在本地上运动我该怎么导入d2lzh_pytorch

[gggamemaster]

求解

[GSwithAI]

同问

[ShusenTang]

基本上每节都有例子呀，如下图

即用sys.path.append(PATH) 把你存放d2lzh_pytorch的路径加进来，然后就可以正常导入了

[GSwithAI]

基本上每节都有例子呀，如下图

即用sys.path.append(PATH) 把你存放d2lzh_pytorch的路径加进来，然后就可以正常导入了

d2lzh_pytorch这个包在哪里下载呢

[ShusenTang]

基本上每节都有例子呀，如下图

即用sys.path.append(PATH) 把你存放d2lzh_pytorch的路径加进来，然后就可以正常导入了

d2lzh_pytorch这个包在哪里下载呢

就在code文件夹里呀

[gggamemaster]

我把这个包下了，在conda虚拟环境安装不成功。

[ShusenTang]

我把这个包下了，在conda虚拟环境安装不成功。

不用安装（也安装不上），直接用就是，代码就在code文件夹里

[gggamemaster]

我把utils.py下载下来。导入我的jupyter notebook中,在运行3.7代码的时候出现了bug，我的pytorch是1.3

[ShusenTang]

我把utils.py下载下来。导入我的jupyter notebook中,在运行3.7代码的时候出现了bug，我的pytorch是1.3

报错信息贴出来看看

[gggamemaster]

RuntimeError Traceback (most recent call last)
in
1 num_epochs = 5
----> 2 d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)

~\utils.py in train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params, lr, optimizer)
140 train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
141 n += y.shape[0]
--> 142 test_acc = evaluate_accuracy(test_iter, net)
143 print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
144 % (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))

~\utils.py in evaluate_accuracy(data_iter, net, device)
212 if isinstance(net, torch.nn.Module):
213 net.eval() # 评估模式, 这会关闭dropout
--> 214 acc_sum += (net(X.to(device)).argmax(dim=1) == y.to(device)).float().sum().cpu().item()
215 net.train() # 改回训练模式
216 else: # 自定义的模型, 3.13节之后不会用到, 不考虑GPU

D:\anaconda\envs\PyTorch\lib\site-packages\torch\nn\modules\module.py in call(self, *input, **kwargs)
539 result = self._slow_forward(*input, **kwargs)
540 else:
--> 541 result = self.forward(*input, **kwargs)
542 for hook in self._forward_hooks.values():
543 hook_result = hook(self, input, result)

D:\anaconda\envs\PyTorch\lib\site-packages\torch\nn\modules\container.py in forward(self, input)
90 def forward(self, input):
91 for module in self._modules.values():
---> 92 input = module(input)
93 return input
94

D:\anaconda\envs\PyTorch\lib\site-packages\torch\nn\modules\module.py in call(self, *input, **kwargs)
539 result = self._slow_forward(*input, **kwargs)
540 else:
--> 541 result = self.forward(*input, **kwargs)
542 for hook in self._forward_hooks.values():
543 hook_result = hook(self, input, result)

D:\anaconda\envs\PyTorch\lib\site-packages\torch\nn\modules\linear.py in forward(self, input)
85
86 def forward(self, input):
---> 87 return F.linear(input, self.weight, self.bias)
88
89 def extra_repr(self):

D:\anaconda\envs\PyTorch\lib\site-packages\torch\nn\functional.py in linear(input, weight, bias)
1368 if input.dim() == 2 and bias is not None:
1369 # fused op is marginally faster
-> 1370 ret = torch.addmm(bias, input, weight.t())
1371 else:
1372 output = input.matmul(weight.t())

RuntimeError: Expected object of device type cuda but got device type cpu for argument #1 'self' in call to _th_addmm

[gggamemaster]

完整的代码
import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
sys.path.append("..")
import utils as d2l

print(torch.version)

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

num_inputs = 784
num_outputs = 10

class LinearNet(nn.Module):

def init(self, num_inputs, num_outputs):

super(LinearNet, self).init()

self.linear = nn.Linear(num_inputs, num_outputs)

def forward(self, x): # x shape: (batch, 1, 28, 28)

y = self.linear(x.view(x.shape[0], -1))

return y

net = LinearNet(num_inputs, num_outputs)

class FlattenLayer(nn.Module):
def init(self):
super(FlattenLayer, self).init()
def forward(self, x): # x shape: (batch, *, *, ...)
return x.view(x.shape[0], -1)

from collections import OrderedDict
net = nn.Sequential(
# FlattenLayer(),
# nn.Linear(num_inputs, num_outputs)
OrderedDict([
('flatten', FlattenLayer()),
('linear', nn.Linear(num_inputs, num_outputs))])
)

init.normal_(net.linear.weight, mean=0, std=0.01)
init.constant_(net.linear.bias, val=0)
loss = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(net.parameters(), lr=0.1)
num_epochs = 5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)

[ShusenTang]

RuntimeError Traceback (most recent call last)
in
1 num_epochs = 5
----> 2 d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)

~\utils.py in train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params, lr, optimizer)
140 train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
141 n += y.shape[0]
--> 142 test_acc = evaluate_accuracy(test_iter, net)
143 print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
144 % (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))

~\utils.py in evaluate_accuracy(data_iter, net, device)
212 if isinstance(net, torch.nn.Module):
213 net.eval() # 评估模式, 这会关闭dropout
--> 214 acc_sum += (net(X.to(device)).argmax(dim=1) == y.to(device)).float().sum().cpu().item()
215 net.train() # 改回训练模式
216 else: # 自定义的模型, 3.13节之后不会用到, 不考虑GPU

