Accompanying code examples of the book "Introduction to Artificial Neural Networks and Deep Learning: A Practical Guide with Applications in Python" by Sebastian Raschka. All code examples are released under the MIT license. If you find this content useful, please consider supporting the work by buying a copy of the book.
Other code examples and content are available on GitHub. The PDF and ebook versions of the book are available through Leanpub.
%load_ext watermark
%watermark -a 'Sebastian Raschka' -v -p torch
Sebastian Raschka CPython 3.7.1 IPython 7.2.0 torch 1.0.0
The network in this notebook is an implementation of the ResNet-34 [1] architecture on the CelebA face dataset [2] to train a gender classifier.
References
[1] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778). (CVPR Link)
[2] Zhang, K., Tan, L., Li, Z., & Qiao, Y. (2016). Gender and smile classification using deep convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 34-38).
Note that the CelebA images are 218 x 178, not 256 x 256. We resize to 128x128
The following figure illustrates residual blocks with skip connections such that the input passed via the shortcut matches the dimensions of the main path's output, which allows the network to learn identity functions.
The ResNet-34 architecture actually uses residual blocks with skip connections such that the input passed via the shortcut matches is resized to dimensions of the main path's output. Such a residual block is illustrated below:
For a more detailed explanation see the other notebook, resnet-ex-1.ipynb.
import os
import time
import numpy as np
import pandas as pd
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision import transforms
import matplotlib.pyplot as plt
from PIL import Image
if torch.cuda.is_available():
torch.backends.cudnn.deterministic = True
##########################
### SETTINGS
##########################
# Hyperparameters
RANDOM_SEED = 1
LEARNING_RATE = 0.001
NUM_EPOCHS = 10
# Architecture
NUM_FEATURES = 128*128
NUM_CLASSES = 2
BATCH_SIZE = 256*torch.cuda.device_count()
DEVICE = 'cuda:0' # default GPU device
GRAYSCALE = False
Note that the ~200,000 CelebA face image dataset is relatively large (~1.3 Gb). The download link provided below was provided by the author on the official CelebA website at http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html.
Download and unzip the file img_align_celeba.zip
, which contains the images in jpeg format.
Download the list_attr_celeba.txt
file, which contains the class labels
Download the list_eval_partition.txt
file, which contains training/validation/test partitioning info
df1 = pd.read_csv('list_attr_celeba.txt', sep="\s+", skiprows=1, usecols=['Male'])
# Make 0 (female) & 1 (male) labels instead of -1 & 1
df1.loc[df1['Male'] == -1, 'Male'] = 0
df1.head()
Male | |
---|---|
000001.jpg | 0 |
000002.jpg | 0 |
000003.jpg | 1 |
000004.jpg | 0 |
000005.jpg | 0 |
df2 = pd.read_csv('list_eval_partition.txt', sep="\s+", skiprows=0, header=None)
df2.columns = ['Filename', 'Partition']
df2 = df2.set_index('Filename')
df2.head()
Partition | |
---|---|
Filename | |
000001.jpg | 0 |
000002.jpg | 0 |
000003.jpg | 0 |
000004.jpg | 0 |
000005.jpg | 0 |
df3 = df1.merge(df2, left_index=True, right_index=True)
df3.head()
Male | Partition | |
---|---|---|
000001.jpg | 0 | 0 |
000002.jpg | 0 | 0 |
000003.jpg | 1 | 0 |
000004.jpg | 0 | 0 |
000005.jpg | 0 | 0 |
df3.to_csv('celeba-gender-partitions.csv')
df4 = pd.read_csv('celeba-gender-partitions.csv', index_col=0)
df4.head()
Male | Partition | |
---|---|---|
000001.jpg | 0 | 0 |
000002.jpg | 0 | 0 |
000003.jpg | 1 | 0 |
000004.jpg | 0 | 0 |
000005.jpg | 0 | 0 |
df4.loc[df4['Partition'] == 0].to_csv('celeba-gender-train.csv')
df4.loc[df4['Partition'] == 1].to_csv('celeba-gender-valid.csv')
df4.loc[df4['Partition'] == 2].to_csv('celeba-gender-test.csv')
img = Image.open('img_align_celeba/000001.jpg')
print(np.asarray(img, dtype=np.uint8).shape)
plt.imshow(img);
(218, 178, 3)
class CelebaDataset(Dataset):
