Update app.py

app.py

@@ -3,7 +3,7 @@ import numpy as np
 import gradio as gr
 import tensorflow as tf
 
-print(33333333333333333333333333333)
+
 model = tf.keras.models.Sequential([
     tf.keras.layers.Input(shape=(28, 28, 1)),
     tf.keras.layers.Conv2D(filters=16, kernel_size=3, strides=1, padding='same', activation='relu', input_shape=(28, 28, 1)),
@@ -24,35 +24,20 @@ model.compile(optimizer=tf.keras.optimizers.Adam(),
              metrics=[tf.keras.metrics.MeanSquaredError(), tf.keras.metrics.AUC(), tf.keras.metrics.CategoricalAccuracy()])
 
 model = tf.keras.models.load_model('my_model.h5', compile=False)
-print(222222222222222222222222)
+
 
 def classify_image(image):
     image = np.array(image['composite'])[:, :, 3] * 255
     image = image[..., np.newaxis]
-    # if len(image.shape) >= 3:
-        # image = tf.image.rgb_to_grayscale(image)
-    
     image_tensor = tf.convert_to_tensor(image)
-    
     image_tensor = tf.image.resize(image_tensor, (28, 28)),
-    # print(1111111111111111111111111111111111111111111)
-    # print(image_tensor.shape)
-    
     image_tensor = tf.cast(image_tensor, tf.float32)
-    print(1111111111111111111111111111111111111111111)
-    # print(image_tensor.shape)
-    
-    # image_tensor = tf.expand_dims(image_tensor, 0)
     image_tensor = image_tensor / 255.0
-    print(1111111111111111111111111111111111111111111)
-    # print(image_tensor.shape)
-    
     prediction = model.predict(image_tensor)
+    print(prediction)
+    print(prediction.argmax)
     
-    print(1111111111111111111111111111111111111111111)
     prediction_label = str(prediction.argmax())
-    print(1111111111111111111111111111111111111111111)
-    
     return prediction_label
 
 
@@ -60,51 +45,19 @@ title = "Draw to Search"
 description = "Using the power of AI to detect the number you draw!"
 article = "for source code you can visit [my github](https://github.com/mralamdari)"
 
-# example_list = [["examples/" + example] for example in os.listdir("examples")]
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+# interface = gr.Interface(fn=classify_image,
+#                           inputs=gr.Sketchpad(),
+#                           outputs='text')
 
 interface = gr.Interface(fn=classify_image,
+                          # inputs=gr.Image(type="pil"),
                           inputs=gr.Sketchpad(),
-                          outputs='text')
-
-# interface = gr.Interface(fn=classify_image,
-#                           # inputs=gr.Image(type="pil"),
-#                           inputs=gr.Sketchpad(),
-#                           # outputs=gr.Label(num_top_classes=3, label="Predictions"),
-#                           outputs='text',
-#                           examples=example_list, 
-#                           title=title,
-#                           description=description,
-#                           article=article)
+                          # outputs=gr.Label(num_top_classes=3, label="Predictions"),
+                          outputs='text',
+                          examples=example_list, 
+                          title=title,
+                          description=description,
+                          article=article)
                         
-interface.launch()
-
-
-
-
-# import gradio as gr
-# # from PIL import Image
-
-# def predict(img):
-#     print(img)
-#     print(11111111111111111111111111111)
-#     print(np.unique(np.array(img['composite'])[:, :, 0], return_counts=True))
-    
-#     print(11111111111111111111111111111)
-#     print(np.unique(np.array(img['composite'])[:, :, 1], return_counts=True))
-    
-#     print(11111111111111111111111111111)
-#     print(np.unique(np.array(img['composite'])[:, :, 2], return_counts=True))
-    
-#     print(11111111111111111111111111111)
-#     print(np.unique(np.array(img['composite'])[:, :, 3], return_counts=True))
-#     img = np.array(img['composite'])[:, :, 3] * 255
-#     print(img)
-#     # print(np.squeeze(np.array(img['composite']), axis=-1))
-#     return img
-
-# sp = gr.Sketchpad()
-
-# gr.Interface(fn=predict,
-#              inputs=sp,
-#              outputs='image',
-#              live=True).launch()
+interface.launch()