Training in progress, step 24

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "MCG-NJU/videomae-base",
+  "architectures": [
+    "VideoMAEForVideoClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "decoder_hidden_size": 384,
+  "decoder_intermediate_size": 1536,
+  "decoder_num_attention_heads": 6,
+  "decoder_num_hidden_layers": 4,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Dish",
+    "1": "DrinkandSnack",
+    "2": "ElectricalAppliance",
+    "3": "FurnitureandDecoration",
+    "4": "Gadgets",
+    "5": "Housework",
+    "6": "LeisureandPerformance",
+    "7": "NursingandCare",
+    "8": "PetsandFruit",
+    "9": "ScienceandCraft",
+    "10": "Sport",
+    "11": "Vehicle"
+  },
+  "ignore_mismatched_sizes": true,
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Dish": 0,
+    "DrinkandSnack": 1,
+    "ElectricalAppliance": 2,
+    "FurnitureandDecoration": 3,
+    "Gadgets": 4,
+    "Housework": 5,
+    "LeisureandPerformance": 6,
+    "NursingandCare": 7,
+    "PetsandFruit": 8,
+    "ScienceandCraft": 9,
+    "Sport": 10,
+    "Vehicle": 11
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "videomae",
+  "norm_pix_loss": true,
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_frames": 16,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "tubelet_size": 2,
+  "use_mean_pooling": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02570310724214346650d5db45d557639b95cd819d6ba01f47067013f9d8306e
+size 344968096

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "VideoMAEFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "VideoMAEImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a78db91faed817cb114ca0921e73e9b2baf1b95a5e02dd0d2fff5380b6f0fdb8
+size 4728