D:\anaconda\envs\PyTorch\lib\site-packages\torch\nn\modules\module.py in call(self, *input, **kwargs)
539 result = self._slow_forward(*input, **kwargs)
540 else:
--> 541 result = self.forward(*input, **kwargs)
542 for hook in self._forward_hooks.values():
543 hook_result = hook(self, input, result)

D:\anaconda\envs\PyTorch\lib\site-packages\torch\nn\modules\container.py in forward(self, input)
90 def forward(self, input):
91 for module in self._modules.values():
---> 92 input = module(input)
93 return input
94

D:\anaconda\envs\PyTorch\lib\site-packages\torch\nn\modules\module.py in call(self, *input, **kwargs)
539 result = self._slow_forward(*input, **kwargs)
540 else:
--> 541 result = self.forward(*input, **kwargs)
542 for hook in self._forward_hooks.values():
543 hook_result = hook(self, input, result)

D:\anaconda\envs\PyTorch\lib\site-packages\torch\nn\modules\linear.py in forward(self, input)
85
86 def forward(self, input):
---> 87 return F.linear(input, self.weight, self.bias)
88
89 def extra_repr(self):

D:\anaconda\envs\PyTorch\lib\site-packages\torch\nn\functional.py in linear(input, weight, bias)
1368 if input.dim() == 2 and bias is not None:
1369 # fused op is marginally faster
-> 1370 ret = torch.addmm(bias, input, weight.t())
1371 else:
1372 output = input.matmul(weight.t())

RuntimeError: Expected object of device type cuda but got device type cpu for argument #1 'self' in call to _th_addmm

报错信息说得很清楚啦就是device不匹配，应该是你的机器有GPU，你把utils.py里面关于evaluate_accuracy的前几行改成以下应该就可以了:

# ############################ 5.5 #########################
def evaluate_accuracy(data_iter, net, device=None):
    if device is None:
        device = list(net.parameters())[0].device # net的device
    acc_sum, n = 0.0, 0

[gggamemaster]

谢谢您，经过修改以后已经可以运行了

[gggamemaster]

代码在实现多层感知机的时候出bug了，bug是由于修改处的代码引起的。
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs,batch_size, params, lr)
AttributeError Traceback (most recent call last)
in
----> 1 d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs,batch_size, params, lr)

~\utils.py in train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params, lr, optimizer)
140 train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
141 n += y.shape[0]
--> 142 test_acc = evaluate_accuracy(test_iter, net)
143 print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
144 % (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))

~\utils.py in evaluate_accuracy(data_iter, net, device)
207 def evaluate_accuracy(data_iter, net, device=None):
208 if device is None:
--> 209 device = list(net.parameters())[0].device # net的device
210 acc_sum, n = 0.0, 0
211 with torch.no_grad():

AttributeError: 'function' object has no attribute 'parameters'

[ShusenTang]

代码在实现多层感知机的时候出bug了，bug是由于修改处的代码引起的。
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs,batch_size, params, lr)
AttributeError Traceback (most recent call last)
in
----> 1 d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs,batch_size, params, lr)

~\utils.py in train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params, lr, optimizer)
140 train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
141 n += y.shape[0]
--> 142 test_acc = evaluate_accuracy(test_iter, net)
143 print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
144 % (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))

~\utils.py in evaluate_accuracy(data_iter, net, device)
207 def evaluate_accuracy(data_iter, net, device=None):
208 if device is None:
--> 209 device = list(net.parameters())[0].device # net的device
210 acc_sum, n = 0.0, 0
211 with torch.no_grad():

AttributeError: 'function' object has no attribute 'parameters'

这里是因为传入net不是一个PyTorch模型而是我们自己写的一个函数，所以没有parameter这个是属性，所以我任务把utils里面的evaluate_accuracy的第一行

if device is None:

改成

if device is None and isinstance(net, torch.nn.Module):

应该就可以了。

[TengFeiHan0]

我导入路径了为什么还不行呢？
sys.path.append("/home/tengfeihan/Dive-into-DL-PyTorch/code/d2lzh_pytorch") 新手不太会 @ShusenTang

[gggamemaster]

把里面的py文件下载下来直接用就行

…

------------------ 原始邮件 ------------------ 发件人: "Tengfei han"<notifications@github.com>; 发送时间: 2019年10月16日(星期三) 下午4:02 收件人: "ShusenTang/Dive-into-DL-PyTorch"<Dive-into-DL-PyTorch@noreply.github.com>; 抄送: "553270311"<553270311@qq.com>; "Author"<author@noreply.github.com>; 主题: Re: [ShusenTang/Dive-into-DL-PyTorch] 在本地上运动我该怎么导入d2lzh_pytorch (#29) 我导入路径了为什么还不行呢？ sys.path.append("/home/tengfeihan/Dive-into-DL-PyTorch/code/d2lzh_pytorch") 新手不太会 @ShusenTang — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

[alljie-cool]

[ShusenTang]

@alljie-cool 首先sys.append.append("..")是为了把父目录加入工作区（因为d2l_pytorch在父目录），我不知道为什么在你这不行。我提供一个解决方案，因为d2l_pytorch所有代码都在d2l_pytorch/utils.y中，所以你可以把这个utils.py放入代码目录里，这样就可以在代码中import utils as d2l，遇到问题可以用python 导入py文件作关键词google

[DayBright-David]

请教：这个怎么解决啊