Dharma KC

Hi guys, did anyone make it work on RTX 2080Ti machine? It doesn't work on mine.

Hi ztzhang, Thank you for the reply. The above method didn't work [yes exactly due to the difference in PyTorch and Cuda versions] and I tried with the given Docker...

Hi @sacmehta, Thank you for the reply. I will perform another experiment with your suggestion. Also, I suppose I will have to increase the warmup iterations as well. What value...

Hi @sacmehta, I did run the training with the --common.accum-freq 8 and the results are still similar. I got around 74.9% top-1 accuracy which is far low than what is...

Hi @sacmehta I am using the old version and using default parameters. I used warmup iterations of 25,000 because in your case the learning rate scheduler has seen 1024 *...

Thank you @sacmehta . Sure, I can provide the log details. I will try without changing warmup iterations and accumulation frequency of 8.

Thank you @sacmehta, Please find the logs from the following file. [tb_logs.zip](https://github.com/apple/ml-cvnets/files/8863827/tb_logs.zip)

@sacmehta I didn't save them. I will save them from the next run and will upload it. Thank you.

Hi @sacmehta Here's the log file for few runs. This time, it didn't converge (loss went to nan) [log.zip](https://github.com/apple/ml-cvnets/files/8950728/log.zip) .

HI @sacmehta That's what I did in the previous experiment (above comment 25k warmup iterations) and you suggested me to try warmup iterations of 3000.