我的快速解决方案有点难看.

My quick solution is a little bit ugly.

我只是复制了ResNet的代码，并将TimeDistributed添加到所有层，然后将基本" ResNet的权重加载到了自定义的ResNet上.

I just copied the code of ResNet and added TimeDistributed to all layers and then loaded the weights from a "basic" ResNet on my customized ResNet.

注意:

要能够像这样分析图像序列，确实会在GPU上占用大量内存.

To be able to analyze sequence of images like this does take a huge amount of memory on the gpu.