ding-Chen

Results 4 issues of ding-Chen

我在单GPU环境下执行: export CUDA_VISIBLE_DEVICES=0 python -m torch.distributed.launch \ --nproc_per_node=1 train.py \ --respath checkpoints/train_STDC1-Seg/ \ --backbone STDCNet813 \ --mode train \ --n_workers_train 12 \ --n_workers_val 1 \ --max_iter 60000 \ --use_boundary_8 True...

您好作者,请问使用1080Ti GPU在Cityscapes语义分割上训练了多长时间?

I didn't understand how to position embedding got in this paper. I read this article in detail, but I didn't find the answer. Could you please introduce it? Thank you.

Hi, how to download the pre-trained model? Show no permission when I download.