search

cuiziteng / Illumination-Adaptive-Transformer

[BMVC 2022] You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction. SOTA for low light enhancement, 0.004 seconds try this for pre-processing.
Apache License 2.0
441 stars 43 forks source link

您好，请问一下怎样将IAT和yolo联合训练呢？ #37

Closed blackpcl closed 1 year ago

cuiziteng commented 1 year ago

感谢关注，请参考论文Sec.8的部分，代码实现就是joint-training，把IAT做为一个pre-encoder前置就好，参考https://github.com/cuiziteng/Illumination-Adaptive-Transformer/blob/main/IAT_high/IAT_mmdetection/mmdet/models/detectors/IAT_detector/IAT_yolo.py

blackpcl commented 1 year ago

谢谢您的回答，明白了。

beyond96 commented 9 months ago

感谢关注，请参考论文Sec.8的部分，代码实现就是joint-training，把IAT做为一个pre-encoder前置就好，参考https://github.com/cuiziteng/Illumination-Adaptive-Transformer/blob/main/IAT_high/IAT_mmdetection/mmdet/models/detectors/IAT_detector/IAT_yolo.py

很棒的工作！有个问题请教您一下，如果把IAT做为一个pre-encoder前置，那我联合训练的时候同样也要读取训练IAT部分对应的LOL数据集吗？还是说我只需要读取exdark这个检测数据集就可以了，只通过检测的结果计算loss

感谢关注，请参考论文Sec.8的部分，代码实现就是joint-training，把IAT做为一个pre-encoder前置就好，参考https://github.com/cuiziteng/Illumination-Adaptive-Transformer/blob/main/IAT_high/IAT_mmdetection/mmdet/models/detectors/IAT_detector/IAT_yolo.py