解压文件命令：
with zipfile.ZipFile(‘../data/kaggle_cifar10/‘ + fin, ‘r‘) as zin:
zin.extractall(‘../data/kaggle_cifar10/‘)
拷贝文件命令：
shutil.copy(原文件, 目标文件)
整理数据
我们有两个文件夹‘../data/kaggle_cifar10/train‘和‘../data/kaggle_cifar10/test‘，一个记录了文件名和类别的索引文件
我们的目的是在新的文件夹下形成拷贝，包含三个文件夹train_valid、train、valid，每个文件夹下存放不同的类别文件夹，里面存放对应类别的图片，
import os
import shutil
def reorg_cifar10_data(data_dir, label_file, train_dir, test_dir, input_dir, valid_ratio):
"""
处理之后，新建三个文件夹存放数据，train_valid、train、valid
data_dir:‘../data/kaggle_cifar10‘
label_file:‘trainLabels.csv‘
train_dir = ‘train‘
test_dir = ‘test‘
input_dir = ‘train_valid_test‘
valid_ratio = 0.1
"""
# 读取训练数据标签。
# 打开csv索引：‘../data/kaggle_cifar10/trainLabels.csv‘
with open(os.path.join(data_dir, label_file), ‘r‘) as f:
# 跳过文件头行（栏名称）。
lines = f.readlines()[1:]
tokens = [l.rstrip().split(‘,‘) for l in lines]
# {索引:标签}
idx_label = dict(((int(idx), label) for idx, label in tokens))
# 标签集合
labels = set(idx_label.values())
# 训练数据数目：‘../data/kaggle_cifar10/train‘
num_train = len(os.listdir(os.path.join(data_dir, train_dir)))
# train数目(对应valid)
num_train_tuning = int(num_train * (1 - valid_ratio))
# <---异常检测
assert 0 < num_train_tuning < num_train
# 每个label的train数据条目
num_train_tuning_per_label = num_train_tuning // len(labels)
label_count = dict()
def mkdir_if_not_exist(path):
if not os.path.exists(os.path.join(*path)):
os.makedirs(os.path.join(*path))
# 整理训练和验证集。
# 循环训练数据图片 ‘../data/kaggle_cifar10/train‘
for train_file in os.listdir(os.path.join(data_dir, train_dir)):
# 去掉扩展名作为索引
idx = int(train_file.split(‘.‘)[0])
# 索引到标签
label = idx_label[idx]
# ‘../data/kaggle_cifar10/train_valid_test/train_valid‘ + 标签名称
mkdir_if_not_exist([data_dir, input_dir, ‘train_valid‘, label])
# 拷贝图片
shutil.copy(os.path.join(data_dir, train_dir, train_file),
os.path.join(data_dir, input_dir, ‘train_valid‘, label))
# 保证train文件夹下的每类标签训练数目足够后，分给valid文件夹
if label not in label_count or label_count[label] < num_train_tuning_per_label:
# ‘../data/kaggle_cifar10/train_valid_test/train‘ + 标签名称
mkdir_if_not_exist([data_dir, input_dir, ‘train‘, label])
shutil.copy(os.path.join(data_dir, train_dir, train_file),
os.path.join(data_dir, input_dir, ‘train‘, label))
label_count[label] = label_count.get(label, 0) + 1
else:
mkdir_if_not_exist([data_dir, input_dir, ‘valid‘, label])
shutil.copy(os.path.join(data_dir, train_dir, train_file),
os.path.join(data_dir, input_dir, ‘valid‘, label))
# 整理测试集
# ‘../data/kaggle_cifar10/train_valid_test/test/unknown‘ 里面存放test图片
mkdir_if_not_exist([data_dir, input_dir, ‘test‘, ‘unknown‘])
for test_file in os.listdir(os.path.join(data_dir, test_dir)):
shutil.copy(os.path.join(data_dir, test_dir, test_file),
os.path.join(data_dir, input_dir, ‘test‘, ‘unknown‘))
train_dir = ‘train‘
test_dir = ‘test‘
batch_size = 128
data_dir = ‘../data/kaggle_cifar10‘
label_file = ‘trainLabels.csv‘
input_dir = ‘train_valid_test‘
valid_ratio = 0.1
reorg_cifar10_data(data_dir, label_file, train_dir, test_dir, input_dir, valid_ratio)
预处理
