convolution layers of keras and caffe has different output

[xiaofeiwu]

It seems that the output of convolution layers of keras and caffe has different output even when the input the and weights are all the same. It may be caused by the padding implementation in tensorflow and caffe. Does anyone meet the same issue?

[nerddd]

Yes，I met the same problem.Did u solve the issue?

[nerddd]

I think pooling layer has the difference between caffe and tf

[to-be-snail]

It seems that the output of convolution layers of keras and caffe has different output even when the input the and weights are all the same. It may be caused by the padding implementation in tensorflow and caffe. Does anyone meet the same issue?

I met the same question.Did you solve the problem?

[to-be-snail]

I think pooling layer has the difference between caffe and tf

I met the same question.Did you solve the problem?

[DanielXu123]

So, bascially, the transfered caffemodel can not get the same results as the keras .h5 model predict?