尝试使用 pytorch 创建我自己的数据集时出现未知重采样过滤器错误
unknown resampling filter error when trying to create my own dataset with pytorch
我正在尝试创建一个在 pytorch 中使用数据增强实现的 CNN 来对狗和猫进行分类。我遇到的问题是，当我尝试输入我的数据集并通过它进行枚举时，我不断收到此错误：
Traceback (most recent call last):
File "<ipython-input-55-6337e0536bae>", line 75, in <module>
for i, (inputs, labels) in enumerate(trainloader):
File "/usr/local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 188, in __next__
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/usr/local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 188, in <listcomp>
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/usr/local/lib/python3.6/site-packages/torchvision/datasets/folder.py", line 124, in __getitem__
img = self.transform(img)
File "/usr/local/lib/python3.6/site-packages/torchvision/transforms/transforms.py", line 42, in __call__
img = t(img)
File "/usr/local/lib/python3.6/site-packages/torchvision/transforms/transforms.py", line 147, in __call__
return F.resize(img, self.size, self.interpolation)
File "/usr/local/lib/python3.6/site-packages/torchvision/transforms/functional.py", line 197, in resize
return img.resize((ow, oh), interpolation)
File "/usr/local/lib/python3.6/site-packages/PIL/Image.py", line 1724, in resize
raise ValueError("unknown resampling filter")
ValueError: unknown resampling filter
而且我真的不知道我的代码有什么问题。我提供了以下代码：
# Creating the CNN
# Importing the libraries
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.autograd import Variable
import torchvision
from torchvision import transforms
#Creating the CNN Model
class CNN(nn.Module):
def __init__(self, nb_outputs):
super(CNN, self).__init__() #activates the inheritance and allows the use of all the tools in the nn.Module
#making the 3 convolutional layers that will be used in the convolutional neural network
self.convolution1 = nn.Conv2d(in_channels = 1, out_channels = 32, kernel_size = 5) #kernal_size -> the deminson of the feature detector e.g kernel_size = 5 => feature detector of size 5x5
self.convolution2 = nn.Conv2d(in_channels = 32, out_channels = 64, kernel_size = 2)
#making 2 full connections one to connect the inputs of the ANN to the hidden layer and another to connect the hidden layer to the outputs of the ANN
self.fc1 = nn.Linear(in_features = self.count_neurons((1, 64,64)), out_features = 40)
self.fc2 = nn.Linear(in_features = 40, out_features = nb_outputs)
def count_neurons(self, image_dim):
x = Variable(torch.rand(1, *image_dim)) #this variable repersents a fake image to allow us to compute the number of neruons
#in order to pass the elements of the tuple image_dim into our function as a list of arguments we need to add a * before image_dim
#since x will be going into our neural network we need to convert it into a torch variable using the Variable() function
x = F.relu(F.max_pool2d(self.convolution1(x), 3, 2)) #first we apply the convolution to x then apply max_pooling to the convolutional fake images and then activate all the neurons in the pooling layer
x = F.relu(F.max_pool2d(self.convolution2(x), 3, 2)) #the signals are now propragated up to the thrid convoulational layer
#Now to flatten x to obtain the number of neurons in the flattening layer
return x.data.view(1, -1).size(1) #this will flatten x into a huge vector and returns the size of the vector, that size repersents the number of neurons that will be inputted into the ANN
#even though x is not a real image from the game since the size of the flattened vector only depends on the dimention of the inputted image we can just set x to have the same dimentions as the image
def forward(self, x):
x = F.relu(F.max_pool2d(self.convolution1(x), 3, 2)) #first we apply the convolution to x then apply max_pooling to the convolutional fake images and then activate all the neurons in the pooling layer
x = F.relu(F.max_pool2d(self.convolution2(x), 3, 2))
#flattening layer of the CNN
x = x.view(x.size(0), -1)
#x is now the inputs to the ANN
