DenseNet121.py

#matplotlib inline
from __future__ import print_function, division

import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
from torch.autograd import Variable
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copy

plt.ion()   # interactive mode

# Data augmentation and normalization for training
# Just normalization for validation
data_transforms = {
    'train': transforms.Compose([
        transforms.CenterCrop(224),
        #transforms.RandomSizedCrop(224),
        #transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) # required by models
    ]),
    'val': transforms.Compose([
        transforms.Scale(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(), # convert to numpy arrays
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

# Still need to figure this out: how to do labeling?
# data_dir = 'hymenoptera_data'
# image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
#                                           data_transforms[x])
#                   for x in ['train', 'val']}
# dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4,
#                                              shuffle=True, num_workers=4)
#               for x in ['train', 'val']}
# dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}


BATCH_SIZE = 11
normalize = transforms.Normalize([0.485, 0.456, 0.406],
                                     [0.229, 0.224, 0.225])

test_dataset = ChestXrayDataSet(data_dir=DATA_DIR,
                                    image_list_file=TEST_IMAGE_LIST,
                                    transform=transforms.Compose([
                                        transforms.Resize(256),
                                        transforms.TenCrop(224),
                                        transforms.Lambda
                                        (lambda crops: torch.stack([transforms.ToTensor()(crop) for crop in crops])),
                                        transforms.Lambda
                                        (lambda crops: torch.stack([normalize(crop) for crop in crops]))
                                    ]))
test_loader = DataLoader(dataset=test_dataset, batch_size=BATCH_SIZE,
                         shuffle=False, num_workers=8, pin_memory=True)


class_names = image_datasets['train'].classes

use_gpu = torch.cuda.is_available()


# display the pictures
def imshow(inp, title=None):
    """Imshow for Tensor."""
    inp = inp.numpy().transpose((1, 2, 0))
    mean = np.array([0.485, 0.456, 0.406])
    std = np.array([0.229, 0.224, 0.225])
    inp = std * inp + mean
    inp = np.clip(inp, 0, 1)
    plt.imshow(inp)
    if title is not None:
        plt.title(title)
    plt.pause(5)  # pause a bit so that plots are updated


# Get a batch of training data
inputs, classes = next(iter(dataloaders['train']))

# Make a grid from batch
out = torchvision.utils.make_grid(inputs)

imshow(out, title=[class_names[x] for x in classes])


# a general model definition, scheduler: learning rate decay
def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
    since = time.time()

    best_model_wts = copy.deepcopy(model.state_dict())
    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', 'val']:
            if phase == 'train':
                scheduler.step()
                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 dataloaders[phase]:
                # get the inputs
                inputs, labels = data

                # wrap them in Variable
                if use_gpu:
                    inputs = Variable(inputs.cuda())
                    labels = 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] * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects / dataset_sizes[phase]

            print('{} Loss: {:.4f} Acc: {:.4f}'.format(
                phase, epoch_loss, epoch_acc))

            # deep copy the model
            if phase == 'val' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())

        print()

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

    # load best model weights
    model.load_state_dict(best_model_wts)
    return model




# a general visulization of train results
def visualize_model(model, num_images=6):
  images_so_far = 0
  fig = plt.figure()

  for i, data in enumerate(dataloaders['val']):
      inputs, labels = data
      if use_gpu:
          inputs, labels = Variable(inputs.cuda()), Variable(labels.cuda())
      else:
          inputs, labels = Variable(inputs), Variable(labels)

      outputs = model(inputs)
      _, preds = torch.max(outputs.data, 1)

      for j in range(inputs.size()[0]):
          images_so_far += 1
          ax = plt.subplot(num_images//2, 2, images_so_far)
          ax.axis('off')
          ax.set_title('predicted: {}'.format(class_names[preds[j]]))
          imshow(inputs.cpu().data[j])

          if images_so_far == num_images:
              return



# define the model, only train last layer
model_conv = torchvision.models.resnet18(pretrained=True) # Here the model can be changed
for param in model_conv.parameters():
    param.requires_grad = False

# Parameters of newly constructed modules have requires_grad=True by default
num_ftrs = model_conv.fc.in_features
model_conv.fc = nn.Linear(num_ftrs, 2)

if use_gpu:
    model_conv = model_conv.cuda()

criterion = nn.CrossEntropyLoss()

# Observe that only parameters of final layer are being optimized as
# opoosed to before.
optimizer_conv = optim.SGD(model_conv.fc.parameters(), lr=0.001, momentum=0.9)

# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)

# Train the model
model_conv = train_model(model_conv, criterion, optimizer_conv,
                         exp_lr_scheduler, num_epochs=25)

visualize_model(model_conv)

plt.ioff()
plt.show()