Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ResNet34_confusion_matrix.png filter=lfs diff=lfs merge=lfs -text
+Swin_confusion_matrix.png filter=lfs diff=lfs merge=lfs -text
+ViT-H_confusion_matrix.png filter=lfs diff=lfs merge=lfs -text
+ViT_confusion_matrix.png filter=lfs diff=lfs merge=lfs -text

ResNet-34/config.json

@@ -0,0 +1,81 @@
+{
+  "_name_or_path": "/home/yoru/.cache/huggingface/hub/models--microsoft--resnet-34/snapshots/4d180fbdc81b4d5d4eaa86ab89bdd669200dd477",
+  "architectures": [
+    "ResNetForImageClassification"
+  ],
+  "depths": [
+    3,
+    4,
+    6,
+    3
+  ],
+  "downsample_in_bottleneck": false,
+  "downsample_in_first_stage": false,
+  "embedding_size": 64,
+  "hidden_act": "relu",
+  "hidden_sizes": [
+    64,
+    128,
+    256,
+    512
+  ],
+  "id2label": {
+    "0": "Civet",
+    "1": "Emerald_Dove",
+    "2": "Foemosan_Gem-faced_Civet",
+    "3": "Formosan_Ferret-badger",
+    "4": "Formosan_Sambar_Deer",
+    "5": "Formosan_Serow",
+    "6": "Formosan_Sika_Deer",
+    "7": "Formosan_Yellow-throated_Marten",
+    "8": "Formosan_macaque",
+    "9": "Formosan_wild_boar",
+    "10": "Mouse",
+    "11": "Reeves's_Muntjac",
+    "12": "Swinhoe's_Pheasant",
+    "13": "Taiwan_Partridge",
+    "14": "Urva",
+    "15": "cat",
+    "16": "dog",
+    "17": "squirrel"
+  },
+  "label2id": {
+    "Civet": 0,
+    "Emerald_Dove": 1,
+    "Foemosan_Gem-faced_Civet": 2,
+    "Formosan_Ferret-badger": 3,
+    "Formosan_Sambar_Deer": 4,
+    "Formosan_Serow": 5,
+    "Formosan_Sika_Deer": 6,
+    "Formosan_Yellow-throated_Marten": 7,
+    "Formosan_macaque": 8,
+    "Formosan_wild_boar": 9,
+    "Mouse": 10,
+    "Reeves's_Muntjac": 11,
+    "Swinhoe's_Pheasant": 12,
+    "Taiwan_Partridge": 13,
+    "Urva": 14,
+    "cat": 15,
+    "dog": 16,
+    "squirrel": 17
+  },
+  "layer_type": "basic",
+  "model_type": "resnet",
+  "num_channels": 3,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "problem_type": "single_label_classification",
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2"
+}

ResNet-34/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b70dec781ad19d03329db7a9ae0d521f37358eab3c0256d0c5c2384a6943aa1c
+size 85272184

ResNet-34/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b07c313a10342e115198b94a6f4d80db196d10022fe20caa6ce1d2863d4ca5df
+size 4984

Swin Transformer/config.json

@@ -0,0 +1,93 @@
+{
+  "_name_or_path": "/home/yoru/.cache/huggingface/hub/models--microsoft--swin-base-patch4-window12-384/snapshots/0c86592b628ac7b09a19ab701c0a76f00b33ce25",
+  "architectures": [
+    "SwinForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    18,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 128,
+  "encoder_stride": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Civet",
+    "1": "Emerald_Dove",
+    "2": "Foemosan_Gem-faced_Civet",
+    "3": "Formosan_Ferret-badger",
+    "4": "Formosan_Sambar_Deer",
+    "5": "Formosan_Serow",
+    "6": "Formosan_Sika_Deer",
+    "7": "Formosan_Yellow-throated_Marten",
+    "8": "Formosan_macaque",
+    "9": "Formosan_wild_boar",
+    "10": "Mouse",
+    "11": "Reeves's_Muntjac",
+    "12": "Swinhoe's_Pheasant",
+    "13": "Taiwan_Partridge",
+    "14": "Urva",
+    "15": "cat",
+    "16": "dog",
+    "17": "squirrel"
+  },
+  "image_size": 384,
+  "initializer_range": 0.02,
+  "label2id": {
+    "Civet": 0,
+    "Emerald_Dove": 1,
+    "Foemosan_Gem-faced_Civet": 2,
+    "Formosan_Ferret-badger": 3,
+    "Formosan_Sambar_Deer": 4,
+    "Formosan_Serow": 5,
+    "Formosan_Sika_Deer": 6,
+    "Formosan_Yellow-throated_Marten": 7,
+    "Formosan_macaque": 8,
+    "Formosan_wild_boar": 9,
+    "Mouse": 10,
+    "Reeves's_Muntjac": 11,
+    "Swinhoe's_Pheasant": 12,
+    "Taiwan_Partridge": 13,
+    "Urva": 14,
+    "cat": 15,
+    "dog": 16,
+    "squirrel": 17
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swin",
+  "num_channels": 3,
+  "num_heads": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "num_layers": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "path_norm": true,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "use_absolute_embeddings": false,
+  "window_size": 12
+}

