Hello!
I am newbie in neural networks, maybe somebody here may help me?
So, i have 2 classes and my own dataset with 17000(7500 for one class, 7500 for another for training, and 2000 for testing) images. I am trying to teach CNN to recognize modified and non modified images. My code is below:
import torch
import numpy as np
# check if CUDA is available
train_on_gpu = torch.cuda.is_available()
if not train_on_gpu:
print('CUDA is not available. Training on CPU ...')
else:
print('CUDA is available! Training on GPU ...')
###################Đ’ Data loading ###################
import torchvision.datasets
from torchvision import datasets
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
from torch.utils.data.sampler import SubsetRandomSampler
# Read data from folders
main_path = '../ready_dataset_2classes'
train_data_path = main_path + '/train'
test_data_path = main_path + '/test'
weigths_path = '../ready_dataset_2classes/weights/weights_for_2classes.pt'
# number of subprocesses to use for data loading
num_workers = 0
# how many samples per batch to load
batch_size = 32 #20
# percentage of training set to use as validation
valid_size = 0.2
# convert data to a normalized torch.FloatTensor
transform = transforms.Compose([
transforms.Resize(32),
transforms.CenterCrop(32),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
# choose the training and test datasets
train_data = torchvision.datasets.ImageFolder(root=train_data_path, transform=transform)
train_data_loader = DataLoader(train_data, batch_size=batch_size, shuffle=True, num_workers=0)
test_data = torchvision.datasets.ImageFolder(root=test_data_path, transform=transform)
test_data_loader = DataLoader(test_data, batch_size=batch_size, shuffle=True, num_workers=0)
# obtain training indices that will be used for validation
num_train = len(train_data)
indices = list(range(num_train))
np.random.shuffle(indices)
split = int(np.floor(valid_size * num_train))
train_idx, valid_idx = indices[split:], indices[:split]
# define samplers for obtaining training and validation batches
train_sampler = SubsetRandomSampler(train_idx)
valid_sampler = SubsetRandomSampler(valid_idx)
# prepare data loaders (combine dataset and sampler)
train_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size,
sampler=train_sampler, num_workers=num_workers)
valid_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size,
sampler=valid_sampler, num_workers=num_workers)
test_loader = torch.utils.data.DataLoader(test_data, batch_size=batch_size,
num_workers=num_workers)
# specify the image classes
classes = ['Modified', 'Original']
# helper function to un-normalize and display an image
def imshow(img):
img = img / 2 + 0.5 # unnormalize
plt.imshow(np.transpose(img, (1, 2, 0))) # convert from Tensor image
# creating checkpoints
def savePoint(main_path, model, optimizer, epoch, valid_loss_min):
torch.save({
'model_state_dict': model.state_dict(),
'optimizer_state_dict': optimizer.state_dict(),
'epoch': epoch,
'valid_loss_min': valid_loss_min,
}, main_path)
def loadPoint(main_path, model, optimizer, epoch, valid_loss_min):
checkpoint = torch.load(main_path)
model.load_state_dict(checkpoint['model_state_dict'])
optimizer.load_state_dict(checkpoint['optimizer_state_dict'])
epoch = checkpoint['epoch']
valid_loss_min = checkpoint['valid_loss_min']
################### Network architecture definition ###################
import torch.nn as nn
import torch.nn.functional as F
# define the CNN architecture
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
# convolutional layer (sees 32x32x3 image tensor)
self.conv1 = nn.Conv2d(3, 16, 3, padding=1)
# convolutional layer (sees 16x16x16 tensor)
self.conv2 = nn.Conv2d(16, 32, 3, padding=1)
# convolutional layer (sees 8x8x32 tensor)
self.conv3 = nn.Conv2d(32, 64, 3, padding=1)
# max pooling layer
self.pool = nn.MaxPool2d(2, 2)
# linear layer (64 * 4 * 4 -> 500)
self.fc1 = nn.Linear(64 * 4 * 4, 500)
# linear layer (500 -> 10)
self.fc2 = nn.Linear(500, 10)
# dropout layer (p=0.25)
self.dropout = nn.Dropout(0.1) #0.25
def forward(self, x):
# add sequence of convolutional and max pooling layers
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = self.pool(F.relu(self.conv3(x)))
# flatten image input
x = x.view(-1, 64 * 4 * 4)
# add dropout layer
x = self.dropout(x)
# add 1st hidden layer, with relu activation function
x = F.relu(self.fc1(x))
# add dropout layer
x = self.dropout(x)
# add 2nd hidden layer, with relu activation function
x = self.fc2(x)
return x
# create a complete CNN
model = Net()
print(model)
# move tensors to GPU if CUDA is available
if train_on_gpu:
model.cuda()
#Loss and optimization specification
import torch.optim as optim
# specify loss function (categorical cross-entropy)
criterion = nn.CrossEntropyLoss()
# specify optimizer
optimizer = optim.SGD(model.parameters(), lr=0.005)
################### Network training ###################
# number of epochs to train the model
n_epochs = 300 #5000
print('Starting training!')
