Upload artifacts

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+samples/bacterial_pneumonia.png filter=lfs diff=lfs merge=lfs -text
+samples/normal.png filter=lfs diff=lfs merge=lfs -text
+samples/viral_pneumonia.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,59 +1,100 @@
 ---
 license: mit
+library_name: transformers
+
+pipeline_tag: image-classification
+
+base_model: facebook/convnextv2-tiny-22k-224
 tags:
-  - image-classification
   - chest-xray
+  - convnext
+  - convnextv2
+  - image-classification
+  - medical
   - medical-imaging
   - pneumonia
-  - pytorch-lightning
-  - convnext
-  - dinov2
-library_name: pytorch
+  - pytorch
+  - transformers
 datasets:
-  - paultimothymooney/chest-xray-pneumonia
-pipeline_tag: image-classification
----
+  - keremberke/chest-xray-classification
 
-# chest-xray-classifier
+metrics:
+  - accuracy
+  - f1
 
-Production-grade 3-class chest X-ray classifier (normal / bacterial pneumonia / viral pneumonia).
+widget:
+  - src: https://huggingface.co/kiselyovd/chest-xray-classifier/resolve/main/samples/bacterial_pneumonia.png
+    title: bacterial_pneumonia
+  - src: https://huggingface.co/kiselyovd/chest-xray-classifier/resolve/main/samples/normal.png
+    title: normal
+  - src: https://huggingface.co/kiselyovd/chest-xray-classifier/resolve/main/samples/viral_pneumonia.png
+    title: viral_pneumonia
 
-Three-class chest X-ray classifier distinguishing **normal**, **bacterial pneumonia**, and **viral pneumonia** on pediatric frontal radiographs. Main model: ConvNeXt-V2-Tiny fine-tuned on the Kaggle Chest X-Ray Images (Pneumonia) dataset (5,856 images) with a bacterial/viral split derived from filename metadata.
 
-Class index order: `("bacterial_pneumonia", "normal", "viral_pneumonia")`.
+model-index:
+  - name: kiselyovd/chest-xray-classifier
+    results:
+      - task:
+          type: image-classification
+        dataset:
+          type: keremberke/chest-xray-classification
+          name: Chest X-Ray Images (Pneumonia)
+        metrics:
+          - type: auroc_macro_ovr
+            value: 0.9752638346619307
+          - type: accuracy
+            value: 0.9134615384615384
+          - type: macro_f1
+            value: 0.9029730638714358
+
+---
+
+# chest-xray-classifier
+
+Production-grade 3-class chest X-ray classifier: normal vs bacterial pneumonia vs viral pneumonia.
 
 ## Metrics
 
 | Metric | Value |
 |---|---|
-| Main model | ConvNeXt-V2-Tiny |
-| Main accuracy | 91.3% |
-| Main macro F1 | 90.3% |
-| Main macro AUROC (OvR) | 97.5% |
-| Baseline model | DINOv2 ViT-S linear probe |
-| Baseline accuracy | 85.6% |
-| Baseline macro F1 | 84.2% |
-| Baseline macro AUROC (OvR) | 94.2% |
-| Test set size | 624.0 |
-| Classes | bacterial_pneumonia, normal, viral_pneumonia |
+| classification_report | {'bacterial_pneumonia': {'precision': 0.8913857677902621, 'recall': 0.9834710743801653, 'f1-score': 0.9351669941060904, 'support': 242.0}, 'normal': {'precision': 0.995260663507109, 'recall': 0.8974358974358975, 'f1-score': 0.9438202247191011, 'support': 234.0}, 'viral_pneumonia': {'precision': 0.8356164383561644, 'recall': 0.8243243243243243, 'f1-score': 0.8299319727891157, 'support': 148.0}, 'accuracy': 0.9134615384615384, 'macro avg': {'precision': 0.9074209565511785, 'recall': 0.9017437653801291, 'f1-score': 0.9029730638714358, 'support': 624.0}, 'weighted avg': {'precision': 0.9171115127285565, 'recall': 0.9134615384615384, 'f1-score': 0.913452367196687, 'support': 624.0}} |
+| confusion_matrix | [[238, 1, 3], [3, 210, 21], [26, 0, 122]] |
+| classes | ['bacterial_pneumonia', 'normal', 'viral_pneumonia'] |
+| auroc_macro_ovr | 0.9752638346619307 |
+| accuracy | 0.9134615384615384 |
+| macro_f1 | 0.9029730638714358 |
 
