Haruko386

As show in pic:  It stuck in 0%. Any suggestion? My device: intel i7-13650H + Nivdia RTX 4060 laptop

I have pytorch2.0.1+cu118 mmcv-full=1.4.0 mmdet=2.14.0 when I try to start training with command `python main.py --dir_data /root/DiffusionDepth/Dataset/nyudepthv2 --data_name NYU --split_json ../data_json/nyu.json \ --patch_height 352 --patch_width 906 --gpus 0 --loss 1.0*L1+1.0*L2+1.0*DDIM...

congrats on great work I am a master's student researching depth estimation. Since our group is not well-funded and only has eight 4090 GPUs, I need to share one 4090...

Hi, Thanks for making your wonderful work public! I have read the paper, which mentions depth estimation for **high-resolution** images, but I did not find any instructions for testing high-resolution...

Hi, excellent work! I'm tring to reproduce this paper on my own PC, which have a single `RTX 4090 24GB`, my training config is: ``` { "train_data_path" : "/root/Dataset/Hypersim/precessed/train", "val_data_path"...

wrong word`unser` -> `under`