MaxPooling with floor mode not consistent with original implementation

[scenarios]

Hi,
I've noticed you are using the maxpooling without ceil mode in 'InceptionModule2', which is not consistent with the caffe implementation. But you can still reproduce the results with the pretrained caffemodel?
BTW, I made the tsn caffemodel available in tensorflow, however, with every layer keeping identical with the TSN caffe implementation, there's still a 10% drop.

[shuangshuangguo]

@scenarios My work just transfers caffe-model to pytorch-model by reading layer parameters. When I get parameters, I use tsn-pytorch code given by authors to test. How does max pooling perform doesn't matter result.
About the second question, I think maybe you should check your input, such as all of transformation.