PyTorch学习笔记（32）pytorch常见报错信息

pytorch常见报错信息

1.报错：

ValueError: num_samples should be a positive integer value, but got num_samples=0

可能的原因：

传入的Dataset中的len(self.data_info)==0，即传入该dataloader的dataset里没有数据

解决方法：

1. 检查dataset中的路径，路径不对，读取不到数据。
2. 检查Dataset的__len__()函数为何输出为零

2.报错：

TypeError: pic should be PIL Image or ndarray. Got

可能的原因：

当前操作需要PIL Image或ndarray数据类型，但传入了Tensor

解决方法：

1. 检查transform中是否存在两次ToTensor()方法
2. 检查transform中每一个操作的数据类型变化

3.报错：

RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 93 and 89 in dimension 1 at /Users/soumith/code/builder/wheel/pytorch-src/aten/src/TH/generic/THTensorMath.cpp:3616

可能的原因：

dataloader的__getitem__函数中，返回的图片形状不一致，导致无法stack

解决方法：检查__getitem__函数中的操作

4.报错：

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

可能的原因：

网络层输入数据与网络的参数不匹配

解决方法：

1. 检查对应网络层前后定义是否有误
2. 检查输入数据shape

5.报错：

AttributeError: ‘DataParallel’ object has no attribute ‘linear’

可能的原因：

并行运算时，模型被dataparallel包装，所有module都增加一个属性 module. 因此需要通过 net.module.linear调用

解决方法：

1. 网络层前加入module.

6.报错:

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.

可能的原因：gpu训练的模型保存后，在无gpu设备上无法直接加载

解决方法：

1. 需要设置map_location=“cpu”

7.报错：

AttributeError: Can’t get attribute ‘FooNet2’ on main’ from ’

可能的原因：

保存的网络模型在当前python脚本中没有定义

解决方法：

1. 提前定义该类

8.报错：

RuntimeError: Assertion `cur_target >= 0 && cur_target < n_classes’ failed. at …/aten/src/THNN/generic/ClassNLLCriterion.c:94

可能的原因：

1. 标签数大于等于类别数量，即不满足 cur_target < n_classes，通常是因为标签从1开始而不是从0开始

解决方法：

1. 修改label，从0开始，例如：10分类的标签取值应该是0-9

9.报错：

RuntimeError: expected device cuda:0 and dtype Long but got device cpu and dtype Long
Expected object of backend CPU but got backend CUDA for argument #2 ‘weight’

可能的原因：

需计算的两个数据不在同一个设备上

解决方法：采用to函数将数据迁移到同一个设备上

10. 报错：

RuntimeError: DataLoader worker (pid 27) is killed by signal: Killed. Details are lost due to multiprocessing. Rerunning with num_workers=0 may give better error trace.

可能原因：

内存不够（不是gpu显存，是内存）

解决方法：申请更大内存

# -*- coding: utf-8 -*-


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 
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, ))
            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)


# ========================== 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 
# 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)

    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])
    w = torch.tensor([2]).to(device)
    # y = w * x

    x = x.to(device)
    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)
        # labels.to(device)
        # outputs = resnet18(inputs)

        inputs = inputs.to(device)
        labels = labels.to(device)
        outputs = resnet18(inputs)
        print("outputs device:{}".format(outputs.device))