resnet152训练_用fastai ResNet50训练CIFAR10，85%准确度

最新推荐文章于 2022-12-04 23:29:48 发布

原创最新推荐文章于 2022-12-04 23:29:48 发布 · 829 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#resnet152训练

本文介绍了如何使用fastai框架训练CIFAR10数据集，通过ResNet50模型达到了85%的验证集准确率。训练过程包括数据预处理、模型创建、训练、调整学习率和模型保存等步骤。展示了训练结果、混淆矩阵和预测错误最多的类别。

部署运行你感兴趣的模型镜像

Fastai是在pytorch上封装的深度学习框架，效果出众，以下是训练CIFAR10的过程。

导入库

from fastai import *

from fastai.vision import *

from fastai.callbacks import CSVLogger, SaveModelCallback

验证集上训练结果计算和显示

def show_result(learn):

# 得到验证集上的准确度

probs, val_labels = learn.get_preds(ds_type=DatasetType.Valid)

print('Accuracy', accuracy(probs, val_labels)),

print('Error Rate', error_rate(probs, val_labels))

训练结果混淆矩阵及预测错误最多的类型显示

def show_matrix(learn):

# 画训练结果的混合矩阵

interp = ClassificationInterpretation.from_learner(learn)

interp.confusion_matrix()

interp.plot_confusion_matrix(dpi=120)

# 显示判断错误最多的类型，min_val指定错误次数，默认1

# 打印顺序为actual, predicted, number of occurrences.

interp.most_confused(min_val=5)

# 模型预测最困难的9个样本显示

# 显示顺序为预测值、实际值、损失值、预测对的概率

interp.plot_top_losses(9, figsize=(10, 10))

下载数据集，因调用linux的tar进行解压，在windows下会出错，可手动解压，解压后的目录：

# 下载数据集

untar_data(URLs.CIFAR)

# 训练数据目录

path = Path(r'C:\Users\Administrator\.fastai\data\cifar10')

定义数据及数据在线增强方式

# 数据在线增强方式定义

tfms = get_transforms(do_flip=False)

data = (ImageList.from_folder(path) # Where to find the data? -> in path and its subfolders

.split_by_rand_pct() # How to split in train/valid? -> use the folders

.label_from_folder() # How to label? -> depending on the folder of the filenames

.add_test_folder() # Optionally add a test set (here default name is test)

.transform(tfms, size=(32, 32)) # Data augmentation? -> use tfms with a size of 164

.databunch(bs=128) # Finally? -> use the defaults for conversion to ImageDataBunch

.normalize(imagenet_stats))

查看数据

# 查看数据信息

data.classes, data.c, data

(['airplane',

'automobile',

'bird',

'cat',

'deer',

'dog',

'frog',

'horse',

'ship',

'truck'],

10,

ImageDataBunch;

Train: LabelList (39072 items)

x: ImageList

Image (3, 32, 32),Image (3, 32, 32),Image (3, 32, 32),Image (3, 32, 32),Image (3, 32, 32)

y: CategoryList

airplane,airplane,airplane,airplane,airplane

Path: C:\Users\Administrator\.fastai\data\cifar10;

Valid: LabelList (9767 items)

x: ImageList

Image (3, 32, 32),Image (3, 32, 32),Image (3, 32, 32),Image (3, 32, 32),Image (3, 32, 32)

y: CategoryList

airplane,deer,deer,deer,automobile

Path: C:\Users\Administrator\.fastai\data\cifar10;

Test: LabelList (10000 items)

x: ImageList

Image (3, 32, 32),Image (3, 32, 32),Image (3, 32, 32),Image (3, 32, 32),Image (3, 32, 32)

y: EmptyLabelList

,,,,

Path: C:\Users\Administrator\.fastai\data\cifar10)

创建训练器

# 创建learn

learn = cnn_learner(data, models.resnet50, metrics=[accuracy, error_rate], callback_fns=[ShowGraph, SaveModelCallback])

第一阶段训练

# 最佳学习率寻找

learn.lr_find(end_lr=1)

LR Finder is complete, type {learner_name}.recorder.plot() to see the graph.

# 画出学习率寻找曲线，给出建议学习率

learn.recorder.plot(suggestion=True)

# 根据学习率曲线得到max_lr，开始训练

learn.fit_one_cycle(cyc_len=15, max_lr=1.78e-2)

epochtrain_lossvalid_lossaccuracyerror_ratetime

1.074162

0.882136

0.709225

0.290775