 ## Usage
 
+
 ```python
-from huggingface_hub import snapshot_download
+from transformers import AutoImageProcessor, AutoModelForImageClassification
+import torch
+from PIL import Image
 
-from chest_xray_classifier.inference.predict import load_model, predict
+processor = AutoImageProcessor.from_pretrained("kiselyovd/chest-xray-classifier")
+model = AutoModelForImageClassification.from_pretrained("kiselyovd/chest-xray-classifier")
 
-ckpt_dir = snapshot_download("kiselyovd/chest-xray-classifier")
-model = load_model(f"{ckpt_dir}/best.ckpt")
-result = predict(model, "path/to/radiograph.jpeg")
-# {"pred": 1, "probs": [0.02, 0.95, 0.03]}
+image = Image.open("your_image.png")
+inputs = processor(images=image, return_tensors="pt")
+with torch.no_grad():
+    logits = model(**inputs).logits
+predicted_class = logits.argmax(-1).item()
+print(model.config.id2label[predicted_class])
 ```
 
-## Intended use
 
-Research and educational purposes only. **This is not a medical device.** Do not use for clinical decision-making. Model was trained on a single publicly available pediatric dataset and has not been validated against clinical ground truth, population diversity, acquisition-device variation, or downstream clinical workflows.
+## Training Data
+
+Trained on [Chest X-Ray Images (Pneumonia)](https://huggingface.co/datasets/keremberke/chest-xray-classification).
+
+
+## Source Code
+
+[GitHub Repository](https://github.com/kiselyovd/chest-xray-classifier)
+
+## Intended Use
 
-## Source
+This model is provided for research and educational purposes. The authors make no warranties about its suitability for any particular application. Users are responsible for evaluating the model's fitness for their use case, including fairness, safety, and compliance with applicable regulations.
 
-https://github.com/kiselyovd/chest-xray-classifier
+> **Note:** This model card was generated from the [ml-project-template](https://github.com/kiselyovd/ml-project-template) scaffold.

config.json

@@ -0,0 +1,51 @@
+{
+  "architectures": [
+    "ConvNextV2ForImageClassification"
+  ],
+  "depths": [
+    3,
+    3,
+    9,
+    3
+  ],
+  "drop_path_rate": 0.0,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_sizes": [
+    96,
+    192,
+    384,
+    768
+  ],
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "convnextv2",
+  "num_channels": 3,
+  "num_stages": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "transformers_version": "5.5.4"
+}

hf_export/config.json

@@ -0,0 +1,51 @@
+{
+  "architectures": [
+    "ConvNextV2ForImageClassification"
+  ],
+  "depths": [
+    3,
+    3,
+    9,
+    3
+  ],
+  "drop_path_rate": 0.0,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_sizes": [
+    96,
+    192,
+    384,
+    768
+  ],
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "convnextv2",
+  "num_channels": 3,
+  "num_stages": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "transformers_version": "5.5.4"
+}

hf_export/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c0b8fba6caa340cfbabf06119c6a9988b018c277a72d9565e0f62acda2a7d0
+size 111498892

hf_export/preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "crop_pct": 0.875,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ConvNextImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c0b8fba6caa340cfbabf06119c6a9988b018c277a72d9565e0f62acda2a7d0
+size 111498892

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "crop_pct": 0.875,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ConvNextImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}