Swin Transformer/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2ee9c3f174708bc65bb96c4f31927074c7ac5dea8cf2815fcf67c770931383
+size 351626336

Swin Transformer/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e46ad23d99dee0cddcc962376b4502627f79b321fafab7f58b624f993a39207
+size 5048

ViT-H/config.json

@@ -0,0 +1,96 @@
+{
+  "_name_or_path": "/home/yoru/.cache/huggingface/hub/models--google--vit-hybrid-base-bit-384/snapshots/e8cc9d5fe904240b3b0035837daeabff06202bf2",
+  "architectures": [
+    "ViTHybridForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "backbone": null,
+  "backbone_config": {
+    "depths": [
+      3,
+      4,
+      9
+    ],
+    "embedding_dynamic_padding": true,
+    "global_padding": "SAME",
+    "layer_type": "bottleneck",
+    "model_type": "bit",
+    "out_features": [
+      "stage3"
+    ],
+    "out_indices": [
+      3
+    ],
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3"
+    ]
+  },
+  "backbone_featmap_shape": [
+    1,
+    1024,
+    24,
+    24
+  ],
+  "backbone_kwargs": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Civet",
+    "1": "Emerald_Dove",
+    "2": "Foemosan_Gem-faced_Civet",
+    "3": "Formosan_Ferret-badger",
+    "4": "Formosan_Sambar_Deer",
+    "5": "Formosan_Serow",
+    "6": "Formosan_Sika_Deer",
+    "7": "Formosan_Yellow-throated_Marten",
+    "8": "Formosan_macaque",
+    "9": "Formosan_wild_boar",
+    "10": "Mouse",
+    "11": "Reeves's_Muntjac",
+    "12": "Swinhoe's_Pheasant",
+    "13": "Taiwan_Partridge",
+    "14": "Urva",
+    "15": "cat",
+    "16": "dog",
+    "17": "squirrel"
+  },
+  "image_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Civet": 0,
+    "Emerald_Dove": 1,
+    "Foemosan_Gem-faced_Civet": 2,
+    "Formosan_Ferret-badger": 3,
+    "Formosan_Sambar_Deer": 4,
+    "Formosan_Serow": 5,
+    "Formosan_Sika_Deer": 6,
+    "Formosan_Yellow-throated_Marten": 7,
+    "Formosan_macaque": 8,
+    "Formosan_wild_boar": 9,
+    "Mouse": 10,
+    "Reeves's_Muntjac": 11,
+    "Swinhoe's_Pheasant": 12,
+    "Taiwan_Partridge": 13,
+    "Urva": 14,
+    "cat": 15,
+    "dog": 16,
+    "squirrel": 17
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit-hybrid",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 1,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "use_pretrained_backbone": false,
+  "use_timm_backbone": false
+}

ViT-H/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7491315150ca2f0a6250665fc7e93c8d9d2fd228fe60ba0e4e0fee60445738e
+size 392830144

ViT-H/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d75dccf6bdaacd2033d3f2c8a4abaf9657ebb143edb287c77947fdb27bd162a0
+size 5048

ViT/config.json

@@ -0,0 +1,64 @@
+{
+  "_name_or_path": "/home/yoru/.cache/huggingface/hub/models--google--vit-large-patch32-384/snapshots/a2b30ad36d02e99f045cd2ecfc71e0ae16991efa",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Civet",
+    "1": "Emerald_Dove",
+    "2": "Foemosan_Gem-faced_Civet",
+    "3": "Formosan_Ferret-badger",
+    "4": "Formosan_Sambar_Deer",
+    "5": "Formosan_Serow",
+    "6": "Formosan_Sika_Deer",
+    "7": "Formosan_Yellow-throated_Marten",
+    "8": "Formosan_macaque",
+    "9": "Formosan_wild_boar",
+    "10": "Mouse",
+    "11": "Reeves's_Muntjac",
+    "12": "Swinhoe's_Pheasant",
+    "13": "Taiwan_Partridge",
+    "14": "Urva",
+    "15": "cat",
+    "16": "dog",
+    "17": "squirrel"
+  },
+  "image_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Civet": 0,
+    "Emerald_Dove": 1,
+    "Foemosan_Gem-faced_Civet": 2,
+    "Formosan_Ferret-badger": 3,
+    "Formosan_Sambar_Deer": 4,
+    "Formosan_Serow": 5,
+    "Formosan_Sika_Deer": 6,
+    "Formosan_Yellow-throated_Marten": 7,
+    "Formosan_macaque": 8,
+    "Formosan_wild_boar": 9,
+    "Mouse": 10,
+    "Reeves's_Muntjac": 11,
+    "Swinhoe's_Pheasant": 12,
+    "Taiwan_Partridge": 13,
+    "Urva": 14,
+    "cat": 15,
+    "dog": 16,
+    "squirrel": 17
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "patch_size": 32,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2"
+}

ViT/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:479ef613d5a93038958e5f3593f6c5144a3bec3a2236e19169489ab195503883
+size 1222551088

ViT/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db72d67a082104ba74e3bfd9b794ddbe90cfde69616db9667e6d8f8ce4d67b9
+size 4984