Open fmthoker opened 6 years ago
Hi, did you have any luck with that?
I have .hdf5 files for TF/Keras if you want.
@pedro-abreu can you share them with me. Email address fmthoker@gmail.com
@pedro-abreu Thanks a lot, but Im using PyTorch atm. For anyone that may be interested, you can download the caffe pretrained weights and convert them to pytorch weights using parse_caffe.py in tsn-pytorch/tf_model_zoo/bninception.
@ekazakos Thanks man, I might switch to Pytorch eventually :). @fmthoker https://drive.google.com/drive/folders/13TaIjogd2ReNsKXNJ55o3_qsDWB5KlkM?usp=sharing here you go.
Thanks to folks! Do you mind sharing it to other users?
@yjxiong Sure, will do soon!
Everyone, you can find the pretrained Kinetics weights for TSN that I converted to work with PyTorch here: https://drive.google.com/drive/folders/1R4n8vSQJ0LtB1mPhhjMHEQrKj3UDQS1U?usp=sharing
Load the weights normally with:
state_dict = torch.load(pretrained)
If you are using Pytorch 0.4 do:
for k, v in state_dict.items(): state_dict[k] = torch.squeeze(v, dim=0)
@ekazakos
Thanks! Do you mind we sharing the files in the project website?
@yjxiong It is totally fine.
Everyone, you can find the pretrained Kinetics weights for TSN that I converted to work with PyTorch here: https://drive.google.com/drive/folders/1R4n8vSQJ0LtB1mPhhjMHEQrKj3UDQS1U?usp=sharing
Load the weights normally with:
state_dict = torch.load(pretrained)
If you are using Pytorch 0.4 do:
for k, v in state_dict.items(): state_dict[k] = torch.squeeze(v, dim=0)
@ekazakos Hello, thanks for sharing the weights. Do you have RGB Difference pretrained weights as well? Another question, have you used BNInception or other architecture?
@AhmedGamal1496 Im really sorry for the very late answer, I do not know how I missed this one. I do not have RGB Difference. And yes I've used only BN-Inception.
Hello everyone, Has anyone successfully converted kinetics pre-trained weights into Pytorch TSN?