.. _sec_kaggle_cifar10:
Kaggle における画像分類（CIFAR-10）
===================================
これまで、深層学習フレームワークの高レベル API
を用いて、画像データセットをテンソル形式で直接取得してきた。
しかし、独自の画像データセットは しばしば画像ファイルの形で提供される。
この節では、 生の画像ファイルから出発し、 それらを整理し、読み込み、
さらに段階的にテンソル形式へ変換していきる。
私たちは :numref:`sec_image_augmentation` で CIFAR-10
データセットを扱った。
これはコンピュータビジョンにおける重要なデータセットである。
この節では、 これまでの節で学んだ知識を CIFAR-10 画像分類の Kaggle
コンペティションで 実践する。 コンペティションの Web アドレスは
https://www.kaggle.com/c/cifar-10 です
:numref:`fig_kaggle_cifar10` はコンペティションの Web
ページにある情報を示している。 結果を提出するには、 Kaggle
アカウントを登録する必要がある。
.. _fig_kaggle_cifar10:
.. figure:: ../img/kaggle-cifar10.png
:width: 600px
CIFAR-10 画像分類コンペティションの Web
ページ情報。コンペティションのデータセットは “Data”
タブをクリックして取得できる。
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
import collections
from d2l import torch as d2l
import math
import torch
import torchvision
from torch import nn
import os
import pandas as pd
import shutil
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
import collections
from d2l import mxnet as d2l
import math
from mxnet import gluon, init, npx
from mxnet.gluon import nn
import os
import pandas as pd
import shutil
npx.set_np()
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
d2l.DATA_HUB['cifar10_tiny'] = (d2l.DATA_URL + 'kaggle_cifar10_tiny.zip',
'2068874e4b9a9f0fb07ebe0ad2b29754449ccacd')
# If you use the full dataset downloaded for the Kaggle competition, set
# `demo` to False
demo = True
if demo:
data_dir = d2l.download_extract('cifar10_tiny')
else:
data_dir = '../data/cifar-10/'
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
d2l.DATA_HUB['cifar10_tiny'] = (d2l.DATA_URL + 'kaggle_cifar10_tiny.zip',
'2068874e4b9a9f0fb07ebe0ad2b29754449ccacd')
# If you use the full dataset downloaded for the Kaggle competition, set
# `demo` to False
demo = True
if demo:
data_dir = d2l.download_extract('cifar10_tiny')
else:
data_dir = '../data/cifar-10/'
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
d2l.DATA_HUB['cifar10_tiny'] = (d2l.DATA_URL + 'kaggle_cifar10_tiny.zip',
'2068874e4b9a9f0fb07ebe0ad2b29754449ccacd')
# If you use the full dataset downloaded for the Kaggle competition, set
# `demo` to False
demo = True
if demo:
data_dir = d2l.download_extract('cifar10_tiny')
else:
data_dir = '../data/cifar-10/'
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
Downloading ../data/kaggle_cifar10_tiny.zip from http://d2l-data.s3-accelerate.amazonaws.com/kaggle_cifar10_tiny.zip...
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
d2l.DATA_HUB['cifar10_tiny'] = (d2l.DATA_URL + 'kaggle_cifar10_tiny.zip',
'2068874e4b9a9f0fb07ebe0ad2b29754449ccacd')
# If you use the full dataset downloaded for the Kaggle competition, set
# `demo` to False
demo = True
if demo:
data_dir = d2l.download_extract('cifar10_tiny')
else:
data_dir = '../data/cifar-10/'
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
Downloading ../data/kaggle_cifar10_tiny.zip from http://d2l-data.s3-accelerate.amazonaws.com/kaggle_cifar10_tiny.zip...
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def read_csv_labels(fname):
"""Read `fname` to return a filename to label dictionary."""
with open(fname, 'r') as f:
# Skip the file header line (column name)
lines = f.readlines()[1:]
tokens = [l.rstrip().split(',') for l in lines]
return dict(((name, label) for name, label in tokens))
labels = read_csv_labels(os.path.join(data_dir, 'trainLabels.csv'))
print('# training examples:', len(labels))
print('# classes:', len(set(labels.values())))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def read_csv_labels(fname):
"""Read `fname` to return a filename to label dictionary."""
with open(fname, 'r') as f:
# Skip the file header line (column name)
lines = f.readlines()[1:]
tokens = [l.rstrip().split(',') for l in lines]
return dict(((name, label) for name, label in tokens))
labels = read_csv_labels(os.path.join(data_dir, 'trainLabels.csv'))
print('# training examples:', len(labels))
print('# classes:', len(set(labels.values())))
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def read_csv_labels(fname):
"""Read `fname` to return a filename to label dictionary."""
