jmiller656 / EDSR-Tensorflow

Tensorflow implementation of Enhanced Deep Residual Networks for Single Image Super-Resolution
MIT License
330 stars 107 forks source link

test error #49

Open zengxi77 opened 5 years ago

zengxi77 commented 5 years ago

I‘v download the pre-trained model files, when I run test.py , I meet this error: ( by the way, I put "General-100" in a directory named "data")

Building EDSR... Done building! Restoring... INFO:tensorflow:Restoring parameters from saved_models\model Restored! No image argument given Traceback (most recent call last):

File "", line 1, in runfile('C:/Users/Administrator/Desktop/non-local/CODE/EDSR-Tensorflow-master/test.py', wdir='C:/Users/Administrator/Desktop/non-local/CODE/EDSR-Tensorflow-master')

File "E:\anaconda\envs\python27\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 704, in runfile execfile(filename, namespace)

File "E:\anaconda\envs\python27\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 108, in execfile exec(compile(f.read(), filename, 'exec'), namespace)

File "C:/Users/Administrator/Desktop/non-local/CODE/EDSR-Tensorflow-master/test.py", line 28, in inputs = x

NameError: name 'x' is not defined

xiaoyi-st commented 3 years ago

你这个要 这样弄 : python test.py --image input.bmp 不要弄地址,【把图片和test.py放在同一个目录下,然后直接运行】,前面不要加地址

我按照您的方法这种弄,发现还是不行,数据加载不进来

xiaoyi-st commented 3 years ago

pytoch代码我也试了,有一些问题我无法解决,您跑过吗?我的电子邮件是xting120@qq.com

------------------ 原始邮件 ------------------ 发件人: "jmiller656/EDSR-Tensorflow" <notifications@github.com>; 发送时间: 2020年11月27日(星期五) 中午11:27 收件人: "jmiller656/EDSR-Tensorflow"<EDSR-Tensorflow@noreply.github.com>; 抄送: "R"<1120922880@qq.com>;"Comment"<comment@noreply.github.com>; 主题: Re: [jmiller656/EDSR-Tensorflow] test error (#49)

你这个要 这样弄 : python test.py --image input.bmp 不要弄地址,【把图片和test.py放在同一个目录下,然后直接运行】,前面不要加地址

我按照您的方法这种弄,发现还是不行,数据加载不进来

个人建议:去跑EDSR-Pytorch代码,这个tensorflow代码复现结果还是不行!达不到原论文的结果。pytorch就可以

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.