weizhiliang0520

Results 17 comments of weizhiliang0520

> Hello, I use your code to train the model using DIV2K, but can not get the training result, the output of the network is black image, my training loss...

> 亲爱的作者,非常 感谢您分享非常有用的代码。 > > 在使用提供的预训练模型的测试数据集运行PAM/BAM时文件的过程中,我发现以下错误: > > 运行时错误:RuntimeError: CUDA out of memory. Tried to allocate 2.00 GiB (GPU 0; 6.00 GiB total capacity; 2.98 GiB already allocated; 1.78 GiB...

> 我的结果和你的一样,请问你解决了嘛,怎么解决,谢谢 > 我之前遇到的是在colab上调试的,后面没有用google colab,直接用服务器跑代码就可以了。听说是因为python版本的问题,有说换成python3.8就好了,我在服务器上跑的是python3.6.12,你试试。

> 我的结果和你的一样,请问你解决了嘛,怎么解决,谢谢! 你看看这个博客: https://blog.csdn.net/qq_41647438/article/details/108344141

> Hello, am trying to start with change detection methods but am having this issue while executing the different commands mentioned in the readme file, am working on Colab. all...

> @weizhiliang0520 Where is the link to download the weight?thank you. you can find it (wight) on the README.md as follows: https://pan.baidu.com/share/init?surl=O1kg7JWunqd87ajtVMM6pg code: 2rja ----------------------------- but your issue title is...

> 我估计是,在计算相似性矩阵的时候,输入的特征图尺寸过大,占用了比较多的显存,从而导致显存不足, 可以通过设置添加 ds参数,来讲特征图进行一次下采样,代码里默认ds=1, 可以试试添加 ' --ds 4 或者 --ds 8 ' 你好,我想问一下,跑代码的时候,baseline可以跑,等跑BAM时候,就出现问题,和你的一样。当我设置batch size 和ds很小的时候,但是我能够跑第一轮,后面不是每train完一轮以后,代码自动val 验证嘛,我的就卡了,out of memory 256G。

你好,我没有在下载代码之后,将图像文件放到该放的地方。 python train.py 就报错,但是从报错的情况来看,是跑完第一个epoch之后,在val 时候出错的。错误如下: `[Network F] Total number of parameters : 16.892 M ----------------------------------------------- Could not connect to Visdom server. Trying to start a server.... Command: /usr/bin/python3 -m visdom.server...

> Metoo, and this is the results of my reproduction: BASE precision 63.5 recall 95.5 f1_score 76.3 BAM precision 65.9 recall 94.6 f1_score 77.7 PAM precision 77.0 recall 89.2 f1_score...

> Metoo, and this is the results of my reproduction: BASE precision 63.5 recall 95.5 f1_score 76.3 BAM precision 65.9 recall 94.6 f1_score 77.7 PAM precision 77.0 recall 89.2 f1_score...