deepinsight / deepinsight/insightface
How to train Casia-webface
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
I want to use arcface torch to train the CASIA webface dataset. But I encountered difficulties.
I download the dataset from [here](https://github.com/deepinsight/insightface/tree/master/recognition/_datasets_).Some blogs told me to set "num_classes" to 10572, but I found that the number of categories in the paper is 10575.The blog was published in 2020. "[insightface](https://github.com/deepinsight/insightface)" is different from that time.I can't find the documentation that tells me how to set up the config file.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with the linked CASIA-WebFace dataset and the arcface torch training setup; compare the downloaded identities with the 10572 and 10575 counts mentioned in the issue. Done means the current configuration values and a reproducible setup path are documented clearly enough for a newcomer to train the dataset.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100