Training in progress, epoch 0

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,65 @@
+{
+  "_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": "tap dancing",
+    "1": "breakdancing",
+    "2": "belly dancing",
+    "3": "dancing charleston",
+    "4": "dancing ballet",
+    "5": "square dancing",
+    "6": "jumpstyle dancing",
+    "7": "salsa dancing",
+    "8": "robot dancing",
+    "9": "country line dancing",
+    "10": "dancing macarena",
+    "11": "mosh pit dancing",
+    "12": "dancing gangnam style",
+    "13": "swing dancing",
+    "14": "tango dancing"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "belly dancing": 2,
+    "breakdancing": 1,
+    "country line dancing": 9,
+    "dancing ballet": 4,
+    "dancing charleston": 3,
+    "dancing gangnam style": 12,
+    "dancing macarena": 10,
+    "jumpstyle dancing": 6,
+    "mosh pit dancing": 11,
+    "robot dancing": 8,
+    "salsa dancing": 7,
+    "square dancing": 5,
+    "swing dancing": 13,
+    "tango dancing": 14,
+    "tap dancing": 0
+  },
+  "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": "4.30.1",
+  "tubelet_size": 2,
+  "use_mean_pooling": false
+}

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
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95f301ebedd72dd60c4e5e6b1a056e17a1e905464265e8086132277a5607bf0
+size 345018933

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e859548f37d8fcf1dadafacc79a9e05b2c2b307146539e6a8a2236d720c1c92
+size 3963