valid_loss_min = np.Inf # track change in validation loss
for epoch in range(1, n_epochs+1):
# keep track of training and validation loss
train_loss = 0.0
valid_loss = 0.0
loadPoint(weigths_path, model, optimizer, epoch, valid_loss_min)
###################
# train the model #
###################
model.train()
for data, target in train_loader:
# move tensors to GPU if CUDA is available
if train_on_gpu:
data, target = data.cuda(), target.cuda()
# clear the gradients of all optimized variables
optimizer.zero_grad()
# forward pass: compute predicted outputs by passing inputs to the model
output = model(data)
# calculate the batch loss
loss = criterion(output, target)
# backward pass: compute gradient of the loss with respect to model parameters
loss.backward()
# perform a single optimization step (parameter update)
optimizer.step()
# update training loss
train_loss += loss.item()*data.size(0)
######################
# validate the model #
######################
model.eval()
for data, target in valid_loader:
# move tensors to GPU if CUDA is available
if train_on_gpu:
data, target = data.cuda(), target.cuda()
# forward pass: compute predicted outputs by passing inputs to the model
output = model(data)
# calculate the batch loss
loss = criterion(output, target)
# update average validation loss
valid_loss += loss.item()*data.size(0)
# calculate average losses
train_loss = train_loss/len(train_loader.sampler)
valid_loss = valid_loss/len(valid_loader.sampler)
# print training/validation statistics
print('Epoch: {} \tTraining Loss: {:.6f} \tValidation Loss: {:.6f}'.format(
epoch, train_loss, valid_loss))
#checkpoint
if valid_loss <= valid_loss_min:
print('Validation loss decreased ({:.6f} --> {:.6f}). Saving model ...'.format(
valid_loss_min,
valid_loss))
savePoint(weigths_path, model, optimizer, epoch, valid_loss_min)
valid_loss_min = valid_loss
# Loading the model with the lowest validation loss
#loadPoint(weigths_path, model, optimizer, epoch, valid_loss_min)
#model.load_state_dict(torch.load('weights.pt'))
################### Neural network testing with UNSEEN data ###################
# track test loss
test_loss = 0.0
class_correct = list(0. for i in range(2))
class_total = list(0. for i in range(2))
model.eval()
# iterate over test data
for data, target in test_loader:
# move tensors to GPU if CUDA is available
if train_on_gpu:
data, target = data.cuda(), target.cuda()
# forward pass: compute predicted outputs by passing inputs to the model
output = model(data)
# calculate the batch loss
loss = criterion(output, target)
# update test loss
test_loss += loss.item()*data.size(0)
# convert output probabilities to predicted class
_, pred = torch.max(output, 1)
# compare predictions to true label
correct_tensor = pred.eq(target.data.view_as(pred))
correct = np.squeeze(correct_tensor.numpy()) if not train_on_gpu else np.squeeze(correct_tensor.cpu().numpy())
# calculate test accuracy for each object class
for i in range(len(target.data)):
label = target.data[i]
class_correct[label] += correct[i].item()
class_total[label] += 1
# average test loss
test_loss = test_loss/len(test_loader.dataset)
print('Test Loss: {:.6f}\n'.format(test_loss))
for i in range(2):
if class_total[i] > 0:
print('Test Accuracy of %5s: %2d%% (%2d/%2d)' % (
classes[i], 100 * class_correct[i] / class_total[i],
np.sum(class_correct[i]), np.sum(class_total[i])))
else:
print('Test Accuracy of %5s: N/A (no training examples)' % (classes[i]))
print('\nTest Accuracy (Overall): %2d%% (%2d/%2d)' % (
100. * np.sum(class_correct) / np.sum(class_total),
np.sum(class_correct), np.sum(class_total)))
My problem is that when i am testing results, i get only 61% percent of recognition, which is pretty low for me. And my neural network do not learn anything new in about ~100 epochs, so it takes a lot of time…
For now my best result in training loss is 0.499814 and valid loss is 0.506415
What should i change to get better result and improve it?
I have already tried to change Dropout and learning rate, but nothing really changed a lot :c
Maybe i am doing something wrong and some of you can give me advice or point out an error?
If i am right, it is “dying ReLu” problem, but i don’t know how to fix it 
p.s. sorry for bad english, i hope i described my problem pretty understandably.
