Update app.py

app.py

@@ -1,74 +1,102 @@
-import numpy as np
+import cv2
 import gradio as gr
 import tensorflow as tf
-import cv2
-
-# Load the trained MNIST model
-model = tf.keras.models.load_model("./number_recognition_model_colab.keras")
-
-# Class names (0 to 9)
-labels = ["zero", "one", "two", "three", "four", "five", "six", "seven", "eight", "nine"]
-
-def predict(data):
-    # Extract the 'composite' key from the input dictionary
-    img = data["composite"]
-    img = np.array(img)
-
-    # Convert RGBA to RGB if needed
-    if img.shape[-1] == 4:  # RGBA
-        img = cv2.cvtColor(img, cv2.COLOR_RGBA2RGB)
-
-    # Convert RGB to Grayscale
-    if img.shape[-1] == 3:  # RGB
-        img = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
-
-    # Resize image to 28x28
-    img = cv2.resize(img, (28, 28))
-
-    # Normalize pixel values to [0, 1]
-    img = img / 255.0
-
-    # Reshape to match model input (1, 28, 28, 1)
-    img = img.reshape(1, 28, 28, 1)
-
-    # Model predictions
-    preds = model.predict(img)[0]
-
-    print(preds)
-
-    # Get top 3 classes
-    top_3_classes = np.argsort(preds)[-3:][::-1]
-    top_3_probs = preds[top_3_classes]
-    class_names = [labels[i] for i in top_3_classes]
-    print(class_names, top_3_probs, top_3_classes)
+import numpy as np
+from PIL import Image
 
-    # Return top 3 predictions as a dictionary
-    return {class_names[i]: float(top_3_probs[i]) for i in range(3)}
+title = "Welcome on your first sketch recognition app!"
 
-# Title and description
-title = "Welcome to your first sketch recognition app!"
 head = (
     "<center>"
-    "<img src='./mnist-classes.png' width=400>"
-    "<p>The model is trained to classify numbers (from 0 to 9). "
-    "To test it, draw your number in the space provided (use the editing tools in the image editor).</p>"
+    "The robot was trained to classify numbers (from 0 to 9). To test it, write your number in the space provided."
     "</center>"
 )
 
-
-with gr.Blocks(title=title) as demo:
-    # Display title and description
-    gr.Markdown(head)
+# Model yükleniyor
+model = tf.keras.models.load_model("./number_recognition_model_colab.keras")
 
 
-    with gr.Row():
-        # Using ImageEditor with type='numpy'
-        im = gr.Sketchpad(type="numpy", label="Draw your digit here (use brush and eraser)")
+img_size = 28
 
-        # Output label (top 3 predictions)
-        label = gr.Label(num_top_classes=3, label="Predictions")
+labels = ["zero", "one", "two", "three", "four", "five", "six", "seven", "eight", "nine"]
 
-    # Trigger prediction whenever the image changes
-    im.change(predict, inputs=im, outputs=label)
+def predict(img):
+    try:
+        # Enhanced image validation and conversion
+        if img is None:
+            raise ValueError("No image provided")
+        
+        # Convert to numpy array if it's a PIL Image
+        if isinstance(img, Image.Image):
+            img = np.array(img)
+        
+        # Handle base64 image strings
+        elif isinstance(img, str):
+            # Check if it's a base64 data URL
+            if img.startswith('data:image'):
+                # Split and decode base64 part
+                img = img.split(',')[1]
+            
+            # Decode base64 to image
+            try:
+                img = Image.open(io.BytesIO(base64.b64decode(img)))
+                img = np.array(img)
+            except Exception as e:
+                print(f"Base64 decoding error: {e}")
+                raise ValueError("Invalid base64 image")
+        
+        # Validate numpy array
+        if not isinstance(img, np.ndarray):
+            raise ValueError("Input could not be converted to a valid image")
+        
+        # Print initial image details for debugging
+        print(f"Initial image type: {type(img)}, shape: {img.shape}")
+        
+        # Handle color channels
+        if img.ndim == 3:
+            if img.shape[-1] == 3:  # Color image
+                img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+            elif img.shape[-1] == 4:  # RGBA image
+                img = cv2.cvtColor(img, cv2.COLOR_RGBA2GRAY)
+        
+        # Ensure single channel
+        if img.ndim == 2:
+            img = np.expand_dims(img, axis=-1)
+        
+        # Resize and normalize
+        img = cv2.resize(img, (img_size, img_size))
+        img = img.astype('float32') / 255.0
+        img = img.reshape(1, img_size, img_size, 1)
+        
+        # Print processed image details
+        print(f"Processed image shape: {img.shape}")
+        
+        # Get predictions from the model
+        preds = model.predict(img)[0]
+        
+        # Print predictions for debugging
+        print("Predictions:", preds)
+        
+        # Return predictions as a dictionary
+        return {label: float(pred) for label, pred in zip(labels, preds)}
+    
+    except Exception as e:
+        # Comprehensive error logging
+        print(f"Full error during prediction: {e}")
+        return {"Error": str(e)}
+            
+   
+
+# Set up the Gradio interface with the input as a sketchpad and output as labels
+label = gr.Label(num_top_classes=3)
+
+# Gradio arayüzü
+interface = gr.Interface(
+    fn=predict,
+    inputs=gr.Sketchpad(type="pil"),
+    outputs=label,
+    title="Sketch Recognition App",
+    description="Draw a number (0-9) and see the model's top predictions."
+)
 
-    demo.launch(share=True)
+interface.launch(debug=True, share=True)