深度学习Pytorch-常见问题(二)_runtimeerror: sizes of tensors must match except i

1.

代码示例：

# ========================== 1 num_samples=0
flag = 0
# flag = 1
if flag:
    # train_dir = os.path.join("..", "data", "rmb_split", "train")
    train_dir = os.path.join("..", "..", "data", "rmb_split", "train")
    train_data = RMBDataset(data_dir=train_dir)

    # 构建DataLoder
    train_loader = DataLoader(dataset=train_data, batch_size=16, shuffle=True)
1
2
3
4
5
6
7
8
9
10

2.

代码示例：

# ========================== 2
# TypeError: pic should be PIL Image or ndarray. Got <class 'torch.Tensor'>
flag = 0
# flag = 1
if flag:
    train_transform = transforms.Compose([
        transforms.Resize((224, 224)),

        transforms.FiveCrop(200),
        transforms.Lambda(lambda crops: torch.stack([(transforms.ToTensor()(crop)) for crop in crops])),

        # transforms.ToTensor(),
        # transforms.ToTensor(),
    ])

    train_dir = os.path.join("..", "..", "data", "rmb_split", "train")
    train_data = RMBDataset(data_dir=train_dir, transform=train_transform)
    train_loader = DataLoader(dataset=train_data, batch_size=16, shuffle=True)

    data, label = next(iter(train_loader))
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20

3.

代码示例：

# ========================== 3
# RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0
flag = 0
# flag = 1
if flag:

    class FooDataset(Dataset):
        def __init__(self,  num_data, data_dir=None, transform=None):
            self.foo = data_dir
            self.transform = transform
            self.num_data = num_data

        def __getitem__(self, item):

            size = torch.randint(63, 64, size=(1, )) #[63,64)]
            fake_data = torch.zeros((3, size, size))
            fake_label = torch.randint(0, 10, size=(1, ))

            return fake_data, fake_label

        def __len__(self):
            return self.num_data


    foo_dataset = FooDataset(num_data=10)
    foo_dataloader = DataLoader(dataset=foo_dataset, batch_size=4)

    data, label = next(iter(foo_dataloader))
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28

4.

代码示例：

# ========================== 4
# Given groups=1, weight of size 6 3 5 5, expected input[16, 1, 32, 32] to have 3 channels, but got 1 channels instead
# RuntimeError: size mismatch, m1: [16 x 576], m2: [400 x 120] at ../aten/src/TH/generic/THTensorMath.cpp:752
flag = 0
# flag = 1
if flag:

    class FooDataset(Dataset):
        def __init__(self,  num_data, shape, data_dir=None, transform=None):
            self.foo = data_dir
            self.transform = transform
            self.num_data = num_data
            self.shape = shape

        def __getitem__(self, item):

            fake_data = torch.zeros(self.shape)
            fake_label = torch.randint(0, 10, size=(1, ))

            if self.transform is not None:
                fake_data = self.transform(fake_data)

            return fake_data, fake_label

        def __len__(self):
            return self.num_data

    # ============================ step 1/5 数据 ============================
    channel = 3     # 1 3
    img_size = 32   # 36 32
    train_data = FooDataset(num_data=32, shape=(channel, img_size, img_size))
    train_loader = DataLoader(dataset=train_data, batch_size=16, shuffle=True)

    # ============================ step 2/5 模型 ============================
    net = LeNet(classes=2)
    # ============================ step 3/5 损失函数 ============================
    criterion = nn.CrossEntropyLoss()
    # ============================ step 4/5 优化器 ============================
    optimizer = optim.SGD(net.parameters(), lr=0.01, momentum=0.9)  # 选择优化器
    scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=10)
    # ============================ step 5/5 训练 ============================
    data, label = next(iter(train_loader))
    outputs = net(data)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43

5.

代码示例：

# ========================== 5
# AttributeError: 'DataParallel' object has no attribute 'linear'
flag = 0
# flag = 1
if flag:
    class FooNet(nn.Module):
        def __init__(self):
            super(FooNet, self).__init__()
            self.linear = nn.Linear(3, 3, bias=True)
            self.conv1 = nn.Conv2d(3, 6, 5)
            self.pool1 = nn.MaxPool2d(5)

        def forward(self, x):
            return 1234567890

    net = FooNet()

    for layer_name, layer in net.named_modules():
        print(layer_name)

    net = nn.DataParallel(net)

    for layer_name, layer in net.named_modules():
        print(layer_name)

    print(net.module.linear) #Parallel后需要采用module来调用
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26

6.

代码示例：

# ========================== 6
# RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False.
#  If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu')
# to map your storages to the CPU.

flag = 0
# flag = 1
if flag:

    path_state_dict = "./model_in_multi_gpu.pkl"
    state_dict_load = torch.load(path_state_dict)
    # state_dict_load = torch.load(path_state_dict, map_location="cpu")
1
2
3
4
5
6
7
8
9
10
11
12

7.

