Update app.py

app.py

@@ -1,205 +1,3 @@
-# import gradio as gr
-# import cv2
-# import numpy as np
-# import onnxruntime as ort
-
-# # Load the ONNX model using onnxruntime
-# onnx_model_path = "Model_IV.onnx"  # Update with your ONNX model path
-# session = ort.InferenceSession(onnx_model_path)
-
-# # Function to perform object detection with the ONNX model
-# def detect_objects(frame, confidence_threshold=0.5):
-#     # Convert the frame from BGR (OpenCV) to RGB
-#     image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-    
-#     # Preprocessing: Resize and normalize the image
-#     # Assuming YOLO model input is 640x640, update according to your model's input size
-#     input_size = (640, 640)
-#     image_resized = cv2.resize(image, input_size)
-#     image_normalized = image_resized / 255.0  # Normalize to [0, 1]
-#     image_input = np.transpose(image_normalized, (2, 0, 1))  # Change to CHW format
-#     image_input = np.expand_dims(image_input, axis=0).astype(np.float32)  # Add batch dimension
-
-#     # Perform inference
-#     inputs = {session.get_inputs()[0].name: image_input}
-#     outputs = session.run(None, inputs)
-    
-#     # # Assuming YOLO model outputs are in the form of [boxes, confidences, class_probs]
-#     # boxes, confidences, class_probs = outputs
-
-#     # # Post-processing: Filter boxes by confidence threshold
-#     # detections = []
-#     # for i, confidence in enumerate(confidences[0]):
-#     #     if confidence >= confidence_threshold:
-#     #         x1, y1, x2, y2 = boxes[0][i]
-#     #         class_id = np.argmax(class_probs[0][i])  # Get class with highest probability
-#     #         detections.append((x1, y1, x2, y2, confidence, class_id))
-    
-#     # # Draw bounding boxes and labels on the image
-#     # for (x1, y1, x2, y2, confidence, class_id) in detections:
-#     #     color = (0, 255, 0)  # Green color for bounding boxes
-#     #     cv2.rectangle(image, (int(x1), int(y1)), (int(x2), int(y2)), color, 2)
-#     #     label = f"Class {class_id}: {confidence:.2f}"
-#     #     cv2.putText(image, label, (int(x1), int(y1)-10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
-    
-#     # # Convert the image back to BGR for displaying in Gradio
-#     # image_bgr = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
-    
-#     return outputs
-
-# # Gradio interface to use the webcam for real-time object detection
-# # Added a slider for the confidence threshold
-# iface = gr.Interface(fn=detect_objects, 
-#                      #inputs=[
-#                          # gr.Video(sources="webcam", type="numpy"),  # Webcam input
-#                          inputs = gr.Image(sources=["webcam"], type="numpy"),
-#                          # gr.Slider(minimum=0.0, maximum=1.0, default=0.5, label="Confidence Threshold")  # Confidence slider
-#                      # ],  
-#                      outputs="image")  # Show output image with bounding boxes
-
-# iface.launch()
-###
-# import gradio as gr
-# import cv2
-# from huggingface_hub import hf_hub_download
-# from gradio_webrtc import WebRTC
-# from twilio.rest import Client
-# import os
-# from inference import YOLOv8
-
-# model_file = hf_hub_download(
-#     repo_id="aje6/ASL-Fingerspelling-Detection", filename="onnx/Model_IV.onnx"
-# )
-
-# model = YOLOv8(model_file)
-
-# account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
-# auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
-
-# if account_sid and auth_token:
-#     client = Client(account_sid, auth_token)
-
-#     token = client.tokens.create()
-
-#     rtc_configuration = {
-#         "iceServers": token.ice_servers,
-#         "iceTransportPolicy": "relay",
-#     }
-# else:
-#     rtc_configuration = None
-
-
-# def detection(image, conf_threshold=0.3):
