Pytorch error: RuntimeError: 1D target tensor expected, multi-target not supported
Pytorch error: RuntimeError: 1D target tensor expected, multi-target not supported
我目前正在研究一个神经元网络，它可以对猫和狗以及除猫狗以外的所有事物进行分类。我的程序有这个：我无法解决的错误：
”文件“/home/johann/Schreibtisch/NN_v0.01/classification.py”，第 146 行，在
火车（纪元）
文件“/home/johann/Schreibtisch/NN_v0.01/classification.py”，第 109 行，在 train 中
损失=标准（出局，目标）
文件“/home/johann/.local/lib/python3.8/site-packages/torch/nn/modules/module.py”，第 889 行，在 _call_impl
结果 = self.forward(*输入, **kwargs)
文件“/home/johann/.local/lib/python3.8/site-packages/torch/nn/modules/loss.py”，第 1047 行，向前
return F.cross_entropy(输入、目标、权重=self.weight,
文件“/home/johann/.local/lib/python3.8/site-packages/torch/nn/functional.py”，第 2693 行，在 cross_entropy
return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
文件“/home/johann/.local/lib/python3.8/site-packages/torch/nn/functional.py”，第 2388 行，在 nll_loss 中
ret = torch._C._nn.nll_loss(输入，目标，权重，_Reduction.get_enum(减少)，ignore_index)
RuntimeError：预期为 1D 目标张量，不支持多目标
代码：
import os
from torchvision import transforms
from PIL import Image
from os import listdir
import random
import torch.optim as optim
from torch.autograd import Variable
import torch.nn.functional as F
import torch.nn as nn
import matplotlib.pyplot as plt
from tqdm import tqdm
normalize = transforms.Normalize(
mean = [0.485, 0.456, 0.406],
std = [0.229, 0.224, 0.225])
transform = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(256),
transforms.ToTensor(), normalize])
train_data_list = []
target_list = []
train_data = []
waited = False
files = listdir('catsanddogs/train/')
for i in range(len(listdir('catsanddogs/train/'))):
if len(train_data) == 58 and not waited:
waited = True
continue
f = random.choice(files)
files.remove(f)
img = Image.open("catsanddogs/train/" + f)
img_tensor = transform(img)
train_data_list.append(img_tensor)
isSomething = 0
isCat = 1 if 'cat' in f else 0
isDog = 1 if 'dog' in f else 0
if isDog == 0 and isCat == 0:
isSomething = 1
target = [isCat, isDog, isSomething] #, isSomthing
target_list.append(target)
if len(train_data_list) >= 256:
train_data.append((torch.stack(train_data_list), target_list))
train_data_list = []
target_list = []
print('Loaded batch ', len(train_data), 'of ', int(len(listdir('catsanddogs/train/')) / 64))
print('Percentage Done: ', 100 * len(train_data) / int(len(listdir('catsanddogs/train/')) / 64), '%')
if len(train_data) > 2:
break
class Netz(nn.Module):
def __init__(self):
super(Netz, self).__init__()
self.conv1 = nn.Conv2d(3, 6, kernel_size=(5, 5))
self.conv2 = nn.Conv2d(6, 12, kernel_size=(5, 5))
self.conv3 = nn.Conv2d(12, 18, kernel_size=(5, 5))
self.conv4 = nn.Conv2d(18, 24, kernel_size=(5, 5))
self.fc1 = nn.Linear(3456, 1000)
self.fc2 = nn.Linear(1000, 3)
def forward(self, x):
x = self.conv1(x)
x = F.max_pool2d(x, 2)
x = F.relu(x)
x = self.conv2(x)
x = F.max_pool2d(x, 2)
x = F.relu(x)
x = self.conv3(x)
x = F.max_pool2d(x, 2)
x = F.relu(x)
x = self.conv4(x)
x = F.max_pool2d(x, 2)
x = F.relu(x)
x = x.view(-1, 3456)
x = F.relu(self.fc1(x))
x = self.fc2(x)
return F.softmax(x, dim=1)
model = Netz()
#if os.path.isfile('catdognetz.pt'):
#model = torch.load('catdognetz.pt')
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)
def count_parameters(model):
return sum(p.numel() for p in model.parameters() if p.requires_grad)
count_parameters(model)
train_losses = []
train_accu = []
def train(epoch):
print('\nEpoch : %d' % epoch)
model.train()
running_loss = 0
correct = 0
total = 0
for data, target in tqdm(train_data):
target = torch.Tensor(target)