代码示例：

# ========================== 7
# AttributeError: Can't get attribute 'FooNet2' on <module '__main__' from '
# flag = 0
flag = 1
if flag:
    path_net = os.path.join(BASE_DIR, "foo_net.pkl")

    # save
    class FooNet2(nn.Module):
        def __init__(self):
            super(FooNet2, self).__init__()
            self.linear = nn.Linear(3, 3, bias=True)

        def forward(self, x):
            return 1234567890
    #
    # net = FooNet2()
    # torch.save(net, path_net)

    # load

    net_load = torch.load(path_net)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22

8.

代码示例：

# ========================== 8
# RuntimeError: Assertion `cur_target >= 0 && cur_target < n_classes' failed.
flag = 0
# flag = 1
if flag:

    inputs = torch.tensor([[1, 2], [1, 3], [1, 3]], dtype=torch.float)
    target = torch.tensor([0, 0, 1], dtype=torch.long) #[0, 0, 2]会报错，因为是二分类任务。，只有0，1

    criterion = nn.CrossEntropyLoss()

    loss = criterion(inputs, target)
1
2
3
4
5
6
7
8
9
10
11
12

9.

代码示例：

# ========================== 9
# RuntimeError: expected device cuda:0 and dtype Long but got device cpu and dtype Long
flag = 0
# flag = 1
if flag:

    x = torch.tensor([1]) #x默认在cpu
    w = torch.tensor([2]).to(device) #y to到gpu
    # y = w * x

    x = x.to(device) #x to到gpu
    y = w * x
1
2
3
4
5
6
7
8
9
10
11
12

10.

代码示例：

# ========================== 10
# RuntimeError: Expected object of backend CPU but got backend CUDA for argument #2 'weight'
# flag = 0
flag = 1
if flag:
    def data_loader(num_data):
        for _ in range(num_data):
            img_ = torch.randn(1, 3, 224, 224)
            label_ = torch.randint(0, 10, size=(1,))
            yield img_, label_

    resnet18 = models.resnet18()
    resnet18.to(device)

    for inputs, labels in data_loader(2):

        # inputs.to(device) #tensor的to操作不是inplace操作，需要赋值
        # labels.to(device)
        # outputs = resnet18(inputs)

        inputs = inputs.to(device)
        labels = labels.to(device)
        outputs = resnet18(inputs)
        print("outputs device:{}".format(outputs.device))
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24

完整代码

common_errors.py

# -*- coding: utf-8 -*-
"""
# @file name  : common_errors.py
# @brief      : 常见errors
"""

import os
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision.transforms as transforms
import torchvision.models as models
from torch.utils.data import DataLoader
from tools.my_dataset import RMBDataset
from torch.utils.data import Dataset
from model.lenet import LeNet
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# ========================== 1 num_samples=0
flag = 0
# flag = 1
if flag:
    # train_dir = os.path.join("..", "data", "rmb_split", "train")
    train_dir = os.path.join("..", "..", "data", "rmb_split", "train")
    train_data = RMBDataset(data_dir=train_dir)

    # 构建DataLoder
    train_loader = DataLoader(dataset=train_data, batch_size=16, shuffle=True)


# ========================== 2
# TypeError: pic should be PIL Image or ndarray. Got <class 'torch.Tensor'>
flag = 0
# flag = 1
if flag:
    train_transform = transforms.Compose([
        transforms.Resize((224, 224)),

        transforms.FiveCrop(200),
        transforms.Lambda(lambda crops: torch.stack([(transforms.ToTensor()(crop)) for crop in crops])),

        # transforms.ToTensor(),
        # transforms.ToTensor(),
    ])

    train_dir = os.path.join("..", "..", "data", "rmb_split", "train")
    train_data = RMBDataset(data_dir=train_dir, transform=train_transform)
    train_loader = DataLoader(dataset=train_data, batch_size=16, shuffle=True)

    data, label = next(iter(train_loader))


# ========================== 3
# RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0
flag = 0
# flag = 1
if flag:

    class FooDataset(Dataset):
        def __init__(self,  num_data, data_dir=None, transform=None):
            self.foo = data_dir
            self.transform = transform
            self.num_data = num_data

        def __getitem__(self, item):

            size = torch.randint(63, 64, size=(1, )) #[63,64)]
            fake_data = torch.zeros((3, size, size))
            fake_label = torch.randint(0, 10, size=(1, ))

            return fake_data, fake_label

        def __len__(self):
            return self.num_data


    foo_dataset = FooDataset(num_data=10)
    foo_dataloader = DataLoader(dataset=foo_dataset, batch_size=4)

    data, label = next(iter(foo_dataloader))


