Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+model.keras filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,59 @@
+
+---
+language: en
+license: mit
+library_name: tf
+tags:
+- chest-xray
+- pneumonia
+- medical
+- tensorflow
+- image-classification
+datasets:
+- chest-xray
+---
+
+# Chest X-Ray Pneumonia Detection Model
+
+This model classifies chest X-rays as either normal or showing signs of pneumonia.
+
+## Model Description
+
+This deep learning model was trained on the Chest X-Ray dataset to differentiate between normal lungs and those affected by pneumonia. It uses transfer learning with a pre-trained network to achieve high accuracy.
+
+### Intended Use
+
+This model is for **research and educational purposes only**. It should not be used for clinical diagnosis or medical decision-making without proper clinical validation.
+
+## Usage
+
+```python
+import tensorflow as tf
+from preprocessing import preprocess_image
+
+# Load the model
+model = tf.keras.models.load_model("model.keras")
+
+# Preprocess an image
+img = preprocess_image("path/to/chest_xray.jpg")
+
+# Make prediction
+prediction = model.predict(img)
+probability = prediction[0][0]
+
+# Interpret results
+if probability > 0.5:
+    result = "PNEUMONIA"
+    confidence = probability
+else:
+    result = "NORMAL"
+    confidence = 1 - probability
+
+print(f"Prediction: {result} with {confidence:.2%} confidence")
+```
+
+## Limitations
+
+- This model should not be used as a substitute for professional medical diagnosis
+- Performance may vary across different patient demographics and equipment
+- The model was trained on a specific dataset which may not represent all clinical scenarios

config.json

@@ -0,0 +1,37 @@
+{
+  "language": "en",
+  "license": "mit",
+  "library_name": "tf",
+  "tags": [
+    "chest-xray",
+    "pneumonia",
+    "medical",
+    "tensorflow"
+  ],
+  "datasets": [
+    "chest-xray"
+  ],
+  "model-index": [
+    {
+      "name": "Chest X-Ray Pneumonia Detection",
+      "results": [
+        {
+          "task": {
+            "type": "image-classification",
+            "subtype": "binary-classification"
+          },
+          "dataset": {
+            "name": "Chest X-Ray",
+            "type": "medical"
+          },
+          "metrics": [
+            {
+              "type": "accuracy",
+              "value": 0.94
+            }
+          ]
+        }
+      ]
+    }
+  ]
+}

example.py

@@ -0,0 +1,36 @@
+
+import tensorflow as tf
+from preprocessing import preprocess_image
+import matplotlib.pyplot as plt
+
+# Example function to run prediction
+def predict_xray(image_path):
+    # Load model
+    model = tf.keras.models.load_model("model.keras")
+    
+    # Preprocess image
+    img = preprocess_image(image_path)
+    
+    # Get raw image for display
+    display_img = plt.imread(image_path)
+    
+    # Run prediction
+    prediction = model.predict(img)
+    prob = prediction[0][0]
+    
+    # Determine class
+    if prob > 0.5:
+        result = "PNEUMONIA"
+        confidence = prob
+    else:
+        result = "NORMAL"
+        confidence = 1 - prob
+    
+    # Display results
+    plt.figure(figsize=(6, 6))
+    plt.imshow(display_img, cmap="gray")
+    plt.title(f"Prediction: {result}\nConfidence: {confidence:.2%}")
+    plt.axis("off")
+    plt.show()
+    
+    return {"class": result, "confidence": float(confidence)}

model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7ee3d351795c188c4412570a4334c8b9ccd5d9b4bfc1489979b8393c05f52c7
+size 140642846

preprocessing.py

@@ -0,0 +1,28 @@
+
+import tensorflow as tf
+
+def preprocess_image(image_path, target_size=(299, 299)):
+    """
+    Preprocesses a chest X-ray image for the model.
+    
+    Args:
+        image_path: Path to the image file
+        target_size: Target size for resizing
+        
+    Returns:
+        Preprocessed image tensor ready for prediction
+    """
+    # Read image
+    img = tf.io.read_file(image_path)
+    img = tf.image.decode_image(img, channels=3)
+    
+    # Resize
+    img = tf.image.resize(img, target_size)
+    
+    # Normalize to [0,1]
+    img = img / 255.0
+    
+    # Add batch dimension
+    img = tf.expand_dims(img, 0)
+    
+    return img

saved_model/fingerprint.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aab39597d41e6bb3b1caf693a7063929afec7b823065ec4f0755f3b0c195147f
+size 55

saved_model/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4f9413ec33133b45a92812478d1052256b332599feaa0725f6ec6b049cf15b5
+size 3826868

saved_model/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8676a90dfe6f3e133c9257323f193423c4a823c7d174d40c6eb6cf4647763c7b
+size 93275355

saved_model/variables/variables.index

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5241ac83ed297fce860cc62c1ccec32169523e73e124e0f97255d70bed10a9d9
+size 59811