Update app.py

app.py

@@ -359,10 +359,17 @@ def classify(platform, UserInput, Images, Textbox2, Textbox3):
                 get_image = requests.get(Images, headers=headers)
                 if get_image.status_code == 200:
                     # print(get_image.content)
-                    # imageData = cv.imdecode(np.asarray(bytearray(get_image.content), dtype="uint8"), cv.IMREAD_COLOR)
-                    image_bytes = get_image.content
-                    image = Image.open(io.BytesIO(image_bytes))
-                    imageData = cv.cvtColor(np.array(image), cv.COLOR_RGB2BGR)
+                    random_id = random.randint(1000, 9999)
+
+                    file_extension = ".png"
+                    filename = f"image_{random_id}{file_extension}"
+                    with open(filename, "wb") as file:
+                        file.write(get_image.content)
+
+                    print(f"Saved image as: {filename}")
+
+                    full_path = os.path.join(os.getcwd(), filename)
+                    print(f"Saved image as: {full_path}")
             elif platform == "web":
                 print("WEB")
                 # Handle web case if needed
@@ -370,15 +377,10 @@ def classify(platform, UserInput, Images, Textbox2, Textbox3):
                 pass
 
             image_data = cv.resize(imageData, (224, 224))
-            normalized_image_array = (imageData.astype(np.float32) / 127.0) - 1
-            data = np.zeros((1, 224, 224, 3))
+            normalized_image_array = (image_data.astype(np.float32) / 127.0) - 1
             data[0] = normalized_image_array
-            prediction = model.predict(data)
-            # image_data = cv.resize(imageData, (224, 224))
-            # normalized_image_array = (image_data.astype(np.float32) / 127.0) - 1
-            # data[0] = normalized_image_array
 
-            # prediction = model.predict(data)
+            prediction = model.predict(data)
 
             max_label_index = None
             max_prediction_value = -1