Achhhe

the same problem to me

还有一个问题，您计算psnr和ssim是用的matlab中现有函数psnr()和ssim()吗

> 首先命令行运行pip install torchfile安装torchfile, > > from torch.utils.serialization import load_lua --》import torchfile, 您好，我按照您说的，pip install torchfile，然后将from torch.utils.serialization import load_lua替换为import torchfile，然后将代码中load_lua改为torchfile.load，最后还是遇到了错误，TypeError：‘NoneType’ object is not callable，请问您是没有遇到么，怎么解决的啊

抱歉啊，我是新手，请问前置计算框架是什么意思，我就是参考您的demo，用mxnet训练好的模型，然后参考test.py测试的实时视频640×480,没有用gpu，大约37ms，请问你有用cpu测试过么

抱歉，又打搅您了 您有尝试过论文中BN合并到conv层么，经过合并以后模型大小可以从4m降为0.99m么

> Yes, not shared, but it would be easy to modify to the shared version This is my modified version, I'm not sure if it's correct class MemoryBlock(nn.Module): """Note: num_memblock...

> It's really kind of you ! The code you shared is really helpful! > I find there are some codes need to change in sub_mean function for Y channel,...