jbwang1997

Thank you very much for your great contributions. As described in the original paper, 30k iterations have been applied for training DAL on DOTA dataset. random flip, rotation, and HSV...

There is also a difference in dealing with difficult cases. ReDet will ignore difficult cases in evaluation.

Hello. Seems you use fp16 to train bs8 s2anet. have you compared the results between fp32 and fp16 models?

Hello @YvesXu, Thanks for your contributions. Please remember to sign the CLA. The lint seems also failed. Please follow the [tutorial](https://github.com/open-mmlab/mmcv/blob/master/CONTRIBUTING.md) to fix the lint.

Hello @BubblyYi, thanks for your contributions. Could you provide the error report before this modification?

Hello @nzmyaaa, could you provide the error report.

Seems the error is because the CUDA_HOME is not set.

Sorry for don't get your questions. The pre-trained model will do the same actions as the fine-tuned model. Could you provide more information?

Every object with the same class will share the same color because we define PLATTE for each class in the dataset. So the behavior of the fine-turned mode is normal....

Thanks for your reporting. We will fix it as soon as possible.