我这个网络输入是4张图片序列,所以用了TimeDistributed层封装,但是运行时候在Flatten层报错了,怎么改才能正常运行呀?我就是要对这一组图像(4张)分类,之前用lstm之类的效果很差
这个是我的代码:
报的错误是这样的:
ValueError: The shape of the input to "Flatten" is not fully defined (got (None, 16, 16, 64). Make sure to pass a complete "input_shape" or "batch_input_shape" argument to the first layer in your model.