Alex Sikand

I also need this too!

I'll try to replicate the results on the test dataset but it's really frustrating trying to get a lot of these research papers to work in code. Half the time...

@ashisharora010 @veralauee I have tried for a week straight to get this repository working and I'm still not having much luck. # Can't run coarse attribute prediction at all Although...

I added that `loss_attr` parameter to the init() method and it still won't work for me... can you explain further @genesysvip ?

I am interested in helping to support this library. I am in a position to add support for comma10k as well as GAN-based weather augmentations soon. I have previously trained...

I have an AGX Xavier on hand that I will hopefully be able to provide some benchmarks on for certain models. Unfortunately I'm no expert at TensorRT custom layers etc...

There are 240 epochs not just one epoch. And on my RTX 2080 Ti with a batch size of 12 I was doing one epoch every 35 minutes or so....

@rsj007 Please close this issue as there is an earlier and far more detailed thread related to building the TensorRT engine. It is one of the earliest issues in this...

Please close this issue as it is in the fit_lane function.

I found that it does not work well and I would avoid it by commenting out the line in the file.