data = Variable(data)
target = Variable(target)
optimizer.zero_grad()
out = model(data)
criterion = nn.CrossEntropyLoss()
loss = criterion(out, target)
loss.backward()
optimizer.step()
running_loss += loss.item()
predicted = out.max(1)
total += target.size(0)
correct += predicted.eq(target).sum().item()
train_loss = running_loss / len(train_data)
accu = 100. * float(correct) / total
train_accu.append(accu)
train_losses.append(train_loss)
print('Train Loss: %.3f | Accuracy: %.3f' % (train_loss, accu))
def test():
model.eval()
file = listdir('catsanddogs/test/')
f = random.choice(file)
img = Image.open('catsanddogs/test/' + f)
img_eval_tensor = transform(img)
img_eval_tensor.unsqueeze_(0)
data = Variable(img_eval_tensor)
out = model(data)
what = "It's a cat"
print(out.data.max(1, keepdim=True)[1].cpu().numpy()[0])
if out.data.max(1, keepdim=True)[1].cpu().numpy()[0] != 0:
what = "It's a Dog"
if out.data.max(1, keepdim=True)[1].cpu().numpy()[0] != 0 and out.data.max(1, keepdim=True)[1].cpu().numpy()[0] != 1:
what = "Neither"
print(what)
img.show()
#x = input('')
epochs = 10
for epoch in range(1, epochs + 1):
train(epoch)
#test()
torch.save(model, 'catdognetz.pt')
plt.plot(train_accu,'-o')
plt.xlabel('epoch')
plt.ylabel('accuracy')
plt.legend(['Kurve: Training'])
plt.title('Train Accuracy')
plt.show()
plt.plot(train_losses,'-o')
plt.xlabel('epoch')
plt.ylabel('loss bzw. Verlust')
plt.legend(['Kruve : Training'])
plt.title('Train Loss')
plt.show()```
此错误背后的原因是您的目标列表是这样的列表列表：
target = [[1,0,0],[0,1,0],[0,0,1],...]
您应该使用一维张量而不是 one-hot 代码列表，因为 CrossEntropyLoss 不接受 one-hot 编码张量。例如，您可以使用：
target = torch.tensor([0, 1, 2, 2, 1, 0, 0, ...]) # cat = 1, dog=2, something else= 2
您可以通过以下方式自动将目标从 one-hot 编码列表转换为 类 张量：
target = torch.tensor(target)
target= torch.argmax(target ,axis=1)
或者您可以更改算法以创建一维张量而不是列表列表。
你可以阅读更多CrossEntropyLoss的文档here
我目前正在研究一个神经元网络，它可以对猫和狗以及除猫狗以外的所有事物进行分类。我的程序有这个：我无法解决的错误：
”文件“/home/johann/Schreibtisch/NN_v0.01/classification.py”，第 146 行，在 火车（纪元） 文件“/home/johann/Schreibtisch/NN_v0.01/classification.py”，第 109 行，在 train 中 损失=标准（出局，目标） 文件“/home/johann/.local/lib/python3.8/site-packages/torch/nn/modules/module.py”，第 889 行，在 _call_impl 结果 = self.forward(*输入, **kwargs) 文件“/home/johann/.local/lib/python3.8/site-packages/torch/nn/modules/loss.py”，第 1047 行，向前 return F.cross_entropy(输入、目标、权重=self.weight, 文件“/home/johann/.local/lib/python3.8/site-packages/torch/nn/functional.py”，第 2693 行，在 cross_entropy return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction) 文件“/home/johann/.local/lib/python3.8/site-packages/torch/nn/functional.py”，第 2388 行，在 nll_loss 中 ret = torch._C._nn.nll_loss(输入，目标，权重，_Reduction.get_enum(减少)，ignore_index) RuntimeError：预期为 1D 目标张量，不支持多目标
代码：
import os
from torchvision import transforms
from PIL import Image
from os import listdir
import random
import torch.optim as optim
from torch.autograd import Variable
import torch.nn.functional as F
import torch.nn as nn
import matplotlib.pyplot as plt
from tqdm import tqdm
normalize = transforms.Normalize(
mean = [0.485, 0.456, 0.406],
std = [0.229, 0.224, 0.225])
transform = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(256),
transforms.ToTensor(), normalize])
train_data_list = []
target_list = []
train_data = []
waited = False
files = listdir('catsanddogs/train/')
for i in range(len(listdir('catsanddogs/train/'))):
if len(train_data) == 58 and not waited:
waited = True
continue
f = random.choice(files)
files.remove(f)
img = Image.open("catsanddogs/train/" + f)
img_tensor = transform(img)
train_data_list.append(img_tensor)
