Python 在PyTorch中运行backward()函数时出错
守则:Python 在PyTorch中运行backward()函数时出错,python,numpy,machine-learning,pytorch,autograd,Python,Numpy,Machine Learning,Pytorch,Autograd,守则: import numpy as np predictors = np.array([[73,67,43],[91,88,64],[87,134,58],[102,43,37],[69,96,70]],dtype='float32') outputs = np.array([[56,70],[81,101],[119,133],[22,37],[103,119]],dtype='float32') inputs = torch.from_numpy(predictors)
import numpy as np
predictors = np.array([[73,67,43],[91,88,64],[87,134,58],[102,43,37],[69,96,70]],dtype='float32')
outputs = np.array([[56,70],[81,101],[119,133],[22,37],[103,119]],dtype='float32')
inputs = torch.from_numpy(predictors)
targets = torch.from_numpy(outputs)
weights = torch.randn(2,3,requires_grad=True)
biases = torch.randn(2,requires_grad=True)
def loss_mse(x,y):
d = x-y
return torch.sum(d*d)/d.numel()
def model(w,b,x):
return x @ w.t() +b
def train(x,y,w,b,lr,e):
w = torch.tensor(w,requires_grad=True)
b = torch.tensor(b,requires_grad=True)
for epoch in range(e):
preds = model(w,b,x)
loss = loss_mse(y,preds)
if epoch%5 == 0:
print("Loss at Epoch [{}/{}] is {}".format(epoch,e,loss))
#loss.requires_grad=True
loss.backward()
with torch.no_grad():
w = w - lr*w.grad
b = b - lr*b.grad
w.grad.zero_()
b.grad.zero_()
train(inputs,targets,weights,biases,1e-5,100)
运行此命令会产生不同的错误。一旦它给出了
loss
大小为0的错误。然后它在更新行w=w-lr*w.grad
中给出了一个错误,即float不能从NoneType中减去。首先,为什么要将权重和偏差包装为张量两次
weights = torch.randn(2,3,requires_grad=True)
biases = torch.randn(2,requires_grad=True)de here
然后在您使用的列车功能内:
w = torch.tensor(w,requires_grad=True)
b = torch.tensor(b,requires_grad=True)
其次,在更新权重的过程中,将其更改为:
with torch.no_grad():
w_new = w - lr*w.grad
b_new = b - lr*b.grad
w.copy_(w_new)
b.copy_(b_new)
w.grad.zero_()
b.grad.zero_()
您可以查看此讨论以获得更全面的解释:
谢谢!事实上,在调试时,我再次包装了权重和偏差,只是为了检查它们是否是问题所在,但在发布之前忘记了删除它们。不管怎样,它成功了。非常感谢你。