Danish Nazir

Thanks alot Sir it worked :)

Hi @YodaEmbedding @yoshitomo-matsubara , As suggested by @YodaEmbedding , I tried to train `bmshj2018-hyperprior` in DDP setting from scratch. I used two V100-16GB GPU's with `batch size of 16 each`...

Hi @yoshitomo-matsubara Thank you for your response. > Could you explain how you executed your script in distributed training mode? `CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch --nproc_per_node=2 --node_rank=0 examples/train.py -d /path/to/dataset/ --epochs...

Hi @yoshitomo-matsubara , Yes I will submit the PR as soon as possible. Thanks.

Hi , use ` randomness = dict(seed=42)` in the config to set the seed. Some models are sensitive to the seed while others are not. By default, no seed is...

arent the fps are too low ? for example with OpenCv without Movidus Chip i can get 6-8 FPS easily on raspberry pi 2

I see!! i have a board which has 2 gb ram 1.7ghz quad core now i want to run deep learning based detectors preferably Yolo and need to detect only...