-#     image = cv2.resize(image, (model.input_width, model.input_height))
-#     new_image = model.detect_objects(image, conf_threshold)
-#     return cv2.resize(new_image, (500, 500))
-
-
-# css = """.my-group {max-width: 600px !important; max-height: 600 !important;}
-#                       .my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""
-
-
-# with gr.Blocks(css=css) as demo:
-#     gr.HTML(
-#         """
-#     <h1 style='text-align: center'>
-#     YOLOv10 Webcam Stream (Powered by WebRTC ⚡️)
-#     </h1>
-#     """
-#     )
-#     gr.HTML(
-#         """
-#         <h3 style='text-align: center'>
-#         <a href='https://arxiv.org/abs/2405.14458' target='_blank'>arXiv</a> | <a href='https://github.com/THU-MIG/yolov10' target='_blank'>github</a>
-#         </h3>
-#         """
-#     )
-#     with gr.Column(elem_classes=["my-column"]):
-#         with gr.Group(elem_classes=["my-group"]):
-#             image = WebRTC(label="Stream", rtc_configuration=rtc_configuration)
-#             conf_threshold = gr.Slider(
-#                 label="Confidence Threshold",
-#                 minimum=0.0,
-#                 maximum=1.0,
-#                 step=0.05,
-#                 value=0.30,
-#             )
-
-#         image.stream(
-#             fn=detection, inputs=[image, conf_threshold], outputs=[image], time_limit=10
-#         )
-
-# if __name__ == "__main__":
-#     demo.launch()
-
-# import gradio as gr
-# import numpy as np
-# import cv2
-# from ultralytics import YOLO
-
-# model = YOLO('Model_IV.pt')
-
-# def transform_cv2(frame, transform):
-#     if transform == "cartoon":
-#         # prepare color
-#         img_color = cv2.pyrDown(cv2.pyrDown(frame))
-#         for _ in range(6):
-#             img_color = cv2.bilateralFilter(img_color, 9, 9, 7)
-#         img_color = cv2.pyrUp(cv2.pyrUp(img_color))
-
-#         # prepare edges
-#         img_edges = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
-#         img_edges = cv2.adaptiveThreshold(
-#             cv2.medianBlur(img_edges, 7),
-#             255,
-#             cv2.ADAPTIVE_THRESH_MEAN_C,
-#             cv2.THRESH_BINARY,
-#             9,
-#             2,
-#         )
-#         img_edges = cv2.cvtColor(img_edges, cv2.COLOR_GRAY2RGB)
-#         # combine color and edges
-#         img = cv2.bitwise_and(img_color, img_edges)
-#         return img
-#     elif transform == "edges":
-#         # perform edge detection
-#         img = cv2.cvtColor(cv2.Canny(frame, 100, 200), cv2.COLOR_GRAY2BGR)
-#         return img
-#     else:
-#         return np.flipud(frame)
-
-# with gr.Blocks() as demo:
-#     with gr.Row():
-#         with gr.Column():
-#             transform = gr.Dropdown(choices=["cartoon", "edges", "flip"],
-#                                     value="flip", label="Transformation")
-#             input_img = gr.Image(sources=["webcam"], type="numpy")
-#         with gr.Column():
-#             output_img = gr.Image(streaming=True)
-#         dep = input_img.stream(transform_cv2, [input_img, transform], [output_img],
-#                                 time_limit=30, stream_every=0.1, concurrency_limit=30)
-
-# if __name__ == "__main__":
-#     demo.launch()
-
-###
-
-# import gradio as gr
-# import torch
-# import cv2
-
-# # Load the YOLOv8 model
-# model = torch.hub.load('ultralytics/yolov8', 'yolov8s', trust_repo=True)
-# model.load_state_dict(torch.load('Model_IV'))
-
-# def inference(img):
-#     results = model(img)
-#     annotated_img = results.render()[0]
-#     return annotated_img
-
-# iface = gr.Interface(fn=inference, inputs="webcam", outputs="image")
-# iface.launch()
-
 import gradio as gr
 import torch
 from PIL import Image
@@ -209,36 +7,13 @@ import onnxruntime as ort
 import cv2
 import numpy as np
 
