相关文章:
【深度学习项目一】全连接神经网络实现mnist数字识别
【深度学习项目二】卷积神经网络LeNet实现minst数字识别
【深度学习项目三】ResNet50多分类任务【十二生肖分类】
『深度学习项目四』基于ResNet101人脸特征点检测
项目链接:https://aistudio.baidu.com/aistudio/projectdetail/1930877
贡献:
全连接层对输入输出大小有限制,用池化层代替没有约束。
按照12生肖在网上”下载的12种动物照片
训练样本量| 7,096张
验证样本量| 639张
测试样本量| 656张
加载使用方式|自定义数据集
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。
.
├── test|train|valid
│ ├── dog
│ ├── dragon
│ ├── goat
│ ├── horse
│ ├── monkey
│ ├── ox
│ ├── pig
│ ├── rabbit
│ ├── ratt
│ ├── rooster
│ ├── snake
│ └── tiger
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。
```python
config.py
__all__ = ['CONFIG', 'get']
CONFIG = {
'model_save_dir': "./output/zodiac",
'num_classes': 12,
'total_images': 7096,
'epochs': 20,
'batch_size': 32,
'image_shape': [3, 224, 224],
'LEARNING_RATE': {
'params': {
'lr': 0.00375
}
},
'OPTIMIZER': {
'params': {
'momentum': 0.9
},
'regularizer': {
'function': 'L2',
'factor': 0.000001
}
},
'LABEL_MAP': [
"ratt",
"ox",
"tiger",
"rabbit",
"dragon",
"snake",
"horse",
"goat",
"monkey",
"rooster",
"dog",
"pig",
]
}
def get(full_path):
for id, name in enumerate(full_path.split('.')):
if id == 0:
config = CONFIG
config = config[name]
return config
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
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。
import paddle
import numpy as np
from config import get
HWC和CHW区别
NCHW
to_tensor
paddle.vision.transforms.to_tensor(pic, data_format=‘CHW’)[源代码]
将 PIL.Image 或 numpy.ndarray 转换成 paddle.Tensor。
我们数据集的代码实现是在dataset.py中。
import paddle
import paddle.vision.transforms as T
import numpy as np
from config import get
from PIL import Image
__all__ = ['ZodiacDataset']
# 定义图像的大小
image_shape = get('image_shape') #'image_shape': [3, 224, 224],
IMAGE_SIZE = (image_shape[1], image_shape[2])
class ZodiacDataset(paddle.io.Dataset):
"""
十二生肖数据集类的定义
"""
def __init__(self, mode='train'):
"""
初始化函数
"""
assert mode in ['train', 'test', 'valid'], 'mode is one of train, test, valid.' #判断参数合法性
self.data = []
"""
根据不同模式选择不同的数据标注文件
"""
with open('signs/{}.txt'.format(mode)) as f:
for line in f.readlines():
info = line.strip().split('\t')
if len(info) > 0:
self.data.append([info[0].strip(), info[1].strip()])#进行切分形成数组,每个数组包含图像的地址和label
if mode == 'train':
self.transforms = T.Compose([
T.RandomResizedCrop(IMAGE_SIZE), # 随机裁剪大小,裁剪地方不同等于间接增加了数据样本 300*300-224*224
T.RandomHorizontalFlip(0.5), # 随机水平翻转,概率0.5,也是等于得到一个新的图像
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
])
else: #评估模式:没必要进行水平翻转增加样本量了,主要是想看看效果
self.transforms = T.Compose([
T.Resize(256), # 图像大小修改
T.RandomCrop(IMAGE_SIZE), # 随机裁剪,
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
])
def __getitem__(self, index):
"""
根据索引获取单个样本
"""
image_file, label = self.data[index]
image = Image.open(image_file)
#转成RGB模式,三通道的
if image.mode != 'RGB':
image = image.convert('RGB')
image = self.transforms(image)#得到预处理后的结果
return image, np.array(label, dtype='int64')#对label做个数据转换,int类型转成numpy
def __len__(self):
"""
获取样本总数
"""
return len(self.data)
from dataset import ZodiacDataset
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)))
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
network = paddle.vision.models.resnet50(num_classes=get('num_classes'), pretrained=True)
#pretrained=True使用别人已经训练好的预训练模型进行训练网络
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 [[1, 128, 28, 28]] [1, 128, 28, 28] 147,456
BatchNorm2D-17 [[1, 128, 28, 28]] [1, 128, 28, 28] 512
Conv2D-18 [[1, 128, 28, 28]] [1, 512, 28, 28] 65,536
BatchNorm2D-18 [[1, 512, 28, 28]] [1, 512, 28, 28] 2,048
BottleneckBlock-5 [[1, 512, 28, 28]] [1, 512, 28, 28] 0
Conv2D-19 [[1, 512, 28, 28]] [1, 128, 28, 28] 65,536
BatchNorm2D-19 [[1, 128, 28, 28]] [1, 128, 28, 28] 512
ReLU-7 [[1, 512, 28, 28]] [1, 512, 28, 28] 0
Conv2D-20 [[1, 128, 28, 28]] [1, 128, 28, 28] 147,456
BatchNorm2D-20 [[1, 128, 28, 28]] [1, 128, 28, 28] 512
