Closed uhfband closed 6 years ago
Сould you please clarify, It's ok to have pool size less than stride size? eg nasnet.py line 620 p1 = AveragePooling2D((1, 1), strides=(2, 2), padding='valid', name='adjust_avg_pool1%s' % id)(p)
Yes. It's a point wise averaging which simply reduces the spacial dimension by half.
Since the weights load correctly, and predictions are correct, such an operation is correct.
Сould you please clarify, It's ok to have pool size less than stride size? eg nasnet.py line 620 p1 = AveragePooling2D((1, 1), strides=(2, 2), padding='valid', name='adjust_avg_pool1%s' % id)(p)