with open(fname, 'r') as f:
# Skip the file header line (column name)
lines = f.readlines()[1:]
tokens = [l.rstrip().split(',') for l in lines]
return dict(((name, label) for name, label in tokens))
labels = read_csv_labels(os.path.join(data_dir, 'trainLabels.csv'))
print('# training examples:', len(labels))
print('# classes:', len(set(labels.values())))
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
# training examples: 1000
# classes: 10
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def read_csv_labels(fname):
"""Read `fname` to return a filename to label dictionary."""
with open(fname, 'r') as f:
# Skip the file header line (column name)
lines = f.readlines()[1:]
tokens = [l.rstrip().split(',') for l in lines]
return dict(((name, label) for name, label in tokens))
labels = read_csv_labels(os.path.join(data_dir, 'trainLabels.csv'))
print('# training examples:', len(labels))
print('# classes:', len(set(labels.values())))
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
# training examples: 1000
# classes: 10
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def copyfile(filename, target_dir):
"""Copy a file into a target directory."""
os.makedirs(target_dir, exist_ok=True)
shutil.copy(filename, target_dir)
#@save
def reorg_train_valid(data_dir, labels, valid_ratio):
"""Split the validation set out of the original training set."""
# The number of examples of the class that has the fewest examples in the
# training dataset
n = collections.Counter(labels.values()).most_common()[-1][1]
# The number of examples per class for the validation set
n_valid_per_label = max(1, math.floor(n * valid_ratio))
label_count = {}
for train_file in os.listdir(os.path.join(data_dir, 'train')):
label = labels[train_file.split('.')[0]]
fname = os.path.join(data_dir, 'train', train_file)
copyfile(fname, os.path.join(data_dir, 'train_valid_test',
'train_valid', label))
if label not in label_count or label_count[label] < n_valid_per_label:
copyfile(fname, os.path.join(data_dir, 'train_valid_test',
'valid', label))
label_count[label] = label_count.get(label, 0) + 1
else:
copyfile(fname, os.path.join(data_dir, 'train_valid_test',
'train', label))
return n_valid_per_label
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def copyfile(filename, target_dir):
"""Copy a file into a target directory."""
os.makedirs(target_dir, exist_ok=True)
shutil.copy(filename, target_dir)
#@save
def reorg_train_valid(data_dir, labels, valid_ratio):
"""Split the validation set out of the original training set."""
# The number of examples of the class that has the fewest examples in the
# training dataset
n = collections.Counter(labels.values()).most_common()[-1][1]
# The number of examples per class for the validation set
n_valid_per_label = max(1, math.floor(n * valid_ratio))
label_count = {}
for train_file in os.listdir(os.path.join(data_dir, 'train')):
label = labels[train_file.split('.')[0]]
fname = os.path.join(data_dir, 'train', train_file)
copyfile(fname, os.path.join(data_dir, 'train_valid_test',
'train_valid', label))
if label not in label_count or label_count[label] < n_valid_per_label:
copyfile(fname, os.path.join(data_dir, 'train_valid_test',
'valid', label))
label_count[label] = label_count.get(label, 0) + 1
else:
copyfile(fname, os.path.join(data_dir, 'train_valid_test',
'train', label))
return n_valid_per_label
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def copyfile(filename, target_dir):
"""Copy a file into a target directory."""
os.makedirs(target_dir, exist_ok=True)
shutil.copy(filename, target_dir)
#@save
def reorg_train_valid(data_dir, labels, valid_ratio):
"""Split the validation set out of the original training set."""
# The number of examples of the class that has the fewest examples in the
# training dataset
n = collections.Counter(labels.values()).most_common()[-1][1]
# The number of examples per class for the validation set
n_valid_per_label = max(1, math.floor(n * valid_ratio))
label_count = {}
for train_file in os.listdir(os.path.join(data_dir, 'train')):
label = labels[train_file.split('.')[0]]
fname = os.path.join(data_dir, 'train', train_file)
copyfile(fname, os.path.join(data_dir, 'train_valid_test',
'train_valid', label))
if label not in label_count or label_count[label] < n_valid_per_label:
copyfile(fname, os.path.join(data_dir, 'train_valid_test',
'valid', label))
label_count[label] = label_count.get(label, 0) + 1
else:
copyfile(fname, os.path.join(data_dir, 'train_valid_test',
'train', label))
return n_valid_per_label
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def copyfile(filename, target_dir):
"""Copy a file into a target directory."""
os.makedirs(target_dir, exist_ok=True)
shutil.copy(filename, target_dir)
#@save
def reorg_train_valid(data_dir, labels, valid_ratio):
"""Split the validation set out of the original training set."""
