I'm trying to modify this pytorch-example (https://github.com/pytorch/examples/blob/master/mnist/main.py) to work with my own dataset.
I tried to feed my data into a dataloader. I encapsulated the data in two different ways: one time as an extension of torch.utils.data.Dataset and one time as torch.utils.data.TensorDataset. Unfortunately I always get the same error that I don't understand:
Traceback (most recent call last):
File "main.py", line 142, in <module>
train(epoch)
File "main.py", line 112, in train
output = model(data)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 210, in __call__
result = self.forward(*input, **kwargs)
File "main.py", line 90, in forward
x = F.relu(F.max_pool2d(self.conv1(x), 2))
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 210, in __call__
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/conv.py", line 235, in forward
self.padding, self.dilation, self.groups)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/functional.py", line 54, in conv2d
return f(input, weight, bias) if bias is not None else f(input, weight)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/_functions/conv.py", line 33, in forward
output = self._update_output(input, weight, bias)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/_functions/conv.py", line 88, in _update_output
return self._thnn('update_output', input, weight, bias)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/_functions/conv.py", line 147, in _thnn
return impl[fn_name](self, self._bufs[0], input, weight, *args)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/_functions/conv.py", line 213, in call_update_output
backend = type2backend[type(input)]
File "/usr/local/lib/python2.7/dist-packages/torch/_thnn/__init__.py", line 13, in __getitem__
return self.backends[name].load()
KeyError: <class 'torch.cuda.ByteTensor'>
Here's my main.py, which is basically this example: https://github.com/pytorch/examples/blob/master/mnist/main.py
from __future__ import print_function
import argparse
import os
import glob
import numpy
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torch.utils.data as data_utils
from PIL import Image
from torchvision import datasets, transforms
from torch.autograd import Variable
from InputData import InputData
# Training settings
parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
parser.add_argument('--batch-size', type=int, default=64, metavar='N',
help='input batch size for training (default: 64)')
parser.add_argument('--test-batch-size', type=int, default=10, metavar='N',
help='input batch size for testing (default: 1000)')
parser.add_argument('--epochs', type=int, default=1, metavar='N',
help='number of epochs to train (default: 10)')
parser.add_argument('--lr', type=float, default=0.01, metavar='LR',
help='learning rate (default: 0.01)')
parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
help='SGD momentum (default: 0.5)')
parser.add_argument('--no-cuda', action='store_true', default=False,
help='disables CUDA training')
parser.add_argument('--seed', type=int, default=1, metavar='S',
help='random seed (default: 1)')
parser.add_argument('--log-interval', type=int, default=10, metavar='N',
help='how many batches to wait before logging training status')
args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
# Original DataLoader - WORKS:
'''
train_loader = torch.utils.data.DataLoader(
datasets.MNIST('../data', train=True, download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args.batch_size, shuffle=True, **kwargs)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('../data', train=False, transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args.batch_size, shuffle=True, **kwargs)
'''
# DataLoader as extension of data.Dataset:
train_loader = torch.utils.data.DataLoader(InputData('~/bakk-arbeit/data', train=True),
batch_size=args.batch_size, shuffle=True, **kwargs)
test_loader = torch.utils.data.DataLoader(InputData('~/bakk-arbeit/data', train=False),
batch_size=args.batch_size, shuffle=True, **kwargs)
# DataLoader as data.TensorDataset:
'''
data_folder = os.path.expanduser('~/bakk-arbeit/data')
InputData = InputData()
train = data_utils.TensorDataset(InputData.read_image_files(os.path.join(data_folder, 'training')),InputData.read_label_files(os.path.join(data_folder, 'training')))
test = data_utils.TensorDataset(InputData.read_image_files(os.path.join(data_folder, 'test')),InputData.read_label_files(os.path.join(data_folder, 'test')))
train_loader = data_utils.DataLoader(train, batch_size=args.batch_size, shuffle=True, **kwargs)
test_loader = data_utils.DataLoader(test, batch_size=args.batch_size, shuffle=True, **kwargs)
'''
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 10, kernel_size=5) # change to 3 input channels for InputData!