isSomething = 0
isCat = 1 if 'cat' in f else 0
isDog = 1 if 'dog' in f else 0
if isDog == 0 and isCat == 0:
isSomething = 1
target = [isCat, isDog, isSomething] #, isSomthing
target_list.append(target)
if len(train_data_list) >= 256:
train_data.append((torch.stack(train_data_list), target_list))
train_data_list = []
target_list = []
print('Loaded batch ', len(train_data), 'of ', int(len(listdir('catsanddogs/train/')) / 64))
print('Percentage Done: ', 100 * len(train_data) / int(len(listdir('catsanddogs/train/')) / 64), '%')
if len(train_data) > 2:
break
class Netz(nn.Module):
def __init__(self):
super(Netz, self).__init__()
self.conv1 = nn.Conv2d(3, 6, kernel_size=(5, 5))
self.conv2 = nn.Conv2d(6, 12, kernel_size=(5, 5))
self.conv3 = nn.Conv2d(12, 18, kernel_size=(5, 5))
self.conv4 = nn.Conv2d(18, 24, kernel_size=(5, 5))
self.fc1 = nn.Linear(3456, 1000)
self.fc2 = nn.Linear(1000, 3)
def forward(self, x):
x = self.conv1(x)
x = F.max_pool2d(x, 2)
x = F.relu(x)
x = self.conv2(x)
x = F.max_pool2d(x, 2)
x = F.relu(x)
x = self.conv3(x)
x = F.max_pool2d(x, 2)
x = F.relu(x)
x = self.conv4(x)
x = F.max_pool2d(x, 2)
x = F.relu(x)
x = x.view(-1, 3456)
x = F.relu(self.fc1(x))
x = self.fc2(x)
return F.softmax(x, dim=1)
model = Netz()
#if os.path.isfile('catdognetz.pt'):
#model = torch.load('catdognetz.pt')
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)
def count_parameters(model):
return sum(p.numel() for p in model.parameters() if p.requires_grad)
count_parameters(model)
train_losses = []
train_accu = []
def train(epoch):
print('\nEpoch : %d' % epoch)
model.train()
running_loss = 0
correct = 0
total = 0
for data, target in tqdm(train_data):
target = torch.Tensor(target)
data = Variable(data)
target = Variable(target)
optimizer.zero_grad()
out = model(data)
criterion = nn.CrossEntropyLoss()
loss = criterion(out, target)
loss.backward()
optimizer.step()
running_loss += loss.item()
predicted = out.max(1)
total += target.size(0)
correct += predicted.eq(target).sum().item()
train_loss = running_loss / len(train_data)
accu = 100. * float(correct) / total
train_accu.append(accu)
train_losses.append(train_loss)
print('Train Loss: %.3f | Accuracy: %.3f' % (train_loss, accu))
def test():
model.eval()
file = listdir('catsanddogs/test/')
f = random.choice(file)
img = Image.open('catsanddogs/test/' + f)
img_eval_tensor = transform(img)
img_eval_tensor.unsqueeze_(0)
data = Variable(img_eval_tensor)
out = model(data)
what = "It's a cat"
print(out.data.max(1, keepdim=True)[1].cpu().numpy()[0])
if out.data.max(1, keepdim=True)[1].cpu().numpy()[0] != 0:
what = "It's a Dog"
if out.data.max(1, keepdim=True)[1].cpu().numpy()[0] != 0 and out.data.max(1, keepdim=True)[1].cpu().numpy()[0] != 1:
what = "Neither"
print(what)
img.show()
#x = input('')
epochs = 10
for epoch in range(1, epochs + 1):
train(epoch)
#test()
torch.save(model, 'catdognetz.pt')
plt.plot(train_accu,'-o')
plt.xlabel('epoch')
plt.ylabel('accuracy')
plt.legend(['Kurve: Training'])
plt.title('Train Accuracy')
plt.show()
plt.plot(train_losses,'-o')
plt.xlabel('epoch')
plt.ylabel('loss bzw. Verlust')
plt.legend(['Kruve : Training'])
plt.title('Train Loss')
plt.show()```
此错误背后的原因是您的目标列表是这样的列表列表：
target = [[1,0,0],[0,1,0],[0,0,1],...]
您应该使用一维张量而不是 one-hot 代码列表，因为 CrossEntropyLoss 不接受 one-hot 编码张量。例如，您可以使用：
target = torch.tensor([0, 1, 2, 2, 1, 0, 0, ...]) # cat = 1, dog=2, something else= 2
您可以通过以下方式自动将目标从 one-hot 编码列表转换为 类 张量：
target = torch.tensor(target)
target= torch.argmax(target ,axis=1)
或者您可以更改算法以创建一维张量而不是列表列表。
你可以阅读更多CrossEntropyLoss的文档here