torch-inception-resnet-v2
torch-inception-resnet-v2 copied to clipboard
The inception-resnet-v2 models re-trained from scratch via torch
Hello, I implemented your setting 2 and 3, but both get a wrong performance much like [https://github.com/revilokeb/inception_resnetv2_caffe](url), so could you release some results or tips about these experiments?
according to "We have trained our networks with stochastic gradient utilizing the TensorFlow [1] distributed machine learning system using 20 replicas running each on a NVidia Kepler GPU" from paper...
I think the file is missing in the PR. Is it possible for you to share it ? thanks :)