Xinyu Wang

Results 22 comments of Xinyu Wang

Hi, thank you for your contribution. We will review this code as soon as possible. At the same time, could you please sign the CLA shown on this page? So...

1. Hi, thank you for your cooperation. 2. The test failed due to a bug caused by mmcv version issue, we are going to fix this soon. 3. The last...

Hi, This might be a memory leak issue caused by pytorch dataloader. A possible solution for the issue is to replace the default multi-process start method with `mp_start_method = 'spawn'`....

Hi, sorry for the late reply. We trained the synth-text pre-trained model on a cluster that was equipped with very large RAM, so we did not notice the possible memory...

Hi @EvgenyM , thank you for your contribution; would you like to sign the CLA shown above, so we can accept the contribution?

Hi, MMOCR currently does not provide a data converter for KIE task. If you would like to train with your custom data, you may refer to the data preparation steps...

Hi, you may refer to this [tutorial](https://mmocr.readthedocs.io/en/latest/tutorials/kie_closeset_openset.html) to learn the `key` and `value` in KIE, which provides some examples of the `key-value` pairs.

Thank you for your contribution! We will review this PR soon. You may currently read some notes below to help us improve this PR. - We have fixed some known...

Hi @EugeneWong2002 , Thank you for your excellent translations! There are a few issues that need to be resolved before we can merge this PR into the repo: - Some...

Hi @GHuiXin, Thank you for your contribution! We'll review this PR soon!