In [4]:
%matplotlib inline
Author: Sasank Chilamkurthy <https://chsasank.github.io>_
In this tutorial, you will learn how to train your network using
transfer learning. You can read more about the transfer learning at cs231n
notes <http://cs231n.github.io/transfer-learning/>__
Quoting this notes,
In practice, very few people train an entire Convolutional Network
from scratch (with random initialization), because it is relatively
rare to have a dataset of sufficient size. Instead, it is common to
pretrain a ConvNet on a very large dataset (e.g. ImageNet, which
contains 1.2 million images with 1000 categories), and then use the
ConvNet either as an initialization or a fixed feature extractor for
the task of interest.
These two major transfer learning scenarios looks as follows:
In [5]:
# License: BSD
# Author: Sasank Chilamkurthy
from __future__ import print_function, division
import torch
import torch.nn as nn
import torch.optim as optim
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 copy
import os
plt.ion() # interactive mode
We will use torchvision and torch.utils.data packages for loading the data.
The problem we're going to solve today is to train a model to classify ants and bees. We have about 120 training images each for ants and bees. There are 75 validation images for each class. Usually, this is a very small dataset to generalize upon, if trained from scratch. Since we are using transfer learning, we should be able to generalize reasonably well.
This dataset is a very small subset of imagenet.
.. Note ::
Download the data from
here <https://download.pytorch.org/tutorial/hymenoptera_data.zip>_
and extract it to the current directory.
In [7]:
# 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])
]),
'val': 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 = 'hymenoptera_data'
dsets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])
for x in ['train', 'val']}
dset_loaders = {x: torch.utils.data.DataLoader(dsets[x], batch_size=4,
shuffle=True, num_workers=4)
for x in ['train', 'val']}
dset_sizes = {x: len(dsets[x]) for x in ['train', 'val']}
dset_classes = dsets['train'].classes
use_gpu = torch.cuda.is_available()
Visualize a few images ^^^^^^^^^^^^^^^^^^^^^^ Let's visualize a few training images so as to understand the data augmentations.
In [8]:
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
plt.imshow(inp)
if title is not None:
plt.title(title)
plt.pause(0.001) # pause a bit so that plots are updated
# Get a batch of training data
inputs, classes = next(iter(dset_loaders['train']))
# Make a grid from batch
out = torchvision.utils.make_grid(inputs)
imshow(out, title=[dset_classes[x] for x in classes])
Now, let's write a general function to train a model. Here, we will illustrate:
In the following, parameter lr_scheduler(optimizer, epoch)
is a function which modifies optimizer so that the learning
rate is changed according to desired schedule.
In [18]:
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', 'val']:
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
print(str(inputs), str(labels))
# 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]
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 = 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 val Acc: {:4f}'.format(best_acc))
return best_model
Learning rate scheduler ^^^^^^^^^^^^^^^^^^^^^^^ Let's create our learning rate scheduler. We will exponentially decrease the learning rate once every few epochs.
In [10]:
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
Visualizing the model predictions ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Generic function to display predictions for a few images
In [11]:
def visualize_model(model, num_images=6):
images_so_far = 0
fig = plt.figure()
for i, data in enumerate(dset_loaders['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(dset_classes[labels.data[j]]))
imshow(inputs.cpu().data[j])
if images_so_far == num_images:
return
In [12]:
model_ft = models.resnet18(pretrained=True)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 2)
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 and evaluate ^^^^^^^^^^^^^^^^^^
It should take around 15-25 min on CPU. On GPU though, it takes less than a minute.
In [19]:
model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
num_epochs=25)