Hi everyone, with torch we had loadcaffe which was extremely useful. Is there any way to achieve the same functionality in pytorch? Simply how can we load caffe models in pytorch?
Thanks a lot!
One way would be to use loadcaffe to load weights in Lua, save them, and use torch.utils.serialization.load_lua to load them in PyTorch. Unfortunately we don't have a ready solution for that yet.
Thanks Adam,hope there is some plan for future solution?
Not anytime soon I'm afraid. There are a lot of high priority tasks.
But it should be quite simple for someone to add that. You just need to read protobufs and translate graphs into modules.
gotcha ya. Thanks a lot for the suggestions.
@apaszke,you means that I can load caffe models in Pytorch using torch?
Yes it should be possible. But these will only be torch.legacy.nn models, not torch.nn networks.