Upload checkpoints

config.json

@@ -0,0 +1,171 @@
+{
+  "coarse_branch": {
+    "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": "vitb",
+    "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_vitb.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": {
+    "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": "vitb",
+    "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_vitb.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": {
+    "g2l": true,
+    "in_channels": [
+      32,
+      128,
+      128,
+      128,
+      128,
+      128
+    ],
+    "n_channels": 5,
+    "num_patches": [
+      203056,
+      66304,
+      16576,
+      4144,
+      1036,
+      266
+    ],
+    "patch_process_shape": [
+      392,
+      518
+    ],
+    "type": "GuidedFusionPatchFusion"
+  },
+  "image_raw_shape": [
+    2160,
+    3840
+  ],
+  "max_depth": 80,
+  "min_depth": 0.001,
+  "patch_process_shape": [
+    392,
+    518
+  ],
+  "patch_split_num": [
+    4,
+    4
+  ],
+  "pretrain_model": [
+    "./work_dir/depthanything_vitb_u4k/coarse_pretrain/checkpoint_24.pth",
+    "./work_dir/depthanything_vitb_u4k/fine_pretrain/checkpoint_24.pth"
+  ],
+  "sigloss": {
+    "type": "SILogLoss"
+  },
+  "transformers_version": "4.36.2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a0f2b998077dbaddc6c8e15a1e4088cd072fd507d5cce14d12a7452b35be4fa
+size 923819968