INNER CODE UNIT · Python

image

vietnh1009/QuickDraw · camera_app.py:89

                        image = canvas_gs[y:y + h, x:x + w]
                        image = cv2.resize(image, (28, 28))
                        image = np.array(image, dtype=np.float32)[None, None, :, :]
                        image = torch.from_numpy(image)
                        logits = model(image)
                        predicted_class = torch.argmax(logits[0])
                        # print (CLASSES[predicted_class])
                        is_shown = True
                    else:
                        print("The object drawn is too small. Please draw a bigger one!")
                        points = deque(maxlen=512)
                        canvas = np.zeros((480, 640, 3), dtype=np.uint8)

        # Read frame from camera
        ret, frame = camera.read()
        frame = cv2.flip(frame, 1)
        hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
        kernel = np.ones((5, 5), np.uint8)

View source record →

📰 Research Paper
Loading…
⏳ Fetching content…