Upload 2 files

app.py

@@ -0,0 +1,45 @@
+import gradio as gr
+import tensorflow as tf
+import numpy as np
+from PIL import Image
+
+
+model_path = "chess-predict-model_transferlearning.keras"
+model = tf.keras.models.load_model(model_path)
+
+# Define the core prediction function
+def predict_figure(image):
+    # Preprocess image
+    print(type(image))
+    image = Image.fromarray(image.astype('uint8'))  # Convert numpy array to PIL image
+    image = image.resize((150, 150)) #resize the image to 150x150
+    image = np.array(image)
+    image = np.expand_dims(image, axis=0) # same as image[None, ...]
+    
+    # Predict
+    prediction = model.predict(image)
+    
+    # Apply softmax to get probabilities for each class
+    prediction = tf.nn.softmax(prediction)
+    
+    # Create a dictionary with the probabilities for each Pokemon
+    bishop = np.round(float(prediction[0][0]), 2)
+    king = np.round(float(prediction[0][1]), 2)
+    knight = np.round(float(prediction[0][2]), 2)
+    pawn = np.round(float(prediction[0][3]), 2)
+    queen = np.round(float(prediction[0][4]), 2)
+    rook = np.round(float(prediction[0][5]), 2)
+
+    
+    return {'Bishop': bishop, 'King': king, 'Knight': knight, 'Pawn': pawn, 'Queen': queen, 'Rook': rook}
+
+input_image = gr.Image()
+iface = gr.Interface(
+    fn=predict_figure,
+    inputs=input_image, 
+    outputs=gr.Label(),
+    description="A simple mlp classification model for image classification using the mnist dataset.")
+iface.launch(share=True)
+
+
+

requirements.txt

@@ -0,0 +1 @@
+tensorflow==2.16.1