"""Custom Dataset for loading CelebA face images"""
def __init__(self, csv_path, img_dir, transform=None):
df = pd.read_csv(csv_path, index_col=0)
self.img_dir = img_dir
self.csv_path = csv_path
self.img_names = df.index.values
self.y = df['Male'].values
self.transform = transform
def __getitem__(self, index):
img = Image.open(os.path.join(self.img_dir,
self.img_names[index]))
if self.transform is not None:
img = self.transform(img)
label = self.y[index]
return img, label
def __len__(self):
return self.y.shape[0]
# Note that transforms.ToTensor()
# already divides pixels by 255. internally
custom_transform = transforms.Compose([transforms.CenterCrop((178, 178)),
transforms.Resize((128, 128)),
#transforms.Grayscale(),
#transforms.Lambda(lambda x: x/255.),
transforms.ToTensor()])
train_dataset = CelebaDataset(csv_path='celeba-gender-train.csv',
img_dir='img_align_celeba/',
transform=custom_transform)
valid_dataset = CelebaDataset(csv_path='celeba-gender-valid.csv',
img_dir='img_align_celeba/',
transform=custom_transform)
test_dataset = CelebaDataset(csv_path='celeba-gender-test.csv',
img_dir='img_align_celeba/',
transform=custom_transform)
train_loader = DataLoader(dataset=train_dataset,
batch_size=BATCH_SIZE,
shuffle=True,
num_workers=4)
valid_loader = DataLoader(dataset=valid_dataset,
batch_size=BATCH_SIZE,
shuffle=False,
num_workers=4)
test_loader = DataLoader(dataset=test_dataset,
batch_size=BATCH_SIZE,
shuffle=False,
num_workers=4)
torch.manual_seed(0)
for epoch in range(2):
for batch_idx, (x, y) in enumerate(train_loader):
print('Epoch:', epoch+1, end='')
print(' | Batch index:', batch_idx, end='')
print(' | Batch size:', y.size()[0])
x = x.to(DEVICE)
y = y.to(DEVICE)
time.sleep(1)
break
Epoch: 1 | Batch index: 0 | Batch size: 1024 Epoch: 2 | Batch index: 0 | Batch size: 1024
The following code cell that implements the ResNet-34 architecture is a derivative of the code provided at https://pytorch.org/docs/0.4.0/_modules/torchvision/models/resnet.html.
##########################
### MODEL
##########################
def conv3x3(in_planes, out_planes, stride=1):
"""3x3 convolution with padding"""
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=1, bias=False)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, layers, num_classes, grayscale):
self.inplanes = 64
if grayscale:
in_dim = 1
else:
in_dim = 3
super(ResNet, self).__init__()
self.conv1 = nn.Conv2d(in_dim, 64, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
self.avgpool = nn.AvgPool2d(7, stride=1, padding=2)
self.fc = nn.Linear(2048 * block.expansion, num_classes)
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, (2. / n)**.5)
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
logits = self.fc(x)
probas = F.softmax(logits, dim=1)
return logits, probas
def resnet34(num_classes, grayscale):
"""Constructs a ResNet-34 model."""
model = ResNet(block=BasicBlock,
layers=[3, 4, 6, 3],
num_classes=NUM_CLASSES,
grayscale=grayscale)
return model
torch.manual_seed(RANDOM_SEED)
##########################
### COST AND OPTIMIZER
##########################
model = resnet34(NUM_CLASSES, GRAYSCALE)
#### DATA PARALLEL START ####
if torch.cuda.device_count() > 1:
print("Using", torch.cuda.device_count(), "GPUs")
model = nn.DataParallel(model)
#### DATA PARALLEL END ####
model.to(DEVICE)
cost_fn = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=LEARNING_RATE)
Using 4 GPUs
def compute_accuracy(model, data_loader, device):
correct_pred, num_examples = 0, 0
for i, (features, targets) in enumerate(data_loader):
features = features.to(device)
targets = targets.to(device)
logits, probas = model(features)
_, predicted_labels = torch.max(probas, 1)
num_examples += targets.size(0)
correct_pred += (predicted_labels == targets).sum()
return correct_pred.float()/num_examples * 100
start_time = time.time()
for epoch in range(NUM_EPOCHS):
model.train()
for batch_idx, (features, targets) in enumerate(train_loader):
features = features.to(DEVICE)
targets = targets.to(DEVICE)