# The number of examples of the class that has the fewest examples in the
# training dataset
n = collections.Counter(labels.values()).most_common()[-1][1]
# The number of examples per class for the validation set
n_valid_per_label = max(1, math.floor(n * valid_ratio))
label_count = {}
for train_file in os.listdir(os.path.join(data_dir, 'train')):
label = labels[train_file.split('.')[0]]
fname = os.path.join(data_dir, 'train', train_file)
copyfile(fname, os.path.join(data_dir, 'train_valid_test',
'train_valid', label))
if label not in label_count or label_count[label] < n_valid_per_label:
copyfile(fname, os.path.join(data_dir, 'train_valid_test',
'valid', label))
label_count[label] = label_count.get(label, 0) + 1
else:
copyfile(fname, os.path.join(data_dir, 'train_valid_test',
'train', label))
return n_valid_per_label
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def reorg_test(data_dir):
"""Organize the testing set for data loading during prediction."""
for test_file in os.listdir(os.path.join(data_dir, 'test')):
copyfile(os.path.join(data_dir, 'test', test_file),
os.path.join(data_dir, 'train_valid_test', 'test',
'unknown'))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def reorg_test(data_dir):
"""Organize the testing set for data loading during prediction."""
for test_file in os.listdir(os.path.join(data_dir, 'test')):
copyfile(os.path.join(data_dir, 'test', test_file),
os.path.join(data_dir, 'train_valid_test', 'test',
'unknown'))
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def reorg_test(data_dir):
"""Organize the testing set for data loading during prediction."""
for test_file in os.listdir(os.path.join(data_dir, 'test')):
copyfile(os.path.join(data_dir, 'test', test_file),
os.path.join(data_dir, 'train_valid_test', 'test',
'unknown'))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def reorg_test(data_dir):
"""Organize the testing set for data loading during prediction."""
for test_file in os.listdir(os.path.join(data_dir, 'test')):
copyfile(os.path.join(data_dir, 'test', test_file),
os.path.join(data_dir, 'train_valid_test', 'test',
'unknown'))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def reorg_cifar10_data(data_dir, valid_ratio):
labels = read_csv_labels(os.path.join(data_dir, 'trainLabels.csv'))
reorg_train_valid(data_dir, labels, valid_ratio)
reorg_test(data_dir)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def reorg_cifar10_data(data_dir, valid_ratio):
labels = read_csv_labels(os.path.join(data_dir, 'trainLabels.csv'))
reorg_train_valid(data_dir, labels, valid_ratio)
reorg_test(data_dir)
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def reorg_cifar10_data(data_dir, valid_ratio):
labels = read_csv_labels(os.path.join(data_dir, 'trainLabels.csv'))
reorg_train_valid(data_dir, labels, valid_ratio)
reorg_test(data_dir)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def reorg_cifar10_data(data_dir, valid_ratio):
labels = read_csv_labels(os.path.join(data_dir, 'trainLabels.csv'))
reorg_train_valid(data_dir, labels, valid_ratio)
reorg_test(data_dir)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
batch_size = 32 if demo else 128
valid_ratio = 0.1
reorg_cifar10_data(data_dir, valid_ratio)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
batch_size = 32 if demo else 128
valid_ratio = 0.1
reorg_cifar10_data(data_dir, valid_ratio)
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
transform_train = torchvision.transforms.Compose([
# Scale the image up to a square of 40 pixels in both height and width
torchvision.transforms.Resize(40),
# Randomly crop a square image of 40 pixels in both height and width to
# produce a small square of 0.64 to 1 times the area of the original
# image, and then scale it to a square of 32 pixels in both height and
# width
torchvision.transforms.RandomResizedCrop(32, scale=(0.64, 1.0),
ratio=(1.0, 1.0)),
torchvision.transforms.RandomHorizontalFlip(),
torchvision.transforms.ToTensor(),
# Standardize each channel of the image
torchvision.transforms.Normalize([0.4914, 0.4822, 0.4465],
[0.2023, 0.1994, 0.2010])])
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
transform_train = gluon.data.vision.transforms.Compose([
