UVM-Net

UVM-Net copied to clipboard

TypeError: `model` must be a `LightningModule`, got `UNet`

4

run python train.py Total number of training data: 6000 GPU available: True (cuda), used: True TPU available: False, using: 0 TPU cores IPU available: False, using: 0 IPUs HPU available:...

formerlya

How do you calculate your params?

2

Hi, thank you for you open-source code. May I know how do you get the result of 19M params in your paper? I get the result of 100M here without...

zinuoli

关于测试尺寸

5

作者您好，看代码中测试也是针对每一个patch做的吗？在测试的时候为啥不对整张大图进行推理计算大图的psnr呢？

lijun2005

CUDA out of memory

13

torch1.13.1+cuda11.7 RTX-Titan 24G 使用默认配置，提示显存不够，batch_size设置为1还是不行。

bzmtxh

The current README.md file does not provide sufficient information regarding the dataset directory structure and the specific commands required to run the UVMNet code based on the provided configuration. Dataset...

PranavS30

找不到 SAFMN

2

作者你好，很感谢你的分享，我碰到一个问题就是在测试代码中from model import SAFMN，找不到这个 SAFMN，不知道怎么解决这个问题，有点困惑，谢谢

Aaronwangz

CUDA error: no kernel image is available for execution on the device

1

请问一下这个怎们解决

zhuzenghui0721

There is no need to reduce the number of layers in the UNet, my basic module has three SSMs, you can remove the one that is the most computationally intensive...

zzr-idam

is this model can be used to do image deburing ?

4

sunzhe09

Issue with reshaping

1

Hello, thanks for the nice work, In the following code, should not the x be permuted first before reshaping, x = self.ln(x.reshape(b, -1, c)) ``` def forward(self, x): b,c,w,h =...

kabbas570