x = F.relu(self.fc1(x)) #we propagte the signals from the flatten layer to the full connected layer and activate the neruons by breaking the linearilty with the relu function
x = F.sigmoid(self.fc2(x))
#x is now the output neurons of the ANN
return x
train_tf = transforms.Compose([transforms.RandomHorizontalFlip(),
transforms.Resize(64,64),
transforms.RandomRotation(20),
transforms.RandomGrayscale(.2),
transforms.ToTensor()])
test_tf = transforms.Compose([transforms.Resize(64,64),
transforms.ToTensor()])
training_set = torchvision.datasets.ImageFolder(root = './dataset/training_set',
transform = train_tf)
test_set = torchvision.datasets.ImageFolder(root = './dataset/test_set',
transform = transforms.Compose([transforms.Resize(64,64),
transforms.ToTensor()]) )
trainloader = torch.utils.data.DataLoader(training_set, batch_size=32,
shuffle=True, num_workers=0)
testloader = torch.utils.data.DataLoader(test_set, batch_size= 32,
shuffle=False, num_workers=0)
#training the model
cnn = CNN(1)
cnn.train()
loss = nn.BCELoss()
optimizer = optim.Adam(cnn.parameters(), lr = 0.001) #the optimizer => Adam optimizer
nb_epochs = 25
for epoch in range(nb_epochs):
train_loss = 0.0
train_acc = 0.0
total = 0.0
for i, (inputs, labels) in enumerate(trainloader):
inputs, labels = Variable(inputs), Variable(labels)
cnn.zero_grad()
outputs = cnn(inputs)
loss_error = loss(outputs, labels)
optimizer.step()
_, pred = torch.max(outputs.data, 1)
total += labels.size(0)
train_loss += loss_error.data[0]
train_acc += (pred == labels).sum()
train_loss = train_loss/len(training_loader)
train_acc = train_acc/total
print('Epoch: %d, loss: %.4f, accuracy: %.4f' %(epoch+1, train_loss, train_acc))
代码的文件夹排列是 /dataset/training_set，在 training_set 文件夹内还有两个文件夹，一个用于所有猫图像，另一个用于所有狗图像。每张图片的名称都是 dog.xxxx.jpg 或 cat.xxxx.jpg，其中 xxxx 表示数字，因此对于第一张猫图片，它将是 cat.1.jpg 到 cat.4000.jpg。这与 test_set 文件夹的格式相同。训练图片数量8000张，测试图片数量2000张。如果有人能指出我的错误，不胜感激。
谢谢
尝试将 transforms.Resize 中所需的大小设置为元组：
transforms.Resize((64, 64))
PIL 使用第二个参数（在你的例子中是 64）作为插值方法。
in torchvision.transforms.Compose（[将每个变换放在这些括号中]），
这样，就不会报错了。
我正在尝试创建一个在 pytorch 中使用数据增强实现的 CNN 来对狗和猫进行分类。我遇到的问题是，当我尝试输入我的数据集并通过它进行枚举时，我不断收到此错误：
Traceback (most recent call last):
File "<ipython-input-55-6337e0536bae>", line 75, in <module>
for i, (inputs, labels) in enumerate(trainloader):
File "/usr/local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 188, in __next__
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/usr/local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 188, in <listcomp>
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/usr/local/lib/python3.6/site-packages/torchvision/datasets/folder.py", line 124, in __getitem__
img = self.transform(img)
File "/usr/local/lib/python3.6/site-packages/torchvision/transforms/transforms.py", line 42, in __call__
img = t(img)
File "/usr/local/lib/python3.6/site-packages/torchvision/transforms/transforms.py", line 147, in __call__
return F.resize(img, self.size, self.interpolation)
File "/usr/local/lib/python3.6/site-packages/torchvision/transforms/functional.py", line 197, in resize
return img.resize((ow, oh), interpolation)
File "/usr/local/lib/python3.6/site-packages/PIL/Image.py", line 1724, in resize
raise ValueError("unknown resampling filter")
ValueError: unknown resampling filter
而且我真的不知道我的代码有什么问题。我提供了以下代码：
# Creating the CNN
# Importing the libraries
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.autograd import Variable
import torchvision
from torchvision import transforms
#Creating the CNN Model
class CNN(nn.Module):
def __init__(self, nb_outputs):
super(CNN, self).__init__() #activates the inheritance and allows the use of all the tools in the nn.Module
#making the 3 convolutional layers that will be used in the convolutional neural network
self.convolution1 = nn.Conv2d(in_channels = 1, out_channels = 32, kernel_size = 5) #kernal_size -> the deminson of the feature detector e.g kernel_size = 5 => feature detector of size 5x5
self.convolution2 = nn.Conv2d(in_channels = 32, out_channels = 64, kernel_size = 2)