# Scale the image up to a square of 40 pixels in both height and width
gluon.data.vision.transforms.Resize(40),
# Randomly crop a square image of 40 pixels in both height and width to
# produce a small square of 0.64 to 1 times the area of the original
# image, and then scale it to a square of 32 pixels in both height and
# width
gluon.data.vision.transforms.RandomResizedCrop(32, scale=(0.64, 1.0),
ratio=(1.0, 1.0)),
gluon.data.vision.transforms.RandomFlipLeftRight(),
gluon.data.vision.transforms.ToTensor(),
# Standardize each channel of the image
gluon.data.vision.transforms.Normalize([0.4914, 0.4822, 0.4465],
[0.2023, 0.1994, 0.2010])])
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
transform_test = torchvision.transforms.Compose([
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize([0.4914, 0.4822, 0.4465],
[0.2023, 0.1994, 0.2010])])
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
transform_test = gluon.data.vision.transforms.Compose([
gluon.data.vision.transforms.ToTensor(),
gluon.data.vision.transforms.Normalize([0.4914, 0.4822, 0.4465],
[0.2023, 0.1994, 0.2010])])
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
train_ds, train_valid_ds = [torchvision.datasets.ImageFolder(
os.path.join(data_dir, 'train_valid_test', folder),
transform=transform_train) for folder in ['train', 'train_valid']]
valid_ds, test_ds = [torchvision.datasets.ImageFolder(
os.path.join(data_dir, 'train_valid_test', folder),
transform=transform_test) for folder in ['valid', 'test']]
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
train_ds, valid_ds, train_valid_ds, test_ds = [
gluon.data.vision.ImageFolderDataset(
os.path.join(data_dir, 'train_valid_test', folder))
for folder in ['train', 'valid', 'train_valid', 'test']]
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
train_iter, train_valid_iter = [torch.utils.data.DataLoader(
dataset, batch_size, shuffle=True, drop_last=True)
for dataset in (train_ds, train_valid_ds)]
valid_iter = torch.utils.data.DataLoader(valid_ds, batch_size, shuffle=False,
drop_last=True)
test_iter = torch.utils.data.DataLoader(test_ds, batch_size, shuffle=False,
drop_last=False)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
train_iter, train_valid_iter = [gluon.data.DataLoader(
dataset.transform_first(transform_train), batch_size, shuffle=True,
last_batch='discard') for dataset in (train_ds, train_valid_ds)]
valid_iter = gluon.data.DataLoader(
valid_ds.transform_first(transform_test), batch_size, shuffle=False,
last_batch='discard')
test_iter = gluon.data.DataLoader(
test_ds.transform_first(transform_test), batch_size, shuffle=False,
last_batch='keep')
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def get_net():
num_classes = 10
net = d2l.resnet18(num_classes, 3)
return net
loss = nn.CrossEntropyLoss(reduction="none")
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
class Residual(nn.HybridBlock):
def __init__(self, num_channels, use_1x1conv=False, strides=1, **kwargs):
super(Residual, self).__init__(**kwargs)
self.conv1 = nn.Conv2D(num_channels, kernel_size=3, padding=1,
strides=strides)
self.conv2 = nn.Conv2D(num_channels, kernel_size=3, padding=1)
if use_1x1conv:
self.conv3 = nn.Conv2D(num_channels, kernel_size=1,
strides=strides)
else:
self.conv3 = None
self.bn1 = nn.BatchNorm()
self.bn2 = nn.BatchNorm()
def hybrid_forward(self, F, X):
Y = F.npx.relu(self.bn1(self.conv1(X)))
Y = self.bn2(self.conv2(Y))
if self.conv3:
X = self.conv3(X)
return F.npx.relu(Y + X)
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def train(net, train_iter, valid_iter, num_epochs, lr, wd, devices, lr_period,
lr_decay):
trainer = torch.optim.SGD(net.parameters(), lr=lr, momentum=0.9,
weight_decay=wd)
scheduler = torch.optim.lr_scheduler.StepLR(trainer, lr_period, lr_decay)
num_batches, timer = len(train_iter), d2l.Timer()
legend = ['train loss', 'train acc']
if valid_iter is not None:
legend.append('valid acc')
animator = d2l.Animator(xlabel='epoch', xlim=[1, num_epochs],
legend=legend)
net = nn.DataParallel(net, device_ids=devices).to(devices[0])
for epoch in range(num_epochs):
net.train()
metric = d2l.Accumulator(3)
for i, (features, labels) in enumerate(train_iter):
timer.start()
l, acc = d2l.train_batch_ch13(net, features, labels,
loss, trainer, devices)
metric.add(l, acc, labels.shape[0])
