Bowei Chen

Hi @juanluisrosaramos, Did you find the "fine-tuning procedure"? Or do you have any insight for the minimum of images for fine-tuning? Thank you!

Hi, I am able to run the code after reducing the network size. I tested on two 12GB Titan X: If my network is large, lets say 20GB, then the...

Hi, Thanks for your reply. It turns out that it was not stuck in these two lines. My finding is that: For this function: [https://github.com/vacancy/Synchronized-BatchNorm-PyTorch/blob/7553990fb9a917cddd9342e89b6dc12a70573f5b/sync_batchnorm/batchnorm.py#L78](url) The master process will execute...

Not sure about it... But it works fine when there is no OOM issue, so I guess the training code is correct. My code is modified based on this repo...