# ========================== 4
# Given groups=1, weight of size 6 3 5 5, expected input[16, 1, 32, 32] to have 3 channels, but got 1 channels instead
# RuntimeError: size mismatch, m1: [16 x 576], m2: [400 x 120] at ../aten/src/TH/generic/THTensorMath.cpp:752
flag = 0
# flag = 1
if flag:

    class FooDataset(Dataset):
        def __init__(self,  num_data, shape, data_dir=None, transform=None):
            self.foo = data_dir
            self.transform = transform
            self.num_data = num_data
            self.shape = shape

        def __getitem__(self, item):

            fake_data = torch.zeros(self.shape)
            fake_label = torch.randint(0, 10, size=(1, ))

            if self.transform is not None:
                fake_data = self.transform(fake_data)

            return fake_data, fake_label

        def __len__(self):
            return self.num_data

    # ============================ step 1/5 数据 ============================
    channel = 3     # 1 3
    img_size = 32   # 36 32
    train_data = FooDataset(num_data=32, shape=(channel, img_size, img_size))
    train_loader = DataLoader(dataset=train_data, batch_size=16, shuffle=True)

    # ============================ step 2/5 模型 ============================
    net = LeNet(classes=2)
    # ============================ step 3/5 损失函数 ============================
    criterion = nn.CrossEntropyLoss()
    # ============================ step 4/5 优化器 ============================
    optimizer = optim.SGD(net.parameters(), lr=0.01, momentum=0.9)  # 选择优化器
    scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=10)
    # ============================ step 5/5 训练 ============================
    data, label = next(iter(train_loader))
    outputs = net(data)


# ========================== 5
# AttributeError: 'DataParallel' object has no attribute 'linear'
flag = 0
# flag = 1
if flag:
    class FooNet(nn.Module):
        def __init__(self):
            super(FooNet, self).__init__()
            self.linear = nn.Linear(3, 3, bias=True)
            self.conv1 = nn.Conv2d(3, 6, 5)
            self.pool1 = nn.MaxPool2d(5)

        def forward(self, x):
            return 1234567890

    net = FooNet()

    for layer_name, layer in net.named_modules():
        print(layer_name)

    net = nn.DataParallel(net)

    for layer_name, layer in net.named_modules():
        print(layer_name)

    print(net.module.linear) #Parallel后需要采用module来调用


# ========================== 6
# RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False.
#  If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu')
# to map your storages to the CPU.

flag = 0
# flag = 1
if flag:

    path_state_dict = "./model_in_multi_gpu.pkl"
    state_dict_load = torch.load(path_state_dict)
    # state_dict_load = torch.load(path_state_dict, map_location="cpu")


# ========================== 7
# AttributeError: Can't get attribute 'FooNet2' on <module '__main__' from '
# flag = 0
flag = 1
if flag:
    path_net = os.path.join(BASE_DIR, "foo_net.pkl")

    # save
    class FooNet2(nn.Module):
        def __init__(self):
            super(FooNet2, self).__init__()
            self.linear = nn.Linear(3, 3, bias=True)

        def forward(self, x):
            return 1234567890
    #
    # net = FooNet2()
    # torch.save(net, path_net)

    # load

    net_load = torch.load(path_net)


# ========================== 8
# RuntimeError: Assertion `cur_target >= 0 && cur_target < n_classes' failed.
flag = 0
# flag = 1
if flag:

    inputs = torch.tensor([[1, 2], [1, 3], [1, 3]], dtype=torch.float)
    target = torch.tensor([0, 0, 1], dtype=torch.long) #[0, 0, 2]会报错，因为是二分类任务。，只有0，1

    criterion = nn.CrossEntropyLoss()

    loss = criterion(inputs, target)

# ========================== 9
# RuntimeError: expected device cuda:0 and dtype Long but got device cpu and dtype Long
flag = 0
# flag = 1
if flag:

    x = torch.tensor([1]) #x默认在cpu
    w = torch.tensor([2]).to(device) #y to到gpu
    # y = w * x

    x = x.to(device) #x to到gpu
    y = w * x


# ========================== 10
# RuntimeError: Expected object of backend CPU but got backend CUDA for argument #2 'weight'
# flag = 0
flag = 1
if flag:
    def data_loader(num_data):
        for _ in range(num_data):
            img_ = torch.randn(1, 3, 224, 224)
            label_ = torch.randint(0, 10, size=(1,))
            yield img_, label_

    resnet18 = models.resnet18()
    resnet18.to(device)

    for inputs, labels in data_loader(2):

        # inputs.to(device) #tensor的to操作不是inplace操作，需要赋值
        # labels.to(device)
        # outputs = resnet18(inputs)

        inputs = inputs.to(device)
        labels = labels.to(device)
        outputs = resnet18(inputs)
        print("outputs device:{}".format(outputs.device))
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246