环境,win10,python3.6,
安装版本为pytorch1.0
笔记本配置为:,戴尔笔记本自带的,nvidia geforce gtx 960m 4 gb,显卡,亲测可以安装cuda10.0
安装命令:
cpu版本:
pip install https://download.pytorch.org/whl/cpu/torch-1.0.0-cp36-cp36m-win_amd64.whl
pip install https://download.pytorch.org/whl/cu100/torch-1.0.0-cp37-cp37m-win_amd64.whl #cuda10.0
什么是pytorch?
Pytorch是一个基于python的科学计算库,有以下特点:
- 类似与numpy,但是它可以使用GPU
- 可以用它定义深度学习模型,可以灵活的进行深度学习模型的训练和使用
用pytorch实现一个两层的神经网络:
N, D_in, H, D_out = 64, 1000, 100, 10
# 随机创建一些训练数据
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)
w1 = torch.randn(D_in, H, requires_grad=True)
w2 = torch.randn(H, D_out, requires_grad=True)
learning_rate = 1e-6
for it in range(500):
# Forward pass
y_pred = x.mm(w1).clamp(min=0).mm(w2)
# compute loss
loss = (y_pred - y).pow(2).sum() # computation graph
print(it, loss.item())
# Backward pass
loss.backward()
# update weights of w1 and w2
with torch.no_grad():
w1 -= learning_rate * w1.grad
w2 -= learning_rate * w2.grad
w1.grad.zero_()
w2.grad.zero_()