bts代码复现

最新推荐文章于 2023-06-21 14:57:40 发布

果冻虾仁猪心

最新推荐文章于 2023-06-21 14:57:40 发布

阅读量996

点赞数

分类专栏：单目深度估计文章标签：深度学习

本文链接：https://blog.csdn.net/shilling_bai/article/details/117961315

版权

单目深度估计专栏收录该内容

2 篇文章

订阅专栏

1.Prepare NYU Depth V2 test set：

795 training images
654 test images

图片存放路径：../../dataset/nyu_depth_v2/official_splits/

2.下载网络模型：

选用DenseNet121 可以在cpu上训练

添加语句device = torch.device("cuda" if torch.cuda.is_available() else "cpu")并且把cuda()改写为to(device)

Note: Modify arguments '--encoder', '--model_name', '--checkpoint_path' and '--pred_path' accordingly.

3.Live Demo

python bts_live_3d.py 
--model_name bts_nyu_v2_pytorch_densenet121 
--encoder densenet121_bts 
--checkpoint_path ./models/bts_nyu_v2_pytorch_densenet121/model 
--max_depth 10 
--input_height 480 
--input_width 640

4.Testing with NYU Depth V2

python bts_test.py arguments_test_nyu.txt

This will save results to ./result_bts_nyu_v2_pytorch_densenet121.

5.Evaluation

python ../utils/eval_with_pngs.py 
--pred_path result_bts_nyu_v2_pytorch_densenet161/raw/
--gt_path ../../dataset/nyu_depth_v2/official_splits/test/
--dataset nyu 
--min_depth_eval 1e-3 
--max_depth_eval 10 
--eigen_crop

You should see outputs like this:

Raw png files reading done
Evaluating 654 files
GT files reading done
0 GT files missing
Computing errors
d1, d2, d3, AbsRel, SqRel, RMSE, RMSElog, SILog, log10
0.885, 0.978, 0.994, 0.110, 0.066, 0.392, 0.142, 11.533, 0.047
Done.

6.Preparation for Training

python utils/download_from_gdrive.py 1AysroWpfISmm-yRFGBgFTrLy6FjQwvwP ../dataset/nyu_depth_v2/sync.zip

unzip sync.zip

Once the dataset is ready, you can train the network using following command.

python bts_main.py arguments_train_nyu.txt

You can check the training using tensorboard:

tensorboard --logdir ./models/bts_nyu_test/ --port 6006

Open localhost:6006 with your favorite browser to see the progress of training.