./wmc_v2_swin-tiny-patch4-window7-224_base_wm811k_cls_contra_learning_1017_6_cls

README.md

@@ -0,0 +1,86 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: microsoft/swin-tiny-patch4-window7-224
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: wmc_v2_swin-tiny-patch4-window7-224_base_wm811k_cls_contra_learning_1017_6_cls
+  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. -->
+
+# wmc_v2_swin-tiny-patch4-window7-224_base_wm811k_cls_contra_learning_1017_6_cls
+
+This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0632
+- Accuracy: 0.9760
+- Precision: 0.9607
+- Recall: 0.9621
+- F1: 0.9611
+
+## 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: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 1.131         | 0.1697 | 100  | 0.6398          | 0.7195   | 0.6527    | 0.5655 | 0.5087 |
+| 0.6353        | 0.3394 | 200  | 0.2183          | 0.9314   | 0.8628    | 0.8571 | 0.8592 |
+| 0.5429        | 0.5091 | 300  | 0.1273          | 0.9594   | 0.9347    | 0.8905 | 0.9073 |
+| 0.4432        | 0.6788 | 400  | 0.1040          | 0.9680   | 0.9322    | 0.9489 | 0.9397 |
+| 0.4109        | 0.8485 | 500  | 0.0998          | 0.9697   | 0.9508    | 0.9442 | 0.9474 |
+| 0.3775        | 1.0182 | 600  | 0.1209          | 0.9573   | 0.9323    | 0.9382 | 0.9326 |
+| 0.3661        | 1.1880 | 700  | 0.0968          | 0.9697   | 0.9313    | 0.9579 | 0.9428 |
+| 0.3609        | 1.3577 | 800  | 0.0879          | 0.9707   | 0.9479    | 0.9524 | 0.9498 |
+| 0.3393        | 1.5274 | 900  | 0.0785          | 0.9734   | 0.9536    | 0.9566 | 0.9547 |
+| 0.3242        | 1.6971 | 1000 | 0.0773          | 0.9732   | 0.9456    | 0.9626 | 0.9533 |
+| 0.3307        | 1.8668 | 1100 | 0.0626          | 0.9781   | 0.9631    | 0.9601 | 0.9615 |
+| 0.3325        | 2.0365 | 1200 | 0.0662          | 0.9767   | 0.9575    | 0.9637 | 0.9603 |
+| 0.2889        | 2.2062 | 1300 | 0.0609          | 0.9780   | 0.9526    | 0.9673 | 0.9594 |
+| 0.2818        | 2.3759 | 1400 | 0.0656          | 0.9762   | 0.9566    | 0.9619 | 0.9588 |
+| 0.3038        | 2.5456 | 1500 | 0.0561          | 0.9795   | 0.9666    | 0.9633 | 0.9647 |
+| 0.2823        | 2.7153 | 1600 | 0.0610          | 0.9781   | 0.9590    | 0.9668 | 0.9626 |
+| 0.2478        | 2.8850 | 1700 | 0.0632          | 0.9760   | 0.9607    | 0.9621 | 0.9611 |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.1

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
+  "architectures": [
+    "SwinForClassificationAndContrastiveLearning"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    6,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 96,
+  "encoder_stride": 32,
+  "finetuning_task": "image-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swin",
+  "num_channels": 3,
+  "num_heads": [
+    3,
+    6,
+    12,
+    24
+  ],
+  "num_layers": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "path_norm": true,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ed53f9646f7b821205d6e5da904cb45a2ce3c0a5f535af1a77b51810467f91f
+size 110355136

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374169baf5b897ee7cc888c444c8393ef0ae015e811c413513ff291edad1b4a8
+size 5304