#making 2 full connections one to connect the inputs of the ANN to the hidden layer and another to connect the hidden layer to the outputs of the ANN
self.fc1 = nn.Linear(in_features = self.count_neurons((1, 64,64)), out_features = 40)
self.fc2 = nn.Linear(in_features = 40, out_features = nb_outputs)
def count_neurons(self, image_dim):
x = Variable(torch.rand(1, *image_dim)) #this variable repersents a fake image to allow us to compute the number of neruons
#in order to pass the elements of the tuple image_dim into our function as a list of arguments we need to add a * before image_dim
#since x will be going into our neural network we need to convert it into a torch variable using the Variable() function
x = F.relu(F.max_pool2d(self.convolution1(x), 3, 2)) #first we apply the convolution to x then apply max_pooling to the convolutional fake images and then activate all the neurons in the pooling layer
x = F.relu(F.max_pool2d(self.convolution2(x), 3, 2)) #the signals are now propragated up to the thrid convoulational layer
#Now to flatten x to obtain the number of neurons in the flattening layer
return x.data.view(1, -1).size(1) #this will flatten x into a huge vector and returns the size of the vector, that size repersents the number of neurons that will be inputted into the ANN
#even though x is not a real image from the game since the size of the flattened vector only depends on the dimention of the inputted image we can just set x to have the same dimentions as the image
def forward(self, x):
x = F.relu(F.max_pool2d(self.convolution1(x), 3, 2)) #first we apply the convolution to x then apply max_pooling to the convolutional fake images and then activate all the neurons in the pooling layer
x = F.relu(F.max_pool2d(self.convolution2(x), 3, 2))
#flattening layer of the CNN
x = x.view(x.size(0), -1)
#x is now the inputs to the ANN
x = F.relu(self.fc1(x)) #we propagte the signals from the flatten layer to the full connected layer and activate the neruons by breaking the linearilty with the relu function
x = F.sigmoid(self.fc2(x))
#x is now the output neurons of the ANN
return x
train_tf = transforms.Compose([transforms.RandomHorizontalFlip(),
transforms.Resize(64,64),
transforms.RandomRotation(20),
transforms.RandomGrayscale(.2),
transforms.ToTensor()])
test_tf = transforms.Compose([transforms.Resize(64,64),
transforms.ToTensor()])
training_set = torchvision.datasets.ImageFolder(root = './dataset/training_set',
transform = train_tf)
test_set = torchvision.datasets.ImageFolder(root = './dataset/test_set',
transform = transforms.Compose([transforms.Resize(64,64),
transforms.ToTensor()]) )
trainloader = torch.utils.data.DataLoader(training_set, batch_size=32,
shuffle=True, num_workers=0)
testloader = torch.utils.data.DataLoader(test_set, batch_size= 32,
shuffle=False, num_workers=0)
#training the model
cnn = CNN(1)
cnn.train()
loss = nn.BCELoss()
optimizer = optim.Adam(cnn.parameters(), lr = 0.001) #the optimizer => Adam optimizer
nb_epochs = 25
for epoch in range(nb_epochs):
train_loss = 0.0
train_acc = 0.0
total = 0.0
for i, (inputs, labels) in enumerate(trainloader):
inputs, labels = Variable(inputs), Variable(labels)
cnn.zero_grad()
outputs = cnn(inputs)
loss_error = loss(outputs, labels)
optimizer.step()
_, pred = torch.max(outputs.data, 1)
total += labels.size(0)
train_loss += loss_error.data[0]
train_acc += (pred == labels).sum()
train_loss = train_loss/len(training_loader)
train_acc = train_acc/total
print('Epoch: %d, loss: %.4f, accuracy: %.4f' %(epoch+1, train_loss, train_acc))
代码的文件夹排列是 /dataset/training_set，在 training_set 文件夹内还有两个文件夹，一个用于所有猫图像，另一个用于所有狗图像。每张图片的名称都是 dog.xxxx.jpg 或 cat.xxxx.jpg，其中 xxxx 表示数字，因此对于第一张猫图片，它将是 cat.1.jpg 到 cat.4000.jpg。这与 test_set 文件夹的格式相同。训练图片数量8000张，测试图片数量2000张。如果有人能指出我的错误，不胜感激。
谢谢
尝试将 transforms.Resize 中所需的大小设置为元组：
transforms.Resize((64, 64))
PIL 使用第二个参数（在你的例子中是 64）作为插值方法。
in torchvision.transforms.Compose（[将每个变换放在这些括号中]）， 这样，就不会报错了。