First commit

.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/cats_dogs_cnn_batchnorm.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45e6d263e65cbec66d3c79becf5865fb41be1f405fee97b4d9c2e39986685297
+size 39753104

Model/cats_dogs_vgg.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d0d8c4bd8b8d2614ae47fccbb87f7e0cd4dc8c94e1f304af8a926c358295642
+size 84128112

app.py

@@ -0,0 +1,38 @@
+import gradio as gr
+import numpy as np
+from tensorflow.keras.models import load_model
+import tensorflow
+from PIL import Image
+
+model = load_model("Model\\cats_dogs_cnn_batchnorm.h5")
+
+# Function to preprocess image
+def preprocess_image(img):
+    img = img.resize((128, 128))  # Resize to match model input size
+    img = np.array(img) / 255.0  # Normalize pixel values
+    img = np.expand_dims(img, axis=0)  # Add batch dimension
+    return img
+
+# Function to predict class
+def predict(img):
+    img = preprocess_image(img)
+    prediction = model.predict(img)[0][0]  # Get model output
+
+    # Convert output to class label
+    label = "Cat 🐱" if prediction > 0.5 else "Dog 🐶" # Cat is labeled 0 and Dog is labeled 1
+    confidence = round(float(prediction * 100), 2) if prediction > 0.5 else round(float((1 - prediction) * 100), 2)
+
+    return f"{label} (Confidence: {confidence}%)"
+
+# Gradio UI
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil"),  # Accepts image input
+    outputs=gr.Textbox(label="Prediction"),
+    title="Cat vs Dog Classifier (Golden Owl code test)",
+    description="Upload an image to predict if it's a cat or a dog."
+)
+
+# Run the app
+if __name__ == "__main__":
+    demo.launch()