Model save

README.md

@@ -0,0 +1,105 @@
+---
+license: apache-2.0
+base_model: microsoft/swinv2-tiny-patch4-window16-256
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: Action_agent
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7914285714285715
+---
+
+<!-- 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. -->
+
+# Action_agent
+
+This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window16-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window16-256) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6412
+- Accuracy: 0.7914
+
+## 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: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.039         | 0.32  | 100  | 1.7706          | 0.4848   |
+| 1.3695        | 0.64  | 200  | 1.0886          | 0.6457   |
+| 1.099         | 0.96  | 300  | 0.9092          | 0.68     |
+| 1.0011        | 1.27  | 400  | 0.8183          | 0.7171   |
+| 0.8437        | 1.59  | 500  | 0.7674          | 0.7190   |
+| 0.8613        | 1.91  | 600  | 0.7168          | 0.7410   |
+| 0.7427        | 2.23  | 700  | 0.7270          | 0.7352   |
+| 0.693         | 2.55  | 800  | 0.6801          | 0.7676   |
+| 0.7789        | 2.87  | 900  | 0.6832          | 0.7590   |
+| 0.6863        | 3.18  | 1000 | 0.6655          | 0.7752   |
+| 0.6437        | 3.5   | 1100 | 0.6382          | 0.7771   |
+| 0.6741        | 3.82  | 1200 | 0.6446          | 0.7790   |
+| 0.5871        | 4.14  | 1300 | 0.6551          | 0.7838   |
+| 0.6051        | 4.46  | 1400 | 0.6970          | 0.7638   |
+| 0.5175        | 4.78  | 1500 | 0.6553          | 0.7790   |
+| 0.5795        | 5.1   | 1600 | 0.6667          | 0.7771   |
+| 0.4919        | 5.41  | 1700 | 0.6317          | 0.7905   |
+| 0.4986        | 5.73  | 1800 | 0.6486          | 0.7810   |
+| 0.5104        | 6.05  | 1900 | 0.6700          | 0.7743   |
+| 0.4919        | 6.37  | 2000 | 0.6528          | 0.7819   |
+| 0.5144        | 6.69  | 2100 | 0.6355          | 0.7876   |
+| 0.5554        | 7.01  | 2200 | 0.6552          | 0.7771   |
+| 0.5389        | 7.32  | 2300 | 0.6361          | 0.7876   |
+| 0.5751        | 7.64  | 2400 | 0.6377          | 0.7905   |
+| 0.4743        | 7.96  | 2500 | 0.6417          | 0.7867   |
+| 0.4519        | 8.28  | 2600 | 0.6309          | 0.7895   |
+| 0.5058        | 8.6   | 2700 | 0.6453          | 0.7867   |
+| 0.4754        | 8.92  | 2800 | 0.6414          | 0.7905   |
+| 0.4637        | 9.24  | 2900 | 0.6330          | 0.7905   |
+| 0.5028        | 9.55  | 3000 | 0.6418          | 0.7857   |
+| 0.4227        | 9.87  | 3100 | 0.6412          | 0.7914   |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,83 @@
+{
+  "_name_or_path": "microsoft/swinv2-tiny-patch4-window16-256",
+  "architectures": [
+    "Swinv2ForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    6,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 96,
+  "encoder_stride": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "\u0995\u09a5\u09be_\u09ac\u09b2\u09be",
+    "1": "\u0995\u09ae\u09cd\u09aa\u09bf\u0989\u099f\u09be\u09b0_\u09ac\u09cd\u09af\u09ac\u09b9\u09be\u09b0_\u0995\u09b0\u09be",
+    "2": "\u0996\u09be\u0993\u09df\u09be",
+    "3": "\u0996\u09c7\u09b2\u09be_\u0995\u09b0\u09be",
+    "4": "\u0998\u09c1\u09ae\u09be\u09a8\u09cb",
+    "5": "\u09aa\u09be\u09a8_\u0995\u09b0\u09be",
+    "6": "\u09aa\u09dc\u09be",
+    "7": "\u09b0\u09be\u09a8\u09cd\u09a8\u09be_\u0995\u09b0\u09be",
+    "8": "\u09b2\u09c7\u0996\u09be",
+    "9": "\u09b9\u09be\u0981\u099f\u09be"
+  },
+  "image_size": 256,
+  "initializer_range": 0.02,
+  "label2id": {
+    "\u0995\u09a5\u09be_\u09ac\u09b2\u09be": "0",
+    "\u0995\u09ae\u09cd\u09aa\u09bf\u0989\u099f\u09be\u09b0_\u09ac\u09cd\u09af\u09ac\u09b9\u09be\u09b0_\u0995\u09b0\u09be": "1",
+    "\u0996\u09be\u0993\u09df\u09be": "2",
+    "\u0996\u09c7\u09b2\u09be_\u0995\u09b0\u09be": "3",
+    "\u0998\u09c1\u09ae\u09be\u09a8\u09cb": "4",
+    "\u09aa\u09be\u09a8_\u0995\u09b0\u09be": "5",
+    "\u09aa\u09dc\u09be": "6",
+    "\u09b0\u09be\u09a8\u09cd\u09a8\u09be_\u0995\u09b0\u09be": "7",
+    "\u09b2\u09c7\u0996\u09be": "8",
+    "\u09b9\u09be\u0981\u099f\u09be": "9"
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swinv2",
+  "num_channels": 3,
+  "num_heads": [
+    3,
+    6,
+    12,
+    24
+  ],
+  "num_layers": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "path_norm": true,
+  "pretrained_window_sizes": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_absolute_embeddings": false,
+  "window_size": 16
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5cf3b87b343cd43304129258627ec15995b5efe57f624c30058abd1a85104a
+size 110374752

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 256,
+    "width": 256
+  }
+}

runs/Apr22_19-46-52_25f23db457d4/events.out.tfevents.1713815212.25f23db457d4.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb21aaacbc41e7069754d7bc02664dfdaaa197fd0871de78d0fd5beef4136819
+size 60483

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e145019e5e9eb49ac1a9542b4cc2430a5e37f69fa201e50c7d9e96b4bb660be
+size 4920