-# Load your model
-
-# model = YOLO("Model_IV.pt")
-# model = torch.load("Model_IV.pt")
-# model.eval()
-# checkpoint = torch.load("Model_IV.pt")
-# model.load_state_dict(checkpoint)  # Load the saved weights
-# model.eval()  # Set the model to evaluation mode
-
 # Load the onnx model
 model = ort.InferenceSession("Model_IV.onnx")
 
-# Define preprocessing
-# transform = T.Compose([
-#     T.Resize((224, 224)),  # Adjust to your model's input size
-#     T.ToTensor(),
-# ])
-
 def predict(image):
-    # # Preprocess the image
-    # img_tensor = transform(image).unsqueeze(0)  # Add batch dimension
-    
-    # # # Make prediction
-    # # with torch.no_grad():
-    # #     output = model(img_tensor)
-    
-    # # Process output (adjust based on your model's format)
-    # results = model(image)
-    # annotated_img = results[0].plot()
-    # return annotated_img
+    # Save shape of original image for later
+    original_image_shape = image.shape
+    print("Original image shape:", original_image_shape)
 
     # Preprocess the image
 
@@ -249,9 +24,6 @@ def predict(image):
     # Resize the image to the model's input shape
     image = cv2.resize(image, (input_shape[2], input_shape[3]))
 
-    original_image_shape = image.shape
-    print("Original image shape:", original_image_shape)
-
     # Reshape the image to match the model's input shape
     image = image.reshape(3, 640, 640)
 
@@ -266,34 +38,20 @@ def predict(image):
     if len(input_shape) == 4 and input_shape[0] == 1:
         image = np.expand_dims(image, axis=0)
     image = image.astype(np.float32)
-
-    print("Input image shape:", image.shape)
     
     # Make prediction
+    print("Input image shape:", image.shape)
     output = model.run(None, {input_name: image})
-
-    # print("Output shape:", output.shape)
-    
-    # print("type output:", type(output))
-    # print(output)
+    print("Output image shape:", output[0].shape)
 
     # Postprocess output image
-    
     annotated_img = output[0]
-
-    
     
-    # annotated_img = (output[0] / 255.0 - mean)/std
-    # annotated_img = classes[output[0][0].argmax(0)]
-    
-    print("Annotated image type before normalization:", type(annotated_img))
+    # print("Annotated image type before normalization:", type(annotated_img))
     # print("Annotated image before normalization:", annotated_img)
     print("Min value of image before normalization:", np.min(annotated_img))
     print("Max value of image before normalization:", np.max(annotated_img))
 
-    # # Normalize output image using ImageNet-style normalization (again)
-    # annotated_img = (annotated_img / 255.0 - mean)/std
-
     # Normalize output image using Min-Max normalization
     min_val = np.min(annotated_img)
     max_val = np.max(annotated_img)
@@ -301,7 +59,7 @@ def predict(image):
 
     print("Min value of image after normalization:", np.min(annotated_img))
     print("Max value of image after normalization:", np.max(annotated_img))
-    print("annotated_img type after normalization:", type(annotated_img))
+    # print("annotated_img type after normalization:", type(annotated_img))
     # print("annotated_img shape after normalization:", annotated_img.shape)
 
     # Reshape the image to match the PIL Image input shape
@@ -310,20 +68,18 @@ def predict(image):
     print("annotated_img shape after reshape:", annotated_img.shape)
 
     # Convert to PIL Image
-    annotated_img = Image.fromarray(annotated_img)
-
+    annotated_img = Image.fromarray(annotated_img) # Hits a ValueError in this line
     print("PIL Image type:", type(annotated_img))
-    # print("PIL Image shape:", annotated_img.shape)
 
     return annotated_img
     
 # Gradio interface
 demo = gr.Interface(
     fn=predict,
-    inputs=gr.Image(sources=["webcam"], type="numpy"),  # Accepts image input
-    # outputs="image"  # Customize based on your output format
-    outputs=gr.Image(type="pil"),  # Accepts image input
+    inputs=gr.Image(sources=["webcam"], type="numpy"),  # Image input from webcam, as a numpy array
+    outputs=gr.Image(type="pil"),  # Image output from model, as a PIL Image
 )
 
+# Launch interface
 if __name__ == "__main__":
     demo.launch()