Closed seriousran closed 4 years ago
Sorry for the late response, @seriousran. It is intended to designate require_flatten=True
in NASNet for disabling NASNet with non-default input shapes. For example, the followings are intended behaviours.
The underlying fact is that the architecture of NASNet differs according to input_shape
.
Specifically, the line 513 causes structural changes,
because the zero-padding in 2x down-sampling (conv, pool) perform differently
according to whether input_shape
is even or odd.
Thus, NASNet with weights='imagenet', include_top=any, input_shape=(None, None, 3)
is meaningless
because it may differ from the intended structure of the authors.
@taehoonlee Thanks for detailed response :) Now I can understand NASNet architecture more precisely.
To solve the issue #13690 in keras
https://github.com/keras-team/keras/issues/13690