Zheng Miao

> Linux python3.6 pytorch could you tell me how do you run the code successfully in python3 linux

Yes， I'm sorry that it is to late to reply to you because I was busy in last two month. I share the code with you At 2020-04-30 09:34:07, "zhangxuyang"...

we can set train parameter as False in train.py for data augomentation

> 我猜你验证集的代码不对，记得最后一个cell中有一行注释，取消掉就好了 你说的挺对的，我开始也是验证集精度很差，验证集part_B 的MAE是1900多，取消掉最后一个cell中的注释img = transform(Image.open(img_paths[i]).convert('RGB')).cuda()后，我的验证集精度为8.998，感谢

你好，您的crop好像没有使用呀？因为train.py文件中train=True，而在imge.py中进行crop需要是train在False的情况下

This notation doesn't seem quite right----ignored regions(0), pedestrian(1), people(2), bicycle(3), car(4), van(5), truck(6), tricycle(7), awning-tricycle(8), bus(9), motor(10), others(11) After I finished my training, I recognized the car as a bicycle