.0473182201385498
+2024/03/15 18:28:21 - patchstitcher - INFO - Evaluation Summary: 
++-----------+----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+
+|     a1    |    a2    |     a3    |  abs_rel  |    rmse   |   log_10  |  rmse_log |   silog   |   sq_rel  |    see    |
++-----------+----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+
+| 0.9604923 | 0.992972 | 0.9974152 | 0.0768845 | 1.3931862 | 0.0329559 | 0.1041152 | 8.8729713 | 0.1381766 | 1.0569959 |
++-----------+----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+
+2024/03/15 18:31:46 - patchstitcher - INFO - Epoch: [03/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.40465447306632996 - sig_loss: 0.40465447306632996
+2024/03/15 18:35:08 - patchstitcher - INFO - Epoch: [03/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 1.1749241352081299 - sig_loss: 1.1749241352081299
+2024/03/15 18:38:29 - patchstitcher - INFO - Epoch: [03/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 1.2686662673950195 - sig_loss: 1.2686662673950195
+2024/03/15 18:41:50 - patchstitcher - INFO - Epoch: [03/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.711976170539856 - sig_loss: 0.711976170539856
+2024/03/15 18:47:46 - patchstitcher - INFO - Epoch: [04/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.5024728775024414 - sig_loss: 0.5024728775024414
+2024/03/15 18:51:07 - patchstitcher - INFO - Epoch: [04/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.527965784072876 - sig_loss: 0.527965784072876
+2024/03/15 18:54:28 - patchstitcher - INFO - Epoch: [04/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.8440424203872681 - sig_loss: 0.8440424203872681
+2024/03/15 18:57:48 - patchstitcher - INFO - Epoch: [04/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.26558583974838257 - sig_loss: 0.26558583974838257
+2024/03/15 19:01:10 - patchstitcher - INFO - Evaluation Summary: 
++-----------+----------+-----------+----------+----------+-----------+-----------+---------+-----------+-----------+
+|     a1    |    a2    |     a3    | abs_rel  |   rmse   |   log_10  |  rmse_log |  silog  |   sq_rel  |    see    |
++-----------+----------+-----------+----------+----------+-----------+-----------+---------+-----------+-----------+
+| 0.9812026 | 0.994635 | 0.9978743 | 0.059769 | 1.174001 | 0.0255657 | 0.0845318 | 7.16214 | 0.1029762 | 0.9235216 |
++-----------+----------+-----------+----------+----------+-----------+-----------+---------+-----------+-----------+
+2024/03/15 19:04:36 - patchstitcher - INFO - Epoch: [05/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.6908500790596008 - sig_loss: 0.6908500790596008
+2024/03/15 19:07:57 - patchstitcher - INFO - Epoch: [05/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.33774641156196594 - sig_loss: 0.33774641156196594
+2024/03/15 19:11:17 - patchstitcher - INFO - Epoch: [05/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.6475552916526794 - sig_loss: 0.6475552916526794
+2024/03/15 19:14:38 - patchstitcher - INFO - Epoch: [05/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.7433701753616333 - sig_loss: 0.7433701753616333
+2024/03/15 19:20:34 - patchstitcher - INFO - Epoch: [06/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.999753475189209 - sig_loss: 0.999753475189209
+2024/03/15 19:23:55 - patchstitcher - INFO - Epoch: [06/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.8219634890556335 - sig_loss: 0.8219634890556335
+2024/03/15 19:27:15 - patchstitcher - INFO - Epoch: [06/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.4194517433643341 - sig_loss: 0.4194517433643341
+2024/03/15 19:30:36 - patchstitcher - INFO - Epoch: [06/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.7954123616218567 - sig_loss: 0.7954123616218567
+2024/03/15 19:33:58 - patchstitcher - INFO - Evaluation Summary: 
++-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+----------+-----------+
+|     a1    |     a2    |     a3    | abs_rel  |    rmse   |   log_10  |  rmse_log |   silog   |  sq_rel  |    see    |
++-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+----------+-----------+
+| 0.9570371 | 0.9941043 | 0.9978197 | 0.101201 | 1.2812451 | 0.0417833 | 0.1185188 | 8.3019764 | 0.123725 | 1.0220292 |
++-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+----------+-----------+
+2024/03/15 19:37:26 - patchstitcher - INFO - Epoch: [07/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.47829562425613403 - sig_loss: 0.47829562425613403
+2024/03/15 19:40:47 - patchstitcher - INFO - Epoch: [07/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 1.0946928262710571 - sig_loss: 1.0946928262710571