# 预处理
from mxnet import autograd
from mxnet import gluon
from mxnet import init
from mxnet import nd
from mxnet.gluon.data import vision
from mxnet.gluon.data.vision import transforms
import numpy as np
transform_train = transforms.Compose([
# transforms.CenterCrop(32)
# transforms.RandomFlipTopBottom(),
# transforms.RandomColorJitter(brightness=0.0, contrast=0.0, saturation=0.0, hue=0.0),
# transforms.RandomLighting(0.0),
# transforms.Cast(‘float32‘),
# transforms.Resize(32),
# 随机按照scale和ratio裁剪，并放缩为32x32的正方形
transforms.RandomResizedCrop(32, scale=(0.08, 1.0), ratio=(3.0/4.0, 4.0/3.0)),
# 随机左右翻转图片
transforms.RandomFlipLeftRight(),
# 将图片像素值缩小到(0,1)内，并将数据格式从"高*宽*通道"改为"通道*高*宽"
transforms.ToTensor(),
# 对图片的每个通道做标准化
transforms.Normalize([0.4914, 0.4822, 0.4465], [0.2023, 0.1994, 0.2010])
])
# 测试时，无需对图像做标准化以外的增强数据处理。
transform_test = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize([0.4914, 0.4822, 0.4465], [0.2023, 0.1994, 0.2010])
])
# ‘../data/kaggle_cifar10、train_valid_test/‘
input_str = data_dir + ‘/‘ + input_dir + ‘/‘
# 读取原始图像文件。flag=1说明输入图像有三个通道（彩色）。
train_ds = vision.ImageFolderDataset(input_str + ‘train‘, flag=1)
valid_ds = vision.ImageFolderDataset(input_str + ‘valid‘, flag=1)
train_valid_ds = vision.ImageFolderDataset(input_str + ‘train_valid‘, flag=1)
test_ds = vision.ImageFolderDataset(input_str + ‘test‘, flag=1)
loader = gluon.data.DataLoader
train_data = loader(train_ds.transform_first(transform_train),
batch_size, shuffle=True, last_batch=‘keep‘)
valid_data = loader(valid_ds.transform_first(transform_test),
batch_size, shuffle=True, last_batch=‘keep‘)
train_valid_data = loader(train_valid_ds.transform_first(transform_train),
batch_size, shuffle=True, last_batch=‘keep‘)
test_data = loader(test_ds.transform_first(transform_test),
batch_size, shuffle=False, last_batch=‘keep‘)
# 交叉熵损失函数。
softmax_cross_entropy = gluon.loss.SoftmaxCrossEntropyLoss()
mxnet.gluon.vision.ImageFolderDatasetmxnet.gluon.data.DataLoader
数据的预处理放在DataLoader中，这样后面可以调用ImageFolderDataset，获取原始图片集
至此，数据准备完成。
模型定义
from mxnet.gluon import nn
from mxnet import nd
class Residual(nn.HybridBlock):
def __init__(self, channels, same_shape=True, **kwargs):
super(Residual, self).__init__(**kwargs)
self.same_shape = same_shape
with self.name_scope():
strides = 1 if same_shape else 2
self.conv1 = nn.Conv2D(channels, kernel_size=3, padding=1,
strides=strides)
self.bn1 = nn.BatchNorm()
self.conv2 = nn.Conv2D(channels, kernel_size=3, padding=1)
self.bn2 = nn.BatchNorm()
if not same_shape:
self.conv3 = nn.Conv2D(channels, kernel_size=1,
strides=strides)
def hybrid_forward(self, F, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.bn2(self.conv2(out))
if not self.same_shape:
x = self.conv3(x)
return F.relu(out + x)
class ResNet(nn.HybridBlock):
def __init__(self, num_classes, verbose=False, **kwargs):
super(ResNet, self).__init__(**kwargs)
self.verbose = verbose
with self.name_scope():
net = self.net = nn.HybridSequential()
# 模块1
net.add(nn.Conv2D(channels=32, kernel_size=3, strides=1, padding=1))
