2.fastAI进阶(1)(DataLoader)

最新推荐文章于 2024-09-10 21:14:51 发布

qwrdxer

最新推荐文章于 2024-09-10 21:14:51 发布

阅读量101

点赞数

分类专栏： fastai 文章标签： pytorch 深度学习神经网络

本文链接：https://blog.csdn.net/qwrdxer/article/details/132734711

版权

fastai 专栏收录该内容

3 篇文章 0 订阅

订阅专栏

FASTAI

1.进阶dataloader

1.1 示例

pets = DataBlock(blocks=(ImageBlock, CategoryBlock), #用到的类型,图片、分类
                 get_items=get_image_files, #获取x的方式
                 splitter=RandomSplitter(), #分割方式
                 get_y=using_attr(RegexLabeller(r'(.+)_\d+.jpg$'), 'name'),	#获取y标签的方法
                 item_tfms=Resize(460),
                 batch_tfms=aug_transforms(size=224))

A datablock is built by giving the fastai library a bunch of informations:

the types used, through an argument called blocks: here we have images and categories, so we pass ImageBlock and CategoryBlock.
how to get the raw items, here our function get_image_files.
how to label those items, here with the same regular expression as before.
how to split those items, here with a random splitter.
the item_tfms and batch_tfms like before.

1.2 通过csv格式文件进行标签

例子使用了多分类的数据集，标签在train.csv中

在这里插入图片描述

dls = ImageDataLoaders.from_df(df, path, folder=‘train’, valid_col=‘is_valid’, label_delim=' ', item_tfms=Resize(460), batch_tfms=aug_transforms(size=224))

使用from_df函数来加载csv的数据集。
path为基目录，folder 用于在path和filename之间增加路径path/folder/filename
label_delim 指定使用空格作为标签分类条件
文件名、标签默认为第一二列所以这里不需要指定。

进阶：

pascal = DataBlock(blocks=(ImageBlock, MultiCategoryBlock),
                   splitter=ColSplitter('is_valid'),
                   get_x=ColReader('fname', pref=str(path/'train') + os.path.sep),
                   get_y=ColReader('labels', label_delim=' '),
                   item_tfms = Resize(460),
                   batch_tfms=aug_transforms(size=224))

多分类使用F1 Score来评价模型的好坏

f1_macro = F1ScoreMulti(thresh=0.5, average='macro')
f1_macro.name = 'F1(macro)'
f1_samples = F1ScoreMulti(thresh=0.5, average='samples')
f1_samples.name = 'F1(samples)'
learn = vision_learner(dls, resnet50, metrics=[partial(accuracy_multi, thresh=0.5), f1_macro, f1_samples])