[英]RuntimeError: Found dtype Double but expected Float
I'm writing a code for reinforcement learning using Python 3 and Pytorch 1.9.1.我正在使用 Python 3 和 Pytorch 1.9.1 编写用于强化学习的代码。
I post a question because I don't understand the error line.我发布了一个问题,因为我不明白错误行。 The error occurs on the line of the loss.mean().backward().
错误发生在 loss.mean().backward() 的行上。
It is said that the dtype should have a float, but the double came in, but no matter how much the dtype is printed, it comes out as a float 32. What's the problem?据说dtype应该有float,但是double进来了,但是不管dtype打印多少,出来的都是float 32。有什么问题吗?
The code in question is as follows.有问题的代码如下。
def train_net_ap(self, idx):
s, a, r, s_prime, done_mask, prob_a = self.make_batch(idx)
print("a is ", a)
for i in range(K_epoch):
td_target = r + gamma * self.v_ap(s_prime) * done_mask
delta = td_target - self.v_ap(s)
delta = delta.detach().numpy()
advantage_lst = []
advantage = 0.0
for delta_t in delta[::-1]:
advantage = gamma * lmbda * advantage + delta_t[0]
advantage_lst.append([advantage])
advantage_lst.reverse()
advantage = torch.tensor(advantage_lst, dtype=torch.float)
pi = self.pi_ap(s, softmax_dim=1)
pi_a = pi.gather(1, a)
ratio = torch.exp(torch.log(pi_a) - torch.log(prob_a)) # a/b == exp(log(a)-log(b))
surr1 = ratio * advantage
surr2 = torch.clamp(ratio, 1 - eps_clip, 1 + eps_clip) * advantage
loss = -torch.min(surr1, surr2) + F.smooth_l1_loss(self.v_ap(s), td_target.detach())
print("loss is ", loss)
print("loss dtype is ", loss.dtype)
print("loss.mean() is ", loss.mean(), loss.mean().dtype)
self.optimizer.zero_grad()
loss.mean().backward()
self.optimizer.step()
The printed phrase and error message are as follows.打印的短语和错误信息如下。
loss dtype is torch.float32
loss.mean() is tensor(6.1353, grad_fn=<MeanBackward0>) torch.float32
Traceback (most recent call last):
main()
model.train_net_ap(x)
loss.mean().backward()
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
allow_unreachable=True, accumulate_grad=True) # allow_unreachable flag
RuntimeError: Found dtype Double but expected Float
The error says that it expected a Float data type, but it is receiving a Double type data, what you can do is change the variable type to the one required in this case do something similar to:该错误表示它期望 Float 数据类型,但它接收的是 Double 类型数据,您可以做的是将变量类型更改为在这种情况下所需的类型,执行类似于:
float(double_variable)
Or if you require a more precise float value or with a specific number of decimal places you could use this:或者,如果您需要更精确的浮点值或具有特定小数位数,您可以使用:
(This is an example)
v1 = 0.00582811585976
import numpy as np
np.float32(v1)
float(np.float32(v1)) #Convert to 32bit and then back to 64bit
'%.14f'%np.float32(v1) #This rounds to v2 if you're printing 14 places of precision ...
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.