Ellen Jian Gao

Just remove the line to run it... Have you successfully finished training? Seems no luck for me to get it work. With all the original settings as provided in the...

Updated results on VisDA17 classification (**70.11%**):  Difference is that previous result was obtained running the code under PyTorch 0.4, this one is using **PyTorch 0.3**. And...

> Hi, @Ellenisawake > do you have any idea what makes this performance difference betewwn pytorch 0.3 and 0.4? I didn't check in detail. Suggest that you just use 0.3...

> Hi, @Ellenisawake > do you use the code the author applied with VisDa classification directly? I couldn't understand the variable of 'val' in the test function, can you tell...

> Thanks for the code ! > > I have a question about the classifier. What is the differences between F1 and F2 classifier? > I can't find any differences...

> Because I'm a totally freshman to deep learning, I could'nt figure out how to process minst database ro other database to get "train_32x32.mat" and "test_32x32.mat". > Can you give...

> Because I'm a totally freshman to deep learning, I could'nt figure out how to process minst database ro other database to get "train_32x32.mat" and "test_32x32.mat". > Can you give...

Same issue here: - tried torch.no_grad(), not working - using 1080Ti, not working - tried with Pytorch 1.0 and 0.4.1, both not working

> Hello, > > Thank you for contacting Label Studio, > > Currently, Label Studio’s video annotation is designed so that a single VideoRectangle annotation (even when combined with a...

> Hi [@Ellenisawake](https://github.com/Ellenisawake) , if you enable evaluation with standard MOT metrics, you should have the tracking results exported as .txt somewhere in the output directory. Can you have a...