Conv2D-21 [[1, 128, 28, 28]] [1, 512, 28, 28] 65,536
BatchNorm2D-21 [[1, 512, 28, 28]] [1, 512, 28, 28] 2,048
BottleneckBlock-6 [[1, 512, 28, 28]] [1, 512, 28, 28] 0
Conv2D-22 [[1, 512, 28, 28]] [1, 128, 28, 28] 65,536
BatchNorm2D-22 [[1, 128, 28, 28]] [1, 128, 28, 28] 512
ReLU-8 [[1, 512, 28, 28]] [1, 512, 28, 28] 0
Conv2D-23 [[1, 128, 28, 28]] [1, 128, 28, 28] 147,456
BatchNorm2D-23 [[1, 128, 28, 28]] [1, 128, 28, 28] 512
Conv2D-24 [[1, 128, 28, 28]] [1, 512, 28, 28] 65,536
BatchNorm2D-24 [[1, 512, 28, 28]] [1, 512, 28, 28] 2,048
BottleneckBlock-7 [[1, 512, 28, 28]] [1, 512, 28, 28] 0
Conv2D-26 [[1, 512, 28, 28]] [1, 256, 28, 28] 131,072
BatchNorm2D-26 [[1, 256, 28, 28]] [1, 256, 28, 28] 1,024
ReLU-9 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0
Conv2D-27 [[1, 256, 28, 28]] [1, 256, 14, 14] 589,824
BatchNorm2D-27 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024
Conv2D-28 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144
BatchNorm2D-28 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096
Conv2D-25 [[1, 512, 28, 28]] [1, 1024, 14, 14] 524,288
BatchNorm2D-25 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096
BottleneckBlock-8 [[1, 512, 28, 28]] [1, 1024, 14, 14] 0
Conv2D-29 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144
BatchNorm2D-29 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024
ReLU-10 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0
Conv2D-30 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824
BatchNorm2D-30 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024
Conv2D-31 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144
BatchNorm2D-31 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096
BottleneckBlock-9 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0
Conv2D-32 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144
BatchNorm2D-32 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024
ReLU-11 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0
Conv2D-33 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824
BatchNorm2D-33 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024
Conv2D-34 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144
BatchNorm2D-34 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096
BottleneckBlock-10 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0
Conv2D-35 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144
BatchNorm2D-35 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024
ReLU-12 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0
Conv2D-36 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824
BatchNorm2D-36 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024
Conv2D-37 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144
BatchNorm2D-37 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096
BottleneckBlock-11 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0
Conv2D-38 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144
BatchNorm2D-38 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024
ReLU-13 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0
Conv2D-39 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824
BatchNorm2D-39 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024
Conv2D-40 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144
BatchNorm2D-40 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096
BottleneckBlock-12 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0
Conv2D-41 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144
BatchNorm2D-41 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024
ReLU-14 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0
Conv2D-42 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824
BatchNorm2D-42 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024
Conv2D-43 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144
BatchNorm2D-