Model save

README.md

@@ -0,0 +1,80 @@
+---
+license: cc-by-nc-4.0
+base_model: MCG-NJU/videomae-base-finetuned-kinetics
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: videomae-finetuned_41
+  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. -->
+
+# videomae-finetuned_41
+
+This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 7.9297
+- Accuracy: 0.3317
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.2
+- training_steps: 61640
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.5175        | 0.05  | 3083  | 4.6977          | 0.3008   |
+| 0.5311        | 1.05  | 6166  | 5.6012          | 0.3081   |
+| 0.5884        | 2.05  | 9249  | 6.2252          | 0.3175   |
+| 0.5206        | 3.05  | 12332 | 6.7917          | 0.3248   |
+| 0.4449        | 4.05  | 15415 | 6.1943          | 0.3008   |
+| 0.3783        | 5.05  | 18498 | 6.8339          | 0.3150   |
+| 0.5032        | 6.05  | 21581 | 6.6566          | 0.3077   |
+| 0.4091        | 7.05  | 24664 | 6.8013          | 0.2972   |
+| 0.4436        | 8.05  | 27747 | 6.8549          | 0.3      |
+| 0.3474        | 9.05  | 30830 | 7.0015          | 0.3268   |
+| 0.2151        | 10.05 | 33913 | 7.7671          | 0.3041   |
+| 0.3597        | 11.05 | 36996 | 7.0724          | 0.3293   |
+| 0.1673        | 12.05 | 40079 | 7.5805          | 0.3248   |
+| 0.114         | 13.05 | 43162 | 7.8196          | 0.3175   |
+| 0.2088        | 14.05 | 46245 | 7.7103          | 0.3272   |
+| 0.1662        | 15.05 | 49328 | 7.7613          | 0.3248   |
+| 0.1961        | 16.05 | 52411 | 7.7730          | 0.3297   |
+| 0.1436        | 17.05 | 55494 | 7.9297          | 0.3317   |
+| 0.1134        | 18.05 | 58577 | 8.0447          | 0.3268   |
+| 0.0634        | 19.05 | 61640 | 7.9717          | 0.3305   |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "MCG-NJU/videomae-base-finetuned-kinetics",
+  "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": "BAND",
+    "1": "BOX",
+    "2": "DIRECTION",
+    "3": "ELECTRIC_CAR",
+    "4": "FACILITY",
+    "5": "KANBAN",
+    "6": "NEUTRAL",
+    "7": "PALLET",
+    "8": "PARTS",
+    "9": "SHELF",
+    "10": "WAGON"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "BAND": 0,
+    "BOX": 1,
+    "DIRECTION": 2,
+    "ELECTRIC_CAR": 3,
+    "FACILITY": 4,
+    "KANBAN": 5,
+    "NEUTRAL": 6,
+    "PALLET": 7,
+    "PARTS": 8,
+    "SHELF": 9,
+    "WAGON": 10
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "videomae",
+  "norm_pix_loss": false,
+  "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": "4.38.1",
+  "tubelet_size": 2,
+  "use_mean_pooling": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:317e80e226e8dec173011e2f7aa2e44fc7a87c18be41c6dcd5cc457f62db8966
+size 344965020

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
+  }
+}

runs/Aug13_15-37-23_WIN-645TP8FEMLV/events.out.tfevents.1723531046.WIN-645TP8FEMLV.24196.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03c7283c87e93b98ee9478be006da26d7f3e6eceadbe54c013b2351e541058cc
+size 78014

runs/Aug13_15-37-23_WIN-645TP8FEMLV/events.out.tfevents.1723597114.WIN-645TP8FEMLV.24196.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc5b140319fc39723dac0ee1f43b5e3c4096802b68660e83e4b4c38b671cb04
+size 417

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a84ba33865b66b576ff42c8e2bd04fa99b4e4df755bdb9e590ef978343c0053
+size 4475