self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
self.conv2_drop = nn.Dropout2d()
self.fc1 = nn.Linear(320, 50) # change 320 to 500 for InputData to match 32x32
self.fc2 = nn.Linear(50, 10)
def forward(self, x):
x = F.relu(F.max_pool2d(self.conv1(x), 2))
x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
x = x.view(-1, 320) # # change 320 to 500 for InputData to match 32x32
x = F.relu(self.fc1(x))
x = F.dropout(x, training=self.training)
x = self.fc2(x)
return F.log_softmax(x)
model = Net()
if args.cuda:
model.cuda()
optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)
def train(epoch):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
# data = data.numpy()
if args.cuda:
data, target = data.cuda(), target.cuda()
data, target = Variable(data), Variable(target)
optimizer.zero_grad()
output = model(data)
loss = F.nll_loss(output, target)
loss.backward()
optimizer.step()
if batch_idx % args.log_interval == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.data[0]))
def test():
model.eval()
test_loss = 0
correct = 0
for data, target in test_loader:
if args.cuda:
data, target = data.cuda(), target.cuda()
data, target = Variable(data, volatile=True), Variable(target)
output = model(data)
test_loss += F.nll_loss(output, target, size_average=False).data[0] # sum up batch loss
pred = output.data.max(1)[1] # get the index of the max log-probability
correct += pred.eq(target.data.view_as(pred)).cpu().sum()
test_loss /= len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
for epoch in range(1, args.epochs + 1):
train(epoch)
test()
...and here's my InputData.py that extends data.Dataset:
import torch
import numpy
import torch.utils.data as data
import glob
import os
from PIL import Image
class InputData(data.Dataset):
train_folder = 'training'
test_folder = 'test'
def __init__(self, root='', train=True):
self.root = os.path.expanduser(root)
self.train = train # training set or test set
if root:
if self.train:
self.training_labels = self.read_label_files(os.path.join(self.root, self.train_folder))
#with open(os.path.join(self.root, 'training_labels.pt'), 'wb') as f:
# torch.save(self.read_label_files(os.path.join(self.root, self.train_folder)), f)
# with open(os.path.join(self.root, 'training_images.pt'), 'wb') as f:
#torch.save(self.read_image_files(os.path.join(self.root, self.train_folder)), f)
self.training_images = self.read_image_files(os.path.join(self.root, self.train_folder))
else:
self.test_images = self.read_image_files(os.path.join(self.root, self.test_folder))
self.test_labels = self.read_label_files(os.path.join(self.root, self.test_folder))
print('initialized')
def read_image_files(self, path):
print('reading image files...')
image_list = []
# ten = torch.ByteTensor(3,32,32)
for filename in glob.glob(path + '/*.png'):
im = Image.open(filename)
data = numpy.asarray(im)
data = numpy.swapaxes(data,0,2)
image_list.append(data)
image_list = numpy.asarray(image_list)
t = torch.from_numpy(image_list)
# ten = torch.stack([ten, t])
print('done!')
return t
def read_label_files(self, path):
print('reading labels...')
labels = []
for filename in glob.glob(path + '/*.png'):
base = os.path.basename(filename)
im_class = int(base[:1])
labels.append(im_class)
print('done!')
return torch.LongTensor(labels)
def __getitem__(self, index):
"""
Args:
index (int): Index
Returns:
tuple: (image, target) where target is index of the target class.
"""
if self.train:
img, target = self.training_images[Index], self.training_labels[Index]
else:
img, target = self.test_images[Index], self.test_labels[Index]
# img = Image.fromarray(img.numpy(), mode='RGB')
# -> won't work for me??? returns TypeError: batch must contain tensors, numbers, or lists; found <class 'PIL.Image.Image'>
return img, target
def __len__(self):
if self.train:
return len(self.training_images)
else:
return len(self.test_images)
What am I doing wrong?
It seems that most operation are defined on FloatTensor and DoubleTensor (source), and your model gets a ByteTensor in model(data).
I would go ahead an make sure that my dataset object outputs FloatTensors. Debug the line before model(data) and see the tensor type of data. I would guess it's a ByteTensor, that would be a good place to start.