### FORWARD AND BACK PROP
logits, probas = model(features)
cost = cost_fn(logits, targets)
optimizer.zero_grad()
cost.backward()
### UPDATE MODEL PARAMETERS
optimizer.step()
### LOGGING
if not batch_idx % 50:
print ('Epoch: %03d/%03d | Batch %04d/%04d | Cost: %.4f'
%(epoch+1, NUM_EPOCHS, batch_idx,
len(train_loader), cost))
model.eval()
with torch.set_grad_enabled(False): # save memory during inference
print('Epoch: %03d/%03d | Train: %.3f%% | Valid: %.3f%%' % (
epoch+1, NUM_EPOCHS,
compute_accuracy(model, train_loader, device=DEVICE),
compute_accuracy(model, valid_loader, device=DEVICE)))
print('Time elapsed: %.2f min' % ((time.time() - start_time)/60))
print('Total Training Time: %.2f min' % ((time.time() - start_time)/60))
Epoch: 001/010 | Batch 0000/0159 | Cost: 0.6839 Epoch: 001/010 | Batch 0050/0159 | Cost: 0.1407 Epoch: 001/010 | Batch 0100/0159 | Cost: 0.0978 Epoch: 001/010 | Batch 0150/0159 | Cost: 0.1101 Epoch: 001/010 | Train: 96.633% | Valid: 96.960% Time elapsed: 2.80 min Epoch: 002/010 | Batch 0000/0159 | Cost: 0.0683 Epoch: 002/010 | Batch 0050/0159 | Cost: 0.0705 Epoch: 002/010 | Batch 0100/0159 | Cost: 0.0884 Epoch: 002/010 | Batch 0150/0159 | Cost: 0.0798 Epoch: 002/010 | Train: 97.172% | Valid: 97.242% Time elapsed: 5.45 min Epoch: 003/010 | Batch 0000/0159 | Cost: 0.0563 Epoch: 003/010 | Batch 0050/0159 | Cost: 0.0755 Epoch: 003/010 | Batch 0100/0159 | Cost: 0.0648 Epoch: 003/010 | Batch 0150/0159 | Cost: 0.0443 Epoch: 003/010 | Train: 97.288% | Valid: 97.227% Time elapsed: 8.12 min Epoch: 004/010 | Batch 0000/0159 | Cost: 0.0342 Epoch: 004/010 | Batch 0050/0159 | Cost: 0.0599 Epoch: 004/010 | Batch 0100/0159 | Cost: 0.0639 Epoch: 004/010 | Batch 0150/0159 | Cost: 0.0566 Epoch: 004/010 | Train: 98.357% | Valid: 97.569% Time elapsed: 10.75 min Epoch: 005/010 | Batch 0000/0159 | Cost: 0.0293 Epoch: 005/010 | Batch 0050/0159 | Cost: 0.0469 Epoch: 005/010 | Batch 0100/0159 | Cost: 0.0486 Epoch: 005/010 | Batch 0150/0159 | Cost: 0.0365 Epoch: 005/010 | Train: 99.018% | Valid: 98.022% Time elapsed: 13.40 min Epoch: 006/010 | Batch 0000/0159 | Cost: 0.0246 Epoch: 006/010 | Batch 0050/0159 | Cost: 0.0362 Epoch: 006/010 | Batch 0100/0159 | Cost: 0.0323 Epoch: 006/010 | Batch 0150/0159 | Cost: 0.0385 Epoch: 006/010 | Train: 98.730% | Valid: 97.770% Time elapsed: 16.07 min Epoch: 007/010 | Batch 0000/0159 | Cost: 0.0220 Epoch: 007/010 | Batch 0050/0159 | Cost: 0.0279 Epoch: 007/010 | Batch 0100/0159 | Cost: 0.0452 Epoch: 007/010 | Batch 0150/0159 | Cost: 0.0219 Epoch: 007/010 | Train: 99.188% | Valid: 97.926% Time elapsed: 18.76 min Epoch: 008/010 | Batch 0000/0159 | Cost: 0.0168 Epoch: 008/010 | Batch 0050/0159 | Cost: 0.0163 Epoch: 008/010 | Batch 0100/0159 | Cost: 0.0276 Epoch: 008/010 | Batch 0150/0159 | Cost: 0.0455 Epoch: 008/010 | Train: 99.456% | Valid: 98.072% Time elapsed: 21.43 min Epoch: 009/010 | Batch 0000/0159 | Cost: 0.0104 Epoch: 009/010 | Batch 0050/0159 | Cost: 0.0184 Epoch: 009/010 | Batch 0100/0159 | Cost: 0.0105 Epoch: 009/010 | Batch 0150/0159 | Cost: 0.0305 Epoch: 009/010 | Train: 98.984% | Valid: 97.866% Time elapsed: 24.11 min Epoch: 010/010 | Batch 0000/0159 | Cost: 0.0106 Epoch: 010/010 | Batch 0050/0159 | Cost: 0.0228 Epoch: 010/010 | Batch 0100/0159 | Cost: 0.0123 Epoch: 010/010 | Batch 0150/0159 | Cost: 0.0137 Epoch: 010/010 | Train: 99.512% | Valid: 97.836% Time elapsed: 26.75 min Total Training Time: 26.75 min
with torch.set_grad_enabled(False): # save memory during inference
print('Test accuracy: %.2f%%' % (compute_accuracy(model, test_loader, device=DEVICE)))
Test accuracy: 97.56%
for batch_idx, (features, targets) in enumerate(test_loader):
features = features
targets = targets
break
plt.imshow(np.transpose(features[0], (1, 2, 0)))
<matplotlib.image.AxesImage at 0x7f9e6145d278>
model.eval()
logits, probas = model(features.to(DEVICE)[0, None])
print('Probability Female %.2f%%' % (probas[0][0]*100))
Probability Female 100.00%
%watermark -iv
numpy 1.15.4 pandas 0.23.4 torch 1.0.0 PIL.Image 5.3.0