+2024/03/15 19:44:07 - patchstitcher - INFO - Epoch: [07/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.653084397315979 - sig_loss: 0.653084397315979
+2024/03/15 19:47:28 - patchstitcher - INFO - Epoch: [07/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.49332454800605774 - sig_loss: 0.49332454800605774
+2024/03/15 19:53:23 - patchstitcher - INFO - Epoch: [08/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.4712163209915161 - sig_loss: 0.4712163209915161
+2024/03/15 19:56:43 - patchstitcher - INFO - Epoch: [08/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.852905809879303 - sig_loss: 0.852905809879303
+2024/03/15 20:00:04 - patchstitcher - INFO - Epoch: [08/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.7322371602058411 - sig_loss: 0.7322371602058411
+2024/03/15 20:03:24 - patchstitcher - INFO - Epoch: [08/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.8382786512374878 - sig_loss: 0.8382786512374878
+2024/03/15 20:06:46 - patchstitcher - INFO - Evaluation Summary: 
++-----------+-----------+-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+
+|     a1    |     a2    |     a3    |  abs_rel  |    rmse   |  log_10  |  rmse_log |   silog   |   sq_rel  |    see    |
++-----------+-----------+-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+
+| 0.9800802 | 0.9948133 | 0.9979888 | 0.0667494 | 1.1031989 | 0.027872 | 0.0859998 | 6.1991318 | 0.0983083 | 0.9544899 |
++-----------+-----------+-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+
+2024/03/15 20:10:12 - patchstitcher - INFO - Epoch: [09/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.6576782464981079 - sig_loss: 0.6576782464981079
+2024/03/15 20:13:33 - patchstitcher - INFO - Epoch: [09/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.3798004686832428 - sig_loss: 0.3798004686832428
+2024/03/15 20:16:53 - patchstitcher - INFO - Epoch: [09/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.27597683668136597 - sig_loss: 0.27597683668136597
+2024/03/15 20:20:14 - patchstitcher - INFO - Epoch: [09/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.4274792969226837 - sig_loss: 0.4274792969226837
+2024/03/15 20:26:10 - patchstitcher - INFO - Epoch: [10/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.28685206174850464 - sig_loss: 0.28685206174850464
+2024/03/15 20:29:30 - patchstitcher - INFO - Epoch: [10/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.6088235378265381 - sig_loss: 0.6088235378265381
+2024/03/15 20:32:51 - patchstitcher - INFO - Epoch: [10/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.8431264758110046 - sig_loss: 0.8431264758110046
+2024/03/15 20:36:11 - patchstitcher - INFO - Epoch: [10/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.4401911497116089 - sig_loss: 0.4401911497116089
+2024/03/15 20:39:33 - patchstitcher - INFO - Evaluation Summary: 
++-----------+----------+-----------+-----------+-----------+-----------+-----------+----------+-----------+----------+
+|     a1    |    a2    |     a3    |  abs_rel  |    rmse   |   log_10  |  rmse_log |  silog   |   sq_rel  |   see    |
++-----------+----------+-----------+-----------+-----------+-----------+-----------+----------+-----------+----------+
+| 0.9842327 | 0.995032 | 0.9980113 | 0.0420645 | 1.0650526 | 0.0181017 | 0.0686697 | 6.248743 | 0.0888892 | 0.887989 |
++-----------+----------+-----------+-----------+-----------+-----------+-----------+----------+-----------+----------+
+2024/03/15 20:42:58 - patchstitcher - INFO - Epoch: [11/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.4226158559322357 - sig_loss: 0.4226158559322357
+2024/03/15 20:46:19 - patchstitcher - INFO - Epoch: [11/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.5998555421829224 - sig_loss: 0.5998555421829224
+2024/03/15 20:49:39 - patchstitcher - INFO - Epoch: [11/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.8624639511108398 - sig_loss: 0.8624639511108398
+2024/03/15 20:52:59 - patchstitcher - INFO - Epoch: [11/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.5691335797309875 - sig_loss: 0.5691335797309875
+2024/03/15 20:58:54 - patchstitcher - INFO - Epoch: [12/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.3543495535850525 - sig_loss: 0.3543495535850525
+2024/03/15 21:02:14 - patchstitcher - INFO - Epoch: [12/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.17586150765419006 - sig_loss: 0.17586150765419006
+2024/03/15 21:05:35 - patchstitcher - INFO - Epoch: [12/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.8585277795791626 - sig_loss: 0.8585277795791626
