MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.
Source framework with version (like Tensorflow 1.4.1 with GPU):tensorflow 1.2.1
Destination framework with version (like CNTK 2.3 with GPU):pytorch 1.5
there are "net_jpg101\model.data-00000-of-00001 net_jpg101\model.index net_jpg101\model.meta" in the tensorflow project.
but the instructions use .ckpt like "-iw imagenet_resnet_v2_152.ckpt"
i wonder what if i don't have the .ckpt file?
how can i trasnfor tensorflow to pytorch ?
Platform (like ubuntu 16.04/win10):win10
Python version:3.6
Source framework with version (like Tensorflow 1.4.1 with GPU):tensorflow 1.2.1
Destination framework with version (like CNTK 2.3 with GPU):pytorch 1.5
there are "net_jpg101\model.data-00000-of-00001 net_jpg101\model.index net_jpg101\model.meta" in the tensorflow project. but the instructions use .ckpt like "-iw imagenet_resnet_v2_152.ckpt" i wonder what if i don't have the .ckpt file? how can i trasnfor tensorflow to pytorch ?