Algorithmic newcomer

> Rednering canonical_360 仅使用场景比例来确定区间补偿。看起来`mydata`场景和`bike`场景之间存在一些比例不匹配。 您需要使用 重新训练场景模型和人体模型`mydata`。 Ok, I have another question. When you saved the output file of densepose in the preprocessing stage, did you save this data？ 

Hello, have you solved it now? The MAP I trained with HALPE26 was low and overfitting. Is it possible that I trained with the HALPE dataset and COCO together?

> @Fang-Haoshu I trained alphapose in halpe 136 dataset, but the MAP is worse than the pretrained_model(halpe136_fast_res50_256x192.path),Are there any details to pay attention to？and could you shard the train log...