+2024/03/15 21:08:55 - patchstitcher - INFO - Epoch: [12/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.39675745368003845 - sig_loss: 0.39675745368003845
+2024/03/15 21:12:17 - patchstitcher - INFO - Evaluation Summary: 
++-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+
+|     a1    |     a2    |     a3    |  abs_rel  |    rmse   |   log_10  |  rmse_log |   silog   |   sq_rel  |    see    |
++-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+
+| 0.9845838 | 0.9949521 | 0.9980043 | 0.0384732 | 1.0613158 | 0.0166137 | 0.0663726 | 6.1042054 | 0.0890013 | 0.8891889 |
++-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+
+2024/03/15 21:15:43 - patchstitcher - INFO - Epoch: [13/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 1.4550189971923828 - sig_loss: 1.4550189971923828
+2024/03/15 21:19:03 - patchstitcher - INFO - Epoch: [13/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.4285925626754761 - sig_loss: 0.4285925626754761
+2024/03/15 21:22:24 - patchstitcher - INFO - Epoch: [13/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.5604073405265808 - sig_loss: 0.5604073405265808
+2024/03/15 21:25:45 - patchstitcher - INFO - Epoch: [13/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.7231113314628601 - sig_loss: 0.7231113314628601
+2024/03/15 21:31:38 - patchstitcher - INFO - Epoch: [14/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.22688111662864685 - sig_loss: 0.22688111662864685
+2024/03/15 21:34:58 - patchstitcher - INFO - Epoch: [14/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.4432392120361328 - sig_loss: 0.4432392120361328
+2024/03/15 21:38:19 - patchstitcher - INFO - Epoch: [14/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.5041521191596985 - sig_loss: 0.5041521191596985
+2024/03/15 21:41:40 - patchstitcher - INFO - Epoch: [14/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.6649416089057922 - sig_loss: 0.6649416089057922
+2024/03/15 21:45:01 - patchstitcher - INFO - Evaluation Summary: 
++-----------+-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+----------+
+|     a1    |     a2    |     a3    |  abs_rel  |   rmse   |   log_10  |  rmse_log |   silog   |   sq_rel  |   see    |
++-----------+-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+----------+
+| 0.9851979 | 0.9949358 | 0.9979829 | 0.0377008 | 1.029974 | 0.0165044 | 0.0661251 | 6.0282001 | 0.0796015 | 0.812903 |
++-----------+-----------+-----------+-----------+----------+-----------+-----------+-----------+-----------+----------+
+2024/03/15 21:48:25 - patchstitcher - INFO - Epoch: [15/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.41866496205329895 - sig_loss: 0.41866496205329895
+2024/03/15 21:51:46 - patchstitcher - INFO - Epoch: [15/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.8762396574020386 - sig_loss: 0.8762396574020386
+2024/03/15 21:55:06 - patchstitcher - INFO - Epoch: [15/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 2.038621664047241 - sig_loss: 2.038621664047241
+2024/03/15 21:58:27 - patchstitcher - INFO - Epoch: [15/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 0.2506561875343323 - sig_loss: 0.2506561875343323
+2024/03/15 22:04:22 - patchstitcher - INFO - Epoch: [16/16] - Step: [00100/00475] - Time: [1/1] - Total Loss: 0.37795141339302063 - sig_loss: 0.37795141339302063
+2024/03/15 22:07:42 - patchstitcher - INFO - Epoch: [16/16] - Step: [00200/00475] - Time: [1/1] - Total Loss: 0.24302588403224945 - sig_loss: 0.24302588403224945
+2024/03/15 22:11:03 - patchstitcher - INFO - Epoch: [16/16] - Step: [00300/00475] - Time: [1/1] - Total Loss: 0.4261029362678528 - sig_loss: 0.4261029362678528
+2024/03/15 22:14:24 - patchstitcher - INFO - Epoch: [16/16] - Step: [00400/00475] - Time: [1/1] - Total Loss: 1.648262858390808 - sig_loss: 1.648262858390808
+2024/03/15 22:17:45 - patchstitcher - INFO - Evaluation Summary: 
++-----------+----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+
+|     a1    |    a2    |     a3    |  abs_rel  |    rmse   |   log_10  |  rmse_log |   silog   |   sq_rel  |    see    |
++-----------+----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+
+| 0.9852235 | 0.994962 | 0.9979886 | 0.0368362 | 1.0233804 | 0.0160672 | 0.0651711 | 5.9528971 | 0.0792726 | 0.8155836 |
++-----------+----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+-----------+
+2024/03/15 22:17:45 - patchstitcher - INFO - Saving ckp, but use the inner get_save_dict fuction to get model_dict
+2024/03/15 22:17:45 - patchstitcher - INFO - For saving space. Would you like to save base model several times? :>
+2024/03/15 22:17:46 - patchstitcher - INFO - save checkpoint_16.pth at ./work_dir/depthanything_vitl_u4k/patchfusion