Upload 3 files

app.py

@@ -0,0 +1,36 @@
+import gradio as gr
+import numpy as np
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing import image
+
+# Load model
+model = load_model("models.h5")
+
+# Class labels
+class_names = ['daisy', 'dandelion', 'rose', 'sunflower', 'tulip']
+
+# Prediction function
+def predict_flower(img):
+    img = img.resize((224, 224))  # Resize to match training input
+    img_array = image.img_to_array(img)
+    img_array = img_array / 255.0  # Normalize
+    img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
+
+    predictions = model.predict(img_array)
+    class_index = np.argmax(predictions)
+    confidence = float(np.max(predictions))
+
+    return {class_names[i]: float(predictions[0][i]) for i in range(5)}
+
+# Gradio interface
+interface = gr.Interface(
+    fn=predict_flower,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Label(num_top_classes=5),
+    title="Flower Classifier",
+    description="Upload a flower image and the model will classify it as daisy, dandelion, rose, sunflower, or tulip.",
+    allow_flagging="never"
+)
+
+if __name__ == "__main__":
+    interface.launch()

models.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44389ef3fef2807d2904a13d693cc23f12c2177d4c4ad24254d902bdbc748b64
+size 5222136

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+tensorflow
+numpy
+pillow