CNN

フィルタ数って？

tf.nn.conv2d

filters: A Tensor. Must have the same type as input. A 4-D tensor of shape (filter_height, filter_width, in_channels, out_channels)

tf.keras.layers.Conv2D

filters: Integer, the dimensionality of the output space (i.e. the number of output filters in the convolution).

複数チャネルの畳み込みって？

1x1(pointwise)畳み込みって？

チャンネルにまたがって畳み込み？