8000 error:sh scripts/DGFNet_test.sh · Issue #4 · XinGP/DGFNet · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

error:sh scripts/DGFNet_test.sh #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

< 8000 p class="mt-4 color-fg-muted text-center"> Already on GitHub? Sign in to your account

Open
WMXJY opened this issue Feb 7, 2025 · 4 comments
Open

error:sh scripts/DGFNet_test.sh #4

WMXJY opened this issue Feb 7, 2025 · 4 comments

Comments

@WMXJY
Copy link
WMXJY commented Feb 7, 2025

When I run this code:
sh scripts/DGFNet_test.sh
I encounter the following error:
FileNotFoundError: [Errno 2] No such file or directory: 'data_argo/features/test/'
Could you please tell me how to create the test dataset? Do I need to write another .sh file?

@XinGP
Copy link
Owner
XinGP commented Feb 8, 2025

You first need to preprocess the raw argoverse data, and then if you want to test it, you need to train a model first.
If you don't want to retrain the model, you can leave your email and I can send you the unorganized code and the trained model.

use
sh scripts/argo_preproc.sh
and
sh scripts/DGFNet_train.sh

@WMXJY
Copy link
Author
WMXJY commented Feb 8, 2025

Firstly, there is no detailed code for processing the test data in the argo_preproc.sh script.
`echo "-- Processing val set..."
python data_argo/run_preprocess.py --mode val
--data_dir ~/data/argodata/val/data/
--save_dir data_argo/features/

echo "-- Processing train set..."
python data_argo/run_preprocess.py --mode train
--data_dir ~/data/argodata/train/data/
--save_dir data_argo/features/`

So, I would like to know how to process the test dataset?
like?
echo "-- Processing test set..." python data_argo/run_preprocess.py --mode test\ --data_dir ~/data/argodata/test/data/ \ --save_dir data_argo/features/

@XinGP
Copy link
Owner
XinGP commented Feb 9, 2025

Yes, there's no problem with your understanding. I did miss the script code here

@Family-Liao
Copy link
Family-Liao commented Mar 17, 2025

You first need to preprocess the raw argoverse data, and then if you want to test it, you need to train a model first. If you don't want to retrain the model, you can leave your email and I can send you the unorganized code and the trained model.

use sh scripts/argo_preproc.sh and sh scripts/DGFNet_train.sh

@XinGP 作者你好,能不能发一份预处理测试集的代码以及生成h5文件的代码,我的邮箱是1311562375@qq.com,非常感谢

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants
0