net.add(nn.BatchNorm())
net.add(nn.Activation(activation=‘relu‘))
# 模块2
for _ in range(3):
net.add(Residual(channels=32))
# 模块3
net.add(Residual(channels=64, same_shape=False))
for _ in range(2):
net.add(Residual(channels=64))
# 模块4
net.add(Residual(channels=128, same_shape=False))
for _ in range(2):
net.add(Residual(channels=128))
# 模块5
net.add(nn.AvgPool2D(pool_size=8))
net.add(nn.Flatten())
net.add(nn.Dense(num_classes))
def hybrid_forward(self, F, x):
out = x
for i, b in enumerate(self.net):
out = b(out)
if self.verbose:
print(‘Block %d output: %s‘%(i+1, out.shape))
return out
def get_net(ctx):
num_outputs = 10
net = ResNet(num_outputs)
net.initialize(ctx=ctx, init=init.Xavier())
return net
训练
gb.accuracy(output, label)
trainer.set_learning_rate(trainer.learning_rate * lr_decay)
gb.evaluate_accuracy(valid_data, net, ctx)
import datetime
import sys
sys.path.append(‘..‘)
import gluonbook as gb
def train(net, train_data, valid_data, num_epochs, lr, wd, ctx, lr_period, lr_decay):
trainer = gluon.Trainer(
net.collect_params(), ‘sgd‘, {‘learning_rate‘: lr, ‘momentum‘: 0.9, ‘wd‘: wd})
prev_time = datetime.datetime.now()
for epoch in range(num_epochs):
train_loss = 0.0
train_acc = 0.0
if epoch > 0 and epoch % lr_period == 0:
trainer.set_learning_rate(trainer.learning_rate * lr_decay)
for data, label in train_data:
label = label.astype(‘float32‘).as_in_context(ctx)
with autograd.record():
output = net(data.as_in_context(ctx))
loss = softmax_cross_entropy(output, label)
loss.backward()
trainer.step(batch_size)
train_loss += nd.mean(loss).asscalar()
train_acc += gb.accuracy(output, label)
cur_time = datetime.datetime.now()
h, remainder = divmod((cur_time - prev_time).seconds, 3600)
m, s = divmod(remainder, 60)
time_str = "Time %02d:%02d:%02d" % (h, m, s)
if valid_data is not None:
valid_acc = gb.evaluate_accuracy(valid_data, net, ctx)
epoch_str = ("Epoch %d. Loss: %f, Train acc %f, Valid acc %f, "
% (epoch, train_loss / len(train_data),
train_acc / len(train_data), valid_acc))
else:
epoch_str = ("Epoch %d. Loss: %f, Train acc %f, "
% (epoch, train_loss / len(train_data),
train_acc / len(train_data)))
prev_time = cur_time
print(epoch_str + time_str + ‘, lr ‘ + str(trainer.learning_rate))
实际训练起来，
ctx = gb.try_gpu()
num_epochs = 1
learning_rate = 0.1
weight_decay = 5e-4
lr_period = 80
lr_decay = 0.1
net = get_net(ctx)
net.hybridize()
train(net, train_data, valid_data, num_epochs, learning_rate,
weight_decay, ctx, lr_period, lr_decay)
预测
import numpy as np
import pandas as pd
# 训练
net = get_net(ctx)
net.hybridize()
train(net, train_valid_data, None, num_epochs, learning_rate,
weight_decay, ctx, lr_period, lr_decay)
# 预测
preds = []
for data, label in test_data:
output = net(data.as_in_context(ctx))
preds.extend(output.argmax(axis=1).astype(int).asnumpy())
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.synsets[x])
df.to_csv(‘submission.csv‘, index=False)
原文地址：https://www.cnblogs.com/hellcat/p/9098168.html
时间： 2024-11-06 03:44:56