GexLoong
GexLoong
在dataloader_sevir.py中,SEVIRDataset类有self.mean = 33.44,self.std = 47.54用于实现标准化,这两个取值是怎么得来的?标准化(X - self.mean) / self.std有什么作用,和归一化X/255不同吗? 
你好,我运行`sh tools/dist_train.sh projects/configs/co_dino_vit/co_dino_5scale_vit_large_coco.py 1`时,会如下错误,我看之前也有人报这个错,请问这个问题如何解决?谢谢 
my machine got the error about " out of memory"  i have change the "total_batch_size" to 2, ues "amp-fp16" , and use dataset "'2018-01-01' to '2018-01-10'" ten days data...