Conv1D卷积层输入输出:
输入尺寸
3D 张量 ,尺寸为 (batch_size, steps, input_dim)。
输出尺寸
3D 张量,尺寸为 (batch_size, new_steps, filters)。 由于填充或窗口按步长滑动,steps 值可能已更改。
pooling 层输入输出:
输入尺寸
如果 data_format='channels_last', 输入为 3D 张量,尺寸为: (batch_size, steps, features)
如果data_format='channels_first', 输入为 3D 张量,尺寸为: (batch_size, features, steps)
输出尺寸
如果 data_format='channels_last', 输出为 3D 张量,尺寸为: (batch_size, downsampled_steps, features)
如果 data_format='channels_first', 输出为 3D 张量,尺寸为: (batch_size, features, downsampled_steps)
NIN: