将很难在此处发布最小的工作示例，但是基本上我正在尝试修改该项目http://torch.ch/blog/2015/09/21/rmva.html，该项目可以与MNIST一起正常工作。我正在尝试使用自定义dataloader.py的数据集运行它，如下所示：
from __future__ import print_function, division #ds
import numpy as np
from utils import plot_images
import os #ds
import pandas as pd #ds
from skimage import io, transform #ds
import torch
from torchvision import datasets
from torch.utils.data import Dataset, DataLoader #ds
from torchvision import transforms
from torchvision import utils #ds
from torch.utils.data.sampler import SubsetRandomSampler
class CDataset(Dataset):
def __init__(self, csv_file, root_dir, transform=None):
"""
Args:
csv_file (string): Path to the csv file with annotations.
root_dir (string): Directory with all the images.
transform (callable, optional): Optional transform to be applied
on a sample.
"""
self.frame = pd.read_csv(csv_file)
self.root_dir = root_dir
self.transform = transform
def __len__(self):
return len(self.frame)
def __getitem__(self, idx):
img_name = os.path.join(self.root_dir,
self.frame.iloc[idx, 0]+'.jpg')
image = io.imread(img_name)
# image = image.transpose((2, 0, 1))
labels = np.array(self.frame.iloc[idx, 1])#.as_matrix() #ds
#landmarks = landmarks.astype('float').reshape(-1, 2)
#print(image.shape)
#print(img_name,labels)
sample = {'image': image, 'labels': labels}
if self.transform:
sample = self.transform(sample)
return sample
class ToTensor(object):
"""Convert ndarrays in sample to Tensors."""
def __call__(self, sample):
image, labels = sample['image'], sample['labels']
#print(image)
#print(labels)
# swap color axis because
# numpy image: H x W x C
# torch image: C X H X W
image = image.transpose((2, 0, 1))
#print(image.shape)
#print((torch.from_numpy(image)))
#print((torch.from_numpy(labels)))
return {'image': torch.from_numpy(image),
'labels': torch.from_numpy(labels)}
def get_train_valid_loader(data_dir,
batch_size,
random_seed,
#valid_size=0.1, #ds
#shuffle=True,
show_sample=False,
num_workers=4,
pin_memory=False):
"""
Utility function for loading and returning train and valid
multi-process iterators over the MNIST dataset. A sample
9x9 grid of the images can be optionally displayed.
If using CUDA, num_workers should be set to 1 and pin_memory to True.
Args
----
- data_dir: path directory to the dataset.
- batch_size: how many samples per batch to load.
- random_seed: fix seed for reproducibility.
- #ds valid_size: percentage split of the training set used for
the validation set. Should be a float in the range [0, 1].
In the paper, this number is set to 0.1.
- shuffle: whether to shuffle the train/validation indices.
- show_sample: plot 9x9 sample grid of the dataset.
- num_workers: number of subprocesses to use when loading the dataset.
- pin_memory: whether to copy tensors into CUDA pinned memory. Set it to
True if using GPU.
Returns
-------
- train_loader: training set iterator.
- valid_loader: validation set iterator.
"""
#ds
#error_msg = "[!] valid_size should be in the range [0, 1]."
#assert ((valid_size >= 0) and (valid_size <= 1)), error_msg
#ds
# define transforms
#normalize = transforms.Normalize((0.1307,), (0.3081,))
trans = transforms.Compose([
ToTensor(), #normalize,
])
# load train dataset
#train_dataset = datasets.MNIST(
# data_dir, train=True, download=True, transform=trans
#)
train_dataset = CDataset(csv_file='/home/Desktop/6June17/util/train.csv',
root_dir='/home/caffe/data/images/',transform=trans)
# load validation dataset
#valid_dataset = datasets.MNIST( #ds
# data_dir, train=True, download=True, transform=trans #ds
#)
valid_dataset = CDataset(csv_file='/home/Desktop/6June17/util/eval.csv',
root_dir='/home/caffe/data/images/',transform=trans)
num_train = len(train_dataset)
train_indices = list(range(num_train))
#ds split = int(np.floor(valid_size * num_train))
num_valid = len(valid_dataset) #ds
valid_indices = list(range(num_valid)) #ds
#if shuffle:
# np.random.seed(random_seed)
# np.random.shuffle(indices)
#ds train_idx, valid_idx = indices[split:], indices[:split]
train_idx = train_indices #ds
valid_idx = valid_indices #ds
train_sampler = SubsetRandomSampler(train_idx)
valid_sampler = SubsetRandomSampler(valid_idx)
train_loader = torch.utils.data.DataLoader(
train_dataset, batch_size=batch_size, sampler=train_sampler,
num_workers=num_workers, pin_memory=pin_memory,
)
print(train_loader)
valid_loader = torch.utils.data.DataLoader(
valid_dataset, batch_size=batch_size, sampler=valid_sampler,
num_workers=num_workers, pin_memory=pin_memory,
)
# visualize some images
if show_sample:
sample_loader = torch.utils.data.DataLoader(
dataset, batch_size=9, #shuffle=shuffle,
num_workers=num_workers, pin_memory=pin_memory
)
data_iter = iter(sample_loader)
images, labels = data_iter.next()
X = images.numpy()
X = np.transpose(X, [0, 2, 3, 1])
plot_images(X, labels)
return (train_loader, valid_loader)
def get_test_loader(data_dir,
batch_size,
num_workers=4,
pin_memory=False):
"""
Utility function for loading and returning a multi-process
test iterator over the MNIST dataset.
If using CUDA, num_workers should be set to 1 and pin_memory to True.
Args
----
- data_dir: path directory to the dataset.
- batch_size: how many samples per batch to load.
- num_workers: number of subprocesses to use when loading the dataset.
- pin_memory: whether to copy tensors into CUDA pinned memory. Set it to
True if using GPU.
Returns
-------
- data_loader: test set iterator.
"""
# define transforms
#normalize = transforms.Normalize((0.1307,), (0.3081,))
trans = transforms.Compose([
ToTensor(), #normalize,
])
# load dataset
#dataset = datasets.MNIST(
# data_dir, train=False, download=True, transform=trans
#)
test_dataset = CDataset(csv_file='/home/Desktop/6June17/util/test.csv',
root_dir='/home/caffe/data/images/',transform=trans)
test_loader = torch.utils.data.DataLoader(
test_dataset, batch_size=batch_size, shuffle=False,
num_workers=num_workers, pin_memory=pin_memory,
)
return test_loader
#for i_batch, sample_batched in enumerate(dataloader):
# print(i_batch, sample_batched['image'].size(),
# sample_batched['landmarks'].size())
# # observe 4th batch and stop.
# if i_batch == 3:
# plt.figure()
# show_landmarks_batch(sample_batched)
# plt.axis('off')
# plt.ioff()
# plt.show()
# break
我进行的其他主要更改是关闭验证大小和改组的参数输入（因为我使用的是预先存在的训练，验证和测试拆分，并且我已经对这些拆分进行了改编）
最后一次更改是在train_one_epoch(self, epoch)函数中进行，而在trainer.py中进行迭代。我已经更改了这部分，因为以前的x，y是作为"image"和"labels"的字符串返回的-python字典的标头，而不是成批分配的值。 / p>
for i, batch in enumerate(self.train_loader):
x, y = batch["image"], batch["labels"]
但是现在我在网络培训中遇到了一些错误，由于我是pytorch的新手，所以我无法弄清楚：
[*] Train on 64034 samples, validate on 18951 samples Epoch: 1/200 - LR: 0.000300 <torch.utils.data.dataloader.DataLoader object at 0x7fe065fd4f60> 0%| | 0/64034 [00:00<?, ?it/s]/home/duygu/recurrent-visual-attention-master/modules.py:106: UserWarning: invalid index of a 0-dim tensor. This will be an error in PyTorch 0.5. Use tensor.item() to convert a 0-dim tensor to a Python number from_x, to_x = from_x.data[0], to_x.data[0] /home/duygu/recurrent-visual-attention-master/modules.py:107: UserWarning: invalid index of a 0-dim tensor. This will be an error in PyTorch 0.5. Use tensor.item() to convert a 0-dim tensor to a Python number from_y, to_y = from_y.data[0], to_y.data[0]
Traceback (most recent call last): File "main.py", line 49, in <module>
main(config) File "main.py", line 40, in main
trainer.train() File "/home/duygu/recurrent-visual-attention-master/trainer.py", line 168, in train
train_loss, train_acc = self.train_one_epoch(epoch) File "/home/duygu/recurrent-visual-attention-master/trainer.py", line 252, in train_one_epoch
h_t, l_t, b_t, p = self.model(x, l_t, h_t) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 491, in __call__
result = self.forward(*input, **kwargs) File "/home/duygu/recurrent-visual-attention-master/model.py", line 101, in forward
g_t = self.sensor(x, l_t_prev) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 491, in __call__
result = self.forward(*input, **kwargs) File "/home/duygu/recurrent-visual-attention-master/modules.py", line 214, in forward
phi_out = F.relu(self.fc1(phi)) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 491, in __call__
result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/linear.py", line 55, in forward
return F.linear(input, self.weight, self.bias) File "/usr/local/lib/python3.5/dist-packages/torch/nn/functional.py", line 992, in linear
return torch.addmm(bias, input, weight.t()) RuntimeError: Expected object of type torch.FloatTensor but found type torch.ByteTensor for argument #4 'mat1'
我正在寻求有关如何纠正此错误并了解导致该错误的建议，即使在没有GPU支持的情况下运行它也会得到此错误。我不知道是否通过查看初始警告将参数传递为空。
答案 0 :(得分：2)
据我所知，似乎您评论了应用于数据集的normalize / transforms.Normalize操作时，图像之间的值没有标准化为float [0, 1]，而是将其byte的值保持在[0, 255]之间。
尝试应用数据规范化或至少将图像转换为float（32位，而不是64）值（例如，在ToTensor中，添加image = image.float()或当它仍然是numpy时在将它们馈送到您的网络之前，先使用data.astype(numpy.float32)进行排列。