SwinTransformer / MIM-Depth-Estimation

This is an official implementation of our CVPR 2023 paper "Revealing the Dark Secrets of Masked Image Modeling" on Depth Estimation.
MIT License
162 stars 12 forks source link

about metric #11

Open wdkang4715 opened 7 months ago

wdkang4715 commented 7 months ago

I trained my own dataset. But I got the below message.

image

So I check the image size and ground-truth value. when I check the iamge size 3011X4008 and the ground truth min : 0.0 the ground turth max : about 730.0

and my command line is like below:

python3 train.py --dataset my_data --max_depth 730.0 --max_depth_eval 730.0 --data_path ../data/ --backbone swin_large_v2 --depths 2 2 18 2 --num_filters 32 32 32 --deconv_kernels 2 2 2 --window_size 30 30 30 15 --pretrain_window_size 12 12 12 6 --use_shift True True False False --flip_test --shift_window_test --shift_size 2 --pretrained weights/swin_v2_large_simmim.pth --save_model --crop_h 480 --crop_w 480 --layer_decay 0.85 --drop_path_rate 0.5 --log_dir logs/ --save_result