我的名字呀
我的名字呀
 这是在运行还是出了什么问题?(是不是数据集太大了...) 当然,前面的比如eval.py等执行的不是很好,有些路径找不到我直接用 . 改到了eval.py的当前目录,不知道会有什么影响。
The size of the image which I used is 640*640. It can be diviable by 128. Thanks for your help! Sample #0/10 Traceback (most recent call last): File ".\generate_blur.py", line...
When I run generic_deblur.py, I got CUDA memory Error. Is there some way to use less memory to debulr? Thank you.
I think it's a amazing tool for CNN, I cann't wait to use it in CNN. Hope for torch.nn.functional very much, thanks for your great job!!!
您好,我使用 1.预训练权重voc_weights_resnet.pth同时设置freeze_train=False; 2.不使用预训练权重同时设置freeze_train=True 冻结训练50epoch,解冻训练共250epoch 两种方式精度都很低,但2比1精度略高,也裁11%左右。 求求楼主解救,谢谢!