ACSCP_cGAN icon indicating copy to clipboard operation
ACSCP_cGAN copied to clipboard

关于代码运行报错

Open kongjibai opened this issue 6 years ago • 6 comments

您好!很高兴您能够分享您的项目,不过我用您的代码直接运行python main.py --phase train会报错,提示: ValueError: Variable vgg_16/conv1/conv1_1/weights already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at: File "/home/user/anaconda2/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 216, in variable use_resource=use_resource) File "/home/user/anaconda2/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args return func(*args, **current_args) File "/home/user/anaconda2/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 261, in model_variable use_resource=use_resource) 即使将vgg_feature.py中的相关函数注释掉也还是一样的,请问您能帮忙解释下么?跪求!

kongjibai avatar Oct 10 '18 11:10 kongjibai

暂时没有遇见这个问题,可以检查下tensorflow版本,项目用的是python3.6和tensorflow1.0.0

Ling-Bao avatar Oct 12 '18 05:10 Ling-Bao

确实是tensorflow版本的问题,谢谢啦!

kongjibai avatar Oct 16 '18 09:10 kongjibai

确实是tensorflow版本的问题,谢谢啦!

你是哪个版本的?

zychen2016 avatar Nov 27 '18 02:11 zychen2016

确实是tensorflow版本的问题,谢谢啦!

你是哪个版本的?

1.0.0

kongjibai avatar Nov 30 '18 06:11 kongjibai

Hi, you may be interested in my implementation in pytorch. It includes the density map generation. https://github.com/RQuispeC/pytorch-ACSCP

RQuispeC avatar Apr 06 '19 21:04 RQuispeC

你好,那么您当时使用的是cuda8嘛?我看到对应的tensorflow-gpu1.0.0对应的只能是8.0;为何更高版本的tensorflow-gpu会出现这个错误呢?不应该是兼容嘛,感谢

EillotY avatar Sep 23 '19 08:09 EillotY