OSError:无法识别图像文件 [英] OSError: cannot identify image file
问题描述
我正在pytorch中尝试实现代码,但出现以下错误.我的python版本是3.6,我的操作系统是linux ubuntu 16.04 lts.我在Mac os的旁边安装了linux.我们将使用torchvision和torch.utils.data包来加载数据.每个类有75个验证图像.
I am trying impelement code in pytorch but I get bellow error. my python version is 3.6 and my os is linux ubuntu 16.04 lts. I installed my linux alongside of mac os. We will use torchvision and torch.utils.data packages for loading the data.There are 75 validation images for each class.
OSError Traceback (most recent call last)
<ipython-input-4-e0e3a841f698> in <module>()
62
63 # Get a batch of training data
---> 64 inputs, classes = next(iter(dset_loaders['train']))
65
66 # Make a grid from batch
/home/zeinab/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py in __next__(self)
172 self.reorder_dict[idx] = batch
173 continue
--> 174 return self._process_next_batch(batch)
175
176 next = __next__ # Python 2 compatibility
/home/zeinab/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py in _process_next_batch(self, batch)
196 self._put_indices()
197 if isinstance(batch, ExceptionWrapper):
--> 198 raise batch.exc_type(batch.exc_msg)
199 return batch
200
OSError: Traceback (most recent call last):
File "/home/zeinab/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 32, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/zeinab/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 32, in <listcomp>
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/zeinab/anaconda3/lib/python3.6/site-packages/torchvision-0.1.7-py3.6.egg/torchvision/datasets/folder.py", line 57, in __getitem__
img = self.loader(os.path.join(self.root, path))
File "/home/zeinab/anaconda3/lib/python3.6/site-packages/torchvision-0.1.7-py3.6.egg/torchvision/datasets/folder.py", line 38, in default_loader
return Image.open(path).convert('RGB')
File "/home/zeinab/anaconda3/lib/python3.6/site-packages/PIL/Image.py", line 2349, in open
% (filename if filename else fp))
OSError: cannot identify image file 'hymenoptera_data/train/ants/._154124431_65460430f2.jpg'
我的代码如下:
%matplotlib inline
# License: BSD
# Author: Sasank Chilamkurthy
from __future__ import print_function, division
import torch
import torch.nn as nn
import torch.optim as optim
from torch.autograd import Variable
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import copy
import os
from PIL import Image
import os, sys
plt.ion() # interactive mode
# Data augmentation and normalization for training
# Just normalization for validation
data_transforms = {
'train': transforms.Compose([
transforms.RandomSizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
'val': transforms.Compose([
transforms.Scale(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
}
data_dir = 'hymenoptera_data'
dsets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])
for x in ['train', 'val']}
dset_loaders = {x: torch.utils.data.DataLoader(dsets[x], batch_size=4,
shuffle=True, num_workers=4)
for x in ['train', 'val']}
dset_sizes = {x: len(dsets[x]) for x in ['train', 'val']}
dset_classes = dsets['train'].classes
use_gpu = torch.cuda.is_available()
def imshow(inp, title=None):
"""Imshow for Tensor."""
inp = inp.numpy().transpose((1, 2, 0))
mean = np.array([0.485, 0.456, 0.406])
std = np.array([0.229, 0.224, 0.225])
inp = std * inp + mean
plt.imshow(inp)
if title is not None:
plt.title(title)
plt.pause(0.001) # pause a bit so that plots are updated
# Get a batch of training data
inputs, classes = next(iter(dset_loaders['train']))
# Make a grid from batch
out = torchvision.utils.make_grid(inputs)
imshow(out, title=[dset_classes[x] for x in classes])
推荐答案
我猜想在Windows环境中使用枕头时,图片或包含图片的文件夹是在MacOS中创建的.手动创建文件夹(例如火车/蚂蚁"),然后将图像复制到新文件夹即可解决该问题.
I guess the pictures or folder containing the pictures are created in MacOS while you are doing with pillow in Windows environment. Manually create folders (like 'train/ants') and copy the images to the new folders would solve it.
这篇关于OSError:无法识别图像文件的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!