Saumya Kumaar Saksena

Hi @zpge I have prepared a script that allows you train your own data using this repo's training strategy. It works on my machine with Pytorch-1.4.0 and Python-3.6.7 (Ubuntu 18.04.03)....

Hi @poornimajd You can load the weights as it is from a pre-trained model, no issues. Just one thing that you need to be careful about is the final layers...

That may be because the classes might be under-represented. You may want to use class balancing techniques like ENet, or maybe use OHEM (Online hard example mining) loss to mitigate...

Hi @huang229 Please make sure that your training environment is similar to what has been mentioned in this repo. I have reproduced the results successfully. An overview of your training...

Ahh my bad. I did not read that properly. But indeed, BiseNEtv2 has some claims that I am not yet sure of. I am in the process of implementing the...

@huang229 the training is indeed slower than V1, for the same crop-size, batchsize and iterations. Perhaps the authors should open-source their codes, but I am not sure when would that...

Hi @lgqfhwy Were you able to resolve this issue because I am facing it as of now. Please let me know your workaround. I did try increasing the max recursion...

Hi @moahaimen I could perhaps try to help on weekends, but weekdays would not be possible.

Hi, Apologies for the late reply. I did not really create an inference code, as this was more of a University assignment. But I will look into it and upload...

Hi @DhineshKS04 Not sure I completely understand your statement.