train.py

from torchvision import datasets, models, transforms
from torch.autograd import Variable
import torch.optim as optim
import torch.nn as nn
import torch
import time
import copy
import os
import sys

# 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])
    ]),
    'test': 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 = 'data7'
dsets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])
         for x in ['train', 'test']}
dset_loaders = {x: torch.utils.data.DataLoader(dsets[x], batch_size=8,
                                               shuffle=True, num_workers=4)
                for x in ['train', 'test']}
dset_sizes = {x: len(dsets[x]) for x in ['train', 'test']}
dset_classes = dsets['train'].classes


# use_gpu = torch.cuda.is_available()
use_gpu = False

print("Using GPU {}".format(use_gpu))

def train_model(model, criterion, optimizer, lr_scheduler, num_epochs=25):
    since = time.time()

    best_model = model
    best_acc = 0.0

    for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch, num_epochs - 1))
        print('-' * 10)

        # Each epoch has a training and validation phase
        for phase in ['train', 'test']:
            if phase == 'train':
                optimizer = lr_scheduler(optimizer, epoch)
                model.train(True)  # Set model to training mode
            else:
                model.train(False)  # Set model to evaluate mode

            running_loss = 0.0
            running_corrects = 0

            # Iterate over data.
            for data in dset_loaders[phase]:
                # get the inputs
                inputs, labels = data

                # wrap them in Variable
                if use_gpu:
                    inputs, labels = Variable(inputs.cuda()), \
                        Variable(labels.cuda())
                else:
                    inputs, labels = Variable(inputs), Variable(labels)

                # zero the parameter gradients
                optimizer.zero_grad()

                # forward
                outputs = model(inputs)
                _, preds = torch.max(outputs.data, 1)
                loss = criterion(outputs, labels)

                # backward + optimize only if in training phase
                if phase == 'train':
                    loss.backward()
                    optimizer.step()

                # statistics
                running_loss += loss.data[0]
                running_corrects += torch.sum(preds == labels.data)                

            epoch_loss = running_loss / dset_sizes[phase] 
            epoch_acc = running_corrects / dset_sizes[phase] *100
            print('{} Loss: {:.4f} Acc: {:.4f}'.format(
                phase, epoch_loss, epoch_acc))

            # deep copy the model
            if phase == 'test' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model = copy.deepcopy(model)

        print()

    time_elapsed = time.time() - since
    print('Training complete in {:.0f}m {:.0f}s'.format(
        time_elapsed // 60, time_elapsed % 60))
    print('Best test Acc: {:4f}'.format(best_acc))
    return best_model

def exp_lr_scheduler(optimizer, epoch, init_lr=0.001, lr_decay_epoch=7):
    """Decay learning rate by a factor of 0.1 every lr_decay_epoch epochs."""
    lr = init_lr * (0.1**(epoch // lr_decay_epoch))

    if epoch % lr_decay_epoch == 0:
        print('LR is set to {}'.format(lr))

    for param_group in optimizer.param_groups:
        param_group['lr'] = lr

    return optimizer

model_ft = models.inception(pretrained=True)
num_ftrs = model_ft.fc.in_features
# we have 13classes in my task
model_ft.fc = nn.Linear(num_ftrs, 7)
model_ft.fc.weight.data.normal_(mean=0, std=0.01)

if use_gpu:
    model_ft = model_ft.cuda()

criterion = nn.CrossEntropyLoss()

# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)


###############
#Train Network#
##############
#model_ft.load_state_dict(torch.load('model/res10c20e.pkl'))
model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
                       num_epochs=1)

#############
#Save model#
############
path = 'model/res3410c10e.pkl'
#torch.save(model_ft.state_dict(), path)