search

VinAIResearch / LeMul

Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images (ICCV 2021)
Apache License 2.0
49 stars 4 forks source link

Questions about evaluation metrics #1

Open Yual16078 opened 2 years ago

Yual16078 commented 2 years ago

Thank you for your generous open source.

Now that I have been through the training process, and obtain a model trained for 70 epochs.

So what I wonder is how to output or where I can find these evaluation metrics to measure the performance of my trained model, and if any ground truth data needed for this evaluation process.

Looking forward to your reply and help, much thanks.

longnhatne commented 2 years ago

Thanks for your appreciation. I've just found that it was my mistake and already updated the testing script.

Testing command: python run.py --config experiments/test_multi_CASIA.yml --gpu 0 --num_workers 4

The output images of your trained model will be exported in test_result_dir which is in your testing config file. For MAD & SIDE, you need ground truth which is already provided in BFM dataset (you can download it by download_synface.sh).