Model save

README.md

@@ -15,13 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.2040
-- eval_accuracy: 0.9249
-- eval_runtime: 182.4036
-- eval_samples_per_second: 4.962
-- eval_steps_per_second: 0.625
-- epoch: 0.1026
-- step: 40
+- eval_loss: 0.1918
+- eval_accuracy: 0.9470
+- eval_runtime: 191.3454
+- eval_samples_per_second: 4.73
+- eval_steps_per_second: 0.596
+- epoch: 3.1026
+- step: 160
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2677d6a260c084998c475c184ce45f48c52ad39e7e3b8053d26dc208f26248d2
+oid sha256:f0a22a62ba075f5222407b1ad3a8f4f9200d7aff7129a80dbdde6a8598498685
 size 344961984

saved-models/config.json

@@ -0,0 +1,55 @@
+{
+  "_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": "Tadasana",
+    "1": "Padmasana",
+    "2": "Head_To_Knee_Pose",
+    "3": "Bhujangasana",
+    "4": "Virbhadrasana1",
+    "5": "Setubandhasana",
+    "6": "Dhanurasana",
+    "7": "Shavasana",
+    "8": "Vrikshasana",
+    "9": "Trikonasana"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Bhujangasana": 3,
+    "Dhanurasana": 6,
+    "Head_To_Knee_Pose": 2,
+    "Padmasana": 1,
+    "Setubandhasana": 5,
+    "Shavasana": 7,
+    "Tadasana": 0,
+    "Trikonasana": 9,
+    "Virbhadrasana1": 4,
+    "Vrikshasana": 8
+  },
+  "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": "4.41.2",
+  "tubelet_size": 2,
+  "use_mean_pooling": false
+}

saved-models/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a22a62ba075f5222407b1ad3a8f4f9200d7aff7129a80dbdde6a8598498685
+size 344961984

saved-models/preprocessor_config.json

@@ -0,0 +1,42 @@
+{
+  "_valid_processor_keys": [
+    "videos",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "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
+  }
+}

saved-models/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9abd3d85afd1f3d894e41acaf586b4db5912319bf21619a535386a8dc0bdda6
+size 5112