-
Notifications
You must be signed in to change notification settings - Fork 3.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
PyTorch was compiled without numpy support #13
Comments
请问你装numpy的时候确定装到了py2吗,有可能装到了py3 |
也有可能是conda的原因,我没用过conda, 不太确定如果是conda应该怎么用 |
问题解决了,主要问题是1、我之前通过源码安装的时候遇到错误:error: could not create '/home/xiaofeng/anaconda2/lib/python2.7/site-packages/torch': Permission denied |
我运行了这个源码,但是现象和视频的不太一样,我将 loss.data[0] 打印出来 然后我将学习效率 改成了0.1 训练次数改成了1000,出现了拟合回归的过程。刚开始学这个,只是知道这个程序的大概原理,还有一点就是参数初始化这点,比如直线y=wa+b ,这个w的初始化时pytorch会给一个默认值么,我们不需要进行指定么 |
torch 初始化 w,b 的时候会默认使用 uniform distribution (如果我没记错的话). 关于初始化参数设置, 你可以参考一下我这个code |
我运行这个源码。python2.7
出现错误:Traceback (most recent call last):
File "./LR_test.py", line 51, in
plt.scatter(x.data.numpy(), y.data.numpy())
RuntimeError: PyTorch was compiled without numpy support
但是我安装的时候运行了conda install numpy pyyaml mkl setuptools cmake cffi这句话,这是什么原因啊
The text was updated successfully, but these errors were encountered: