tinycoop

@jacobgil Hey! There is a problem with size mismatch. For example: `RuntimeError: Error(s) in loading state_dict for ModifiedVGG16Model: size mismatch for features.0.weight: copying a param with shape torch.Size([50, 3, 3,...

@ms-krajesh Probably not a solution but I just rewrote model architecture with altered layer numbers.

@okuchaiev I have lowered my lr to 0.001 and optimizer to Adam. nan's disappeared but loss wont converge. label's range between 1-5. Also my batch:64 and hidden_layers:128,196,256,320. I have tried...

@UdonDa could you please expand your answer? where to fix the code so it would work on multiple gpu?\ thanx

HI @perone , EuclidesDB is deployed in Ubuntu 16.04 and segmentation fault happens when I relaunch EuclidesDB. When I first launched EuclidesDB there were no errors. Then I started adding...

@perone, this is without Docker, In docker it worked just fine. I actually copied model from docker and didn't add any other model. I use PyTorch 0.4.

@perone Thank you for your work! I'll try to upgrade PyTorch. Regarding to faiss, I found some benchmarks here [http://www.itu.dk/people/pagh/SSS/ann-benchmarks/glove-data_10_-1_glove-query_angular.html](url).

@novioleo could you please share your training config like? -resnet50 or resnet34? -batch size -how many epochs did you train? -didnt you overfit? -which dataset are you using to train?

@novioleo Thanx did it take you like weeks to get loss: 0.0028 ? because it trains really slowly

@novioleo I'm trained it on icdar2017(7200 images) and now fine-tuning on icdar2015. Could you please share your weights with 0.0028 loss? Thanx