SwinV2-fineTuned

README.md

@@ -0,0 +1,70 @@
+---
+base_model: swinv2
+tags:
+- image-classification
+- breast cancer
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: swinV2-CBIS
+  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. -->
+
+# swinV2-CBIS
+
+This model is a fine-tuned version of [swinv2](https://huggingface.co/swinv2) on the CBIS-DDSM dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6876
+- Accuracy: 0.6085
+- Precision: 0.3702
+- Recall: 0.6085
+- F1: 0.4604
+
+## 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: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- 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     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.7205        | 1.0   | 165  | 0.6842          | 0.6085   | 0.3702    | 0.6085 | 0.4604 |
+| 0.6924        | 2.0   | 330  | 0.6847          | 0.6085   | 0.3702    | 0.6085 | 0.4604 |
+| 0.6867        | 3.0   | 495  | 0.6876          | 0.6085   | 0.3702    | 0.6085 | 0.4604 |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "microsoft/swinv2-base-patch4-window8-256",
+  "architectures": [
+    "Swinv2ForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    18,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 128,
+  "encoder_stride": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Benign",
+    "1": "Malignant"
+  },
+  "image_size": 256,
+  "initializer_range": 0.02,
+  "label2id": {
+    "Benign": 0,
+    "Malignant": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swinv2",
+  "num_channels": 3,
+  "num_heads": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "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": "4.42.4",
+  "use_absolute_embeddings": false,
+  "window_size": 8
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:830e05b68a75949d16b56c75b28639fb0fc7146f913dc605f4c41bbe75d01487
+size 347645480

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "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
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60f903f899e17a465cda26640e1f42b6c2115e612a54108746d4d6284283deb3
+size 5112