文章目录
paddle2.0高层API实现ResNet50(十二生肖分类实战)
『深度学习7日打卡营·快速入门特辑』
零基础解锁深度学习神器飞桨框架高层API，七天时间助你掌握CV、NLP领域最火模型及应用。
- 掌握深度学习常用模型基础知识
- 熟练掌握一种国产开源深度学习框架
- 具备独立完成相关深度学习任务的能力
- 能用所学为AI加一份年味
① 问题定义
十二生肖分类的本质是图像分类任务，我们采用CNN网络结构进行相关实践。
② 数据准备
2.1 解压缩数据集
我们将网上获取的数据集以压缩包的方式上传到aistudio数据集中，并加载到我们的项目内。
在使用之前我们进行数据集压缩包的一个解压。
!unzip -q -o data/data68755/signs.zip
2.2 数据标注
我们先看一下解压缩后的数据集长成什么样子。
.
├── test
│ ├── dog
│ ├── dragon
│ ├── goat
│ ├── horse
│ ├── monkey
│ ├── ox
│ ├── pig
│ ├── rabbit
│ ├── ratt
│ ├── rooster
│ ├── snake
│ └── tiger
├── train
│ ├── dog
│ ├── dragon
│ ├── goat
│ ├── horse
│ ├── monkey
│ ├── ox
│ ├── pig
│ ├── rabbit
│ ├── ratt
│ ├── rooster
│ ├── snake
│ └── tiger
└── valid
├── dog
├── dragon
├── goat
├── horse
├── monkey
├── ox
├── pig
├── rabbit
├── ratt
├── rooster
├── snake
└── tiger
数据集分为train、valid、test三个文件夹，每个文件夹内包含12个分类文件夹，每个分类文件夹内是具体的样本图片。
我们对这些样本进行一个标注处理，最终生成train.txt/valid.txt/test.txt三个数据标注文件。
# %cd work
!ls
1512224.ipynb config.py data dataset.py __MACOSX __pycache__ signs work
import io
import os
from PIL import Image
from config import get
# 数据集根目录
DATA_ROOT = 'signs'
# 标签List
LABEL_MAP = get('LABEL_MAP')
# 标注生成函数
def generate_annotation(mode):
# 建立标注文件
with open('{}/{}.txt'.format(DATA_ROOT, mode), 'w') as f:
# 对应每个用途的数据文件夹，train/valid/test
train_dir = '{}/{}'.format(DATA_ROOT, mode)
# 遍历文件夹，获取里面的分类文件夹
for path in os.listdir(train_dir):
# 标签对应的数字索引，实际标注的时候直接使用数字索引
label_index = LABEL_MAP.index(path)
# 图像样本所在的路径
image_path = '{}/{}'.format(train_dir, path)
# 遍历所有图像
for image in os.listdir(image_path):
# 图像完整路径和名称
image_file = '{}/{}'.format(image_path, image)
try:
# 验证图片格式是否ok
with open(image_file, 'rb') as f_img:
image = Image.open(io.BytesIO(f_img.read()))
image.load()
if image.mode == 'RGB':
f.write('{}\t{}\n'.format(image_file, label_index))
except:
continue
generate_annotation('train') # 生成训练集标注文件
generate_annotation('valid') # 生成验证集标注文件
generate_annotation('test') # 生成测试集标注文件
2.3 数据集定义
接下来我们使用标注好的文件进行数据集类的定义，方便后续模型训练使用。
2.3.1 导入相关库
import paddle
import numpy as np
from config import get
paddle.__version__
'2.0.0'
2.3.2 导入数据集的定义实现
我们数据集的代码实现是在dataset.py中。
数据增强data_augumentation为：
self.transforms = T.Compose([
T.RandomResizedCrop(IMAGE_SIZE), # 随机裁剪大小
T.RandomHorizontalFlip(0.5), # 随机水平翻转
T.ToTensor(), # 数据的格式转换和标准化 HWC => CHW
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) # 图像归一化
])
from dataset import ZodiacDataset
2.3.3 实例化数据集类
根据所使用的数据集需求实例化数据集类，并查看总样本量。
train_dataset = ZodiacDataset(mode='train')
valid_dataset = ZodiacDataset(mode='valid')
print('训练数据集：{}张；验证数据集：{}张'.format(len(train_dataset), len(valid_dataset)))
训练数据集：7096张；验证数据集：639张
③ 模型选择和开发
3.1 网络构建
本次我们使用ResNet50网络来完成我们的案例实践。
1）ResNet系列网络
2）ResNet50结构
3）残差区块
4）ResNet其他版本
# 请补齐模型实例化代码
network = paddle.vision.models.resnet50(num_classes=get('num_classes'), pretrained=True)
100%|██████████| 151272/151272 [00:03<00:00, 41104.37it/s]
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py:1263: UserWarning: Skip loading for fc.weight. fc.weight receives a shape [2048, 1000], but the expected shape is [2048, 12].
warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py:1263: UserWarning: Skip loading for fc.bias. fc.bias receives a shape [1000], but the expected shape is [12].
warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
模型可视化
model = paddle.Model(network)
model.summary((-1, ) + tuple(get('image_shape')))
-------------------------------------------------------------------------------
Layer (type) Input Shape Output Shape Param #
===============================================================================
Conv2D-1 [[1, 3, 224, 224]] [1, 64, 112, 112] 9,408
BatchNorm2D-1 [[1, 64, 112, 112]] [1, 64, 112, 112] 256
ReLU-1 [[1, 64, 112, 112]] [1, 64, 112, 112] 0
MaxPool2D-1 [[1, 64, 112, 112]] [1, 64, 56, 56] 0
Conv2D-3 [[1, 64, 56, 56]] [1, 64, 56, 56] 4,096
BatchNorm2D-3 [[1, 64, 56, 56]] [1, 64, 56, 56] 256
ReLU-2 [[1, 256, 56, 56]] [1, 256, 56, 56] 0
Conv2D-4 [[1, 64, 56, 56]] [1, 64, 56, 56] 36,864
BatchNorm2D-4 [[1, 64, 56, 56]] [1, 64, 56, 56] 256
Conv2D-5 [[1, 64, 56, 56]] [1, 256, 56, 56] 16,384
BatchNorm2D-5 [[1, 256, 56, 56]] [1, 256, 56, 56] 1,024
Conv2D-2 [[1, 64, 56, 56]] [1, 256, 56, 56] 16,384
BatchNorm2D-2 [[1, 256, 56, 56]] [1, 256, 56, 56] 1,024
BottleneckBlock-1 [[1, 64, 56, 56]] [1, 256, 56, 56] 0
Conv2D-6 [[1, 256, 56, 56]] [1, 64, 56, 56] 16,384
BatchNorm2D-6 [[1, 64, 56, 56]] [1, 64, 56, 56] 256
ReLU-3 [[1, 256, 56, 56]] [1, 256, 56, 56] 0
Conv2D-7 [[1, 64, 56, 56]] [1, 64, 56, 56] 36,864
BatchNorm2D-7 [[1, 64, 56, 56]] [1, 64, 56, 56] 256
Conv2D-8 [[1, 64, 56, 56]] [1, 256, 56, 56] 16,384
BatchNorm2D-8 [[1, 256, 56, 56]] [1, 256, 56, 56] 1,024
BottleneckBlock-2 [[1, 256, 56, 56]] [1, 256, 56, 56] 0
Conv2D-9 [[1, 256, 56, 56]] [1, 64, 56, 56] 16,384
BatchNorm2D-9 [[1, 64, 56, 56]] [1, 64, 56, 56] 256
ReLU-4 [[1, 256, 56, 56]] [1, 256, 56, 56] 0
Conv2D-10 [[1, 64, 56, 56]] [1, 64, 56, 56] 36,864
BatchNorm2D-10 [[1, 64, 56, 56]] [1, 64, 56, 56] 256
Conv2D-11 [[1, 64, 56, 56]] [1, 256, 56, 56] 16,384
BatchNorm2D-11 [[1, 256, 56, 56]] [1, 256, 56, 56] 1,024
BottleneckBlock-3 [[1, 256, 56, 56]] [1, 256, 56, 56] 0
Conv2D-13 [[1, 256, 56, 56]] [1, 128, 56, 56] 32,768
BatchNorm2D-13 [[1, 128, 56, 56]] [1, 128, 56, 56] 512
ReLU-5 [[1, 512, 28, 28]] [1, 512, 28, 28] 0
Conv2D-14 [[1, 128, 56, 56]] [1, 128, 28, 28] 147,456
BatchNorm2D-14 [[1, 128, 28, 28]] [1, 128, 28, 28] 512
Conv2D-15 [[1, 128, 28, 28]] [1, 512, 28, 28] 65,536
BatchNorm2D-15 [[1, 512, 28, 28]] [1, 512, 28, 28] 2,048
Conv2D-12 [[1, 256, 56, 56]] [1, 512, 28, 28] 131,072
BatchNorm2D-12 [[1, 512, 28, 28]] [1, 512, 28, 28] 2,048
BottleneckBlock-4 [[1, 256, 56, 56]] [1, 512, 28, 28] 0
Conv2D-16 [[1, 512, 28, 28]] [1, 128, 28, 28] 65,536
BatchNorm2D-16 [[1, 128, 28, 28]] [1, 128, 28, 28] 512
ReLU-6 [[1, 512, 28, 28]] [1, 512, 28, 28] 0
Conv2D-17 
最低0.47元/天 解锁文章
956
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
