when I train Inception_v4 by caffe, it take a mistake.

[clscy]

I train your Inception_v3_GoogLeNet by caffe, it is successful. But I train Inception_v4 by caffe, it is wrong.

inception_v4_train_test.prototxt.txt

The mistake is
Check failed: top_shape[j] == bottom[i]->shape(j) (45 vs. 46) All input
s must have the same shape, except at concat_axis.
So,I want to konw how you modofy your Inception_v3_GoogLeNet through original Inception_v3.
thanks.

[n3011]

Inception v4 needs careful design, as it uses VALID padding for some layers (size mismatches due to valid padding only ). So to make thing simple you can use SAME padding for all layers.