Model save

README.md

@@ -0,0 +1,62 @@
+---
+library_name: transformers
+license: cc-by-nc-4.0
+base_model: MCG-NJU/videomae-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: baseball-videomae
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# baseball-videomae
+
+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:
+- Loss: 2.4185
+- Accuracy: 0.0463
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.4685        | 1.0   | 218  | 2.4185          | 0.0463   |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.7.0.dev20250109
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -12,21 +12,33 @@
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
   "id2label": {
-    "0": "bunt",
-    "1": "fly_ball",
-    "2": "ground_ball",
-    "3": "line_drive",
-    "4": "popup"
+    "0": "CH",
+    "1": "CU",
+    "2": "EP",
+    "3": "FC",
+    "4": "FF",
+    "5": "FS",
+    "6": "KC",
+    "7": "KN",
+    "8": "SI",
+    "9": "SL",
+    "10": "ST"
   },
   "image_size": 224,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "bunt": 0,
-    "fly_ball": 1,
-    "ground_ball": 2,
-    "line_drive": 3,
-    "popup": 4
+    "CH": 0,
+    "CU": 1,
+    "EP": 2,
+    "FC": 3,
+    "FF": 4,
+    "FS": 5,
+    "KC": 6,
+    "KN": 7,
+    "SI": 8,
+    "SL": 9,
+    "ST": 10
   },
   "layer_norm_eps": 1e-12,
   "model_type": "videomae",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab7b59f7daf41a106ad26eee94c709f1cdc968f2cf99f0aa4b52787c6ff3b2d2
-size 344946604
+oid sha256:6afaeaac0abf5a271cb25294403459dace9e0c869bbac92c9be0a2e7d408f148
+size 344965060

pitch_type/config.json

@@ -0,0 +1,57 @@
+{
+  "_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": "CH",
+    "1": "CU",
+    "2": "EP",
+    "3": "FC",
+    "4": "FF",
+    "5": "FS",
+    "6": "KC",
+    "7": "KN",
+    "8": "SI",
+    "9": "SL",
+    "10": "ST"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "CH": 0,
+    "CU": 1,
+    "EP": 2,
+    "FC": 3,
+    "FF": 4,
+    "FS": 5,
+    "KC": 6,
+    "KN": 7,
+    "SI": 8,
+    "SL": 9,
+    "ST": 10
+  },
+  "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": "4.47.1",
+  "tubelet_size": 2,
+  "use_mean_pooling": false
+}

pitch_type/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6afaeaac0abf5a271cb25294403459dace9e0c869bbac92c9be0a2e7d408f148
+size 344965060

pitch_type/preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "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
+  }
+}

pitch_type/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dfb6a96bd4770516fbe664ee849635a567a07863a62aac1f73f935621e63c61
+size 5304