cv2_imshow collab 没有显示使用 cnn+l;stm 模型预测视频的任何内容

Question

大家好，我正在尝试将我的模型测试到视频中以进行预测

我没有错误日志或任何东西

但没有出现，我正在尝试打开视频并使用我的 cnn(alexnet)+lstm 模型进行预测

这是我的代码

model_path = 'Model/CCTV_10Frame_Adam_Model_1e2_b16_regul.h5'
model = models.load_model(model_path)

vid = cv2.VideoCapture("Data16_116.mp4")

while(True):
    ret, frame = vid.read()
    start = time.time()
    if ret:
        draw = frame.copy()
        draw = cv2.cvtColor(draw, cv2.COLOR_BGR2RGB)
        scale_percent = 20 # percent of original size
        width = 299
        height = width
        dim = (width, height)
        frame_set = cv2.resize(draw, dim, interpolation = cv2.INTER_AREA)
        frame_set=np.arange(10*width*height*3).reshape(10,width, height, 3)
        frame_set.reshape(10, width, height, 3).shape
        frame_set = np.expand_dims(frame_set, axis=0)
        result=model.predict(frame_set)
        
        cv2_imshow(result)

        if cv2.waitKey(1) & 0xFF == ord('q'):
            break
        else:
            break

vid.release()
cv2.destroyAllWindows()

有人知道这件事吗？

任何答案将不胜感激

非常感谢！

注意：我确实在 vsc 中尝试过，但遗憾的是它只打开了 1 秒并且日志说

Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.25GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.

Answer 1

"""您能否在从代码中删除 **else:break** 块后进行检查？因为它可能会跳过相机帧而不验证来自用户的任何中断。 """

    if cv2.waitKey(1) & 0xFF == ord('q'): // remove the else block
        break

cv2_imshow collab 没有显示使用 cnn+l;stm 模型预测视频的任何内容

cv2_imshow collab doesnt show anything for predicting video using cnn+l;stm model

python

deep-learning

conv-neural-network

lstm

tensorflow