timer.stop()
if (i + 1) % (num_batches // 5) == 0 or i == num_batches - 1:
animator.add(epoch + (i + 1) / num_batches,
(metric[0] / metric[2], metric[1] / metric[2],
None))
if valid_iter is not None:
valid_acc = d2l.evaluate_accuracy_gpu(net, valid_iter)
animator.add(epoch + 1, (None, None, valid_acc))
scheduler.step()
measures = (f'train loss {metric[0] / metric[2]:.3f}, '
f'train acc {metric[1] / metric[2]:.3f}')
if valid_iter is not None:
measures += f', valid acc {valid_acc:.3f}'
print(measures + f'\n{metric[2] * num_epochs / timer.sum():.1f}'
f' examples/sec on {str(devices)}')
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def resnet18(num_classes):
net = nn.HybridSequential()
net.add(nn.Conv2D(64, kernel_size=3, strides=1, padding=1),
nn.BatchNorm(), nn.Activation('relu'))
def resnet_block(num_channels, num_residuals, first_block=False):
blk = nn.HybridSequential()
for i in range(num_residuals):
if i == 0 and not first_block:
blk.add(Residual(num_channels, use_1x1conv=True, strides=2))
else:
blk.add(Residual(num_channels))
return blk
net.add(resnet_block(64, 2, first_block=True),
resnet_block(128, 2),
resnet_block(256, 2),
resnet_block(512, 2))
net.add(nn.GlobalAvgPool2D(), nn.Dense(num_classes))
return net
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
devices, num_epochs, lr, wd = d2l.try_all_gpus(), 20, 2e-4, 5e-4
lr_period, lr_decay, net = 4, 0.9, get_net()
net(next(iter(train_iter))[0])
train(net, train_iter, valid_iter, num_epochs, lr, wd, devices, lr_period,
lr_decay)
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
train loss 0.771, train acc 0.740, valid acc 0.359
986.7 examples/sec on [device(type='cuda', index=0), device(type='cuda', index=1)]
.. figure:: output_kaggle-cifar10_c0cabc_150_1.svg
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def get_net(devices):
num_classes = 10
net = resnet18(num_classes)
net.initialize(ctx=devices, init=init.Xavier())
return net
loss = gluon.loss.SoftmaxCrossEntropyLoss()
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
net, preds = get_net(), []
net(next(iter(train_valid_iter))[0])
train(net, train_valid_iter, None, num_epochs, lr, wd, devices, lr_period,
lr_decay)
for X, _ in test_iter:
y_hat = net(X.to(devices[0]))
preds.extend(y_hat.argmax(dim=1).type(torch.int32).cpu().numpy())
sorted_ids = list(range(1, len(test_ds) + 1))
sorted_ids.sort(key=lambda x: str(x))
df = pd.DataFrame({'id': sorted_ids, 'label': preds})
df['label'] = df['label'].apply(lambda x: train_valid_ds.classes[x])
df.to_csv('submission.csv', index=False)
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
train loss 0.676, train acc 0.746
1136.6 examples/sec on [device(type='cuda', index=0), device(type='cuda', index=1)]
.. figure:: output_kaggle-cifar10_c0cabc_159_1.svg
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def train(net, train_iter, valid_iter, num_epochs, lr, wd, devices, lr_period,
lr_decay):
trainer = gluon.Trainer(net.collect_params(), 'sgd',
{'learning_rate': lr, 'momentum': 0.9, 'wd': wd})
num_batches, timer = len(train_iter), d2l.Timer()
legend = ['train loss', 'train acc']
if valid_iter is not None:
legend.append('valid acc')
animator = d2l.Animator(xlabel='epoch', xlim=[1, num_epochs],
legend=legend)
for epoch in range(num_epochs):
metric = d2l.Accumulator(3)
if epoch > 0 and epoch % lr_period == 0:
trainer.set_learning_rate(trainer.learning_rate * lr_decay)
for i, (features, labels) in enumerate(train_iter):
timer.start()
l, acc = d2l.train_batch_ch13(
net, features, labels.astype('float32'), loss, trainer,
devices, d2l.split_batch)
metric.add(l, acc, labels.shape[0])
timer.stop()
if (i + 1) % (num_batches // 5) == 0 or i == num_batches - 1:
animator.add(epoch + (i + 1) / num_batches,
(metric[0] / metric[2], metric[1] / metric[2],
None))
if valid_iter is not None:
valid_acc = d2l.evaluate_accuracy_gpus(net, valid_iter,
d2l.split_batch)
animator.add(epoch + 1, (None, None, valid_acc))
measures = (f'train loss {metric[0] / metric[2]:.3f}, '
f'train acc {metric[1] / metric[2]:.3f}')
if valid_iter is not None:
measures += f', valid acc {valid_acc:.3f}'
print(measures + f'\n{metric[2] * num_epochs / timer.sum():.1f}'
f' examples/sec on {str(devices)}')
.. raw:: html
.. raw:: html