Update app.py

app.py

@@ -23,97 +23,6 @@ model.overrides['max_det'] = 1000  # maximum number of detections per image
 model.to(device)
 
 
-#play = pafy.new(_URL).streams[-1] #'-1' means read the lowest quality of video.
-
-#assert play is not None # we want to make sure their is a input to read.
-#stream = cv2.VideoCapture(play.url) #create a opencv video stream.
-#stream = cv2.VideoCapture(0) # 0 means read from local camera.
-#camera_ip = "rtsp://username:password@IP/port"
-#stream = cv2.VideoCapture(camera_ip)
-#class Capvid:
- 
-
-# load model
-
-# set image
-#image = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'
-
-# perform inference
-#def show(feed)
-#    return model.predict(feed)
-
-# observe results
-#print(results[0].boxes)
-#render = render_result(model=model, image=image, result=results[0])
-#render.show()
-
-"""
-The function below identifies the device which is availabe to make the prediction and uses it to load and infer the frame. Once it has results it will extract the labels and cordinates(Along with scores) for each object detected in the frame.
-"""
-def score_frame(frame):
-    #frame = [torch.tensor(frame)]
-    result = model(frame)
-    results = [torch.tensor(result)]
-    labels = results[0][:, -1].numpy()
-    cord = results[0][:, :-1].numpy()
-    return labels, cord
-
-"""
-The function below takes the results and the frame as input and plots boxes over all the objects which have a score higer than our threshold.
-"""
-def plot_boxes(results, frame):
-    labels, cord = results
-    n = len(labels)
-    x_shape, y_shape = frame.shape[1], frame.shape[0]
-    for i in range(n):
-        row = cord[i]
-        # If score is less than 0.2 we avoid making a prediction.
-        if row[4] < 0.2: 
-            continue
-        x1 = int(row[0]*x_shape)
-        y1 = int(row[1]*y_shape)
-        x2 = int(row[2]*x_shape)
-        y2 = int(row[3]*y_shape)
-        bgr = (0, 255, 0) # color of the box
-        classes = model.names # Get the name of label index
-        label_font = cv2.FONT_HERSHEY_SIMPLEX #Font for the label.
-        cv2.rectangle(frame, \
-                      (x1, y1), (x2, y2), \
-                       bgr, 2) #Plot the boxes
-        cv2.putText(frame,\
-                    classes[labels[i]], \
-                    (x1, y1), \
-                    label_font, 0.9, bgr, 2) #Put a label over box.
-        return frame
-
-"""
-The Function below oracestrates the entire operation and performs the real-time parsing for video stream.
-"""
-def vid_play(vid_cap):
-    stream = cv2.VideoCapture(vid_cap)
-    
-    player = stream #Get your video stream.
-    assert player.isOpened() # Make sure that their is a stream. 
-    #Below code creates a new video writer object to write our
-    #output stream.
-    out_vid = ("vid_tmp.avi")
-    x_shape = int(player.get(cv2.CAP_PROP_FRAME_WIDTH))
-    y_shape = int(player.get(cv2.CAP_PROP_FRAME_HEIGHT))
-    four_cc = cv2.VideoWriter_fourcc(*"MJPG") #Using MJPEG codex
-    out = cv2.VideoWriter(out_vid, four_cc, 20, \
-                          (x_shape, y_shape)) 
-    ret, frame = player.read() # Read the first frame.
-    while True: # Run until stream is out of frames
-        start_time = time.time() # We would like to measure the FPS.
-        results = score_frame(frame) # Score the Frame
-        frame = plot_boxes(results, frame) # Plot the boxes.
-        end_time = time.time()
-        fps = 1/np.round(end_time - start_time, 3) #Measure the FPS.
-        print(f"Frames Per Second : {fps}")
-        out.write(frame) # Write the frame onto the output.
-        ret, frame = player.read() # Read next frame.
-        return out
-
 with gr.Blocks() as app:
     stream = gr.State()
     def load(URL):
@@ -128,44 +37,27 @@ with gr.Blocks() as app:
         
     def vid_play2(cap,frame_num):
         player = cv2.VideoCapture(cap)
-        
-        #player = stream #Get your video stream.
         assert player.isOpened() # Make sure that their is a stream. 
-        #Below code creates a new video writer object to write our
-        #output stream.
-        #out_vid = ("vid_tmp.avi")
-        #x_shape = int(player.get(cv2.CAP_PROP_FRAME_WIDTH))
-        #y_shape = int(player.get(cv2.CAP_PROP_FRAME_HEIGHT))
-        #four_cc = cv2.VideoWriter_fourcc(*"MJPG") #Using MJPEG codex
-        #out = cv2.VideoWriter(out_vid, four_cc, 20,(x_shape, y_shape)) 
-        #stream.set(cv2.CAP_PROP_POS_FRAMES, int(frame_num))
+        player.set(cv2.CAP_PROP_POS_FRAMES, int(frame_num))
 
         ret, frame = player.read(int(frame_num))
         results = model.predict(frame)
-
         render = render_result(model=model, image=frame, result=results[0])
-        #out = render.show()
-        #start_time = time.time() # We would like to measure the FPS.
-        #results = score_frame(frame) # Score the Frame
-        #frame = plot_boxes(results, frame) # Plot the boxes.
-        #end_time = time.time()
-        #fps = 1/np.round(end_time - start_time, 3) #Measure the FPS.
-        #print(f"Frames Per Second : {fps}")
-        #out.write(frame) # Write the frame onto the output.
-        #ret, frame = player.read() # Read next frame.
         return render
    
      
 
-
-    youtube_url = gr.Textbox(label="YouTube URL",value=f"{URL}")
-    load_button = gr.Button("Load Video")
     with gr.Row():
-        total_frames = gr.Number(interactive=False)
-        run_button = gr.Button()
-        cur_frame = gr.Number()
+        with gr.Column():
+            youtube_url = gr.Textbox(label="YouTube URL",value=f"{URL}")
+            load_button = gr.Button("Load Video")
+            output_win = gr.Video()
+        with gr.Column():
+            with gr.Row():
+                cur_frame = gr.Number()    
+                total_frames = gr.Number(interactive=False)
+            run_button = gr.Button()
     with gr.Row():
-        output_win = gr.Video()
         det_win = gr.Image(source="webcam", streaming=True)
     load_button.click(load,youtube_url,[output_win,cur_frame,total_frames])
     run_button.click(vid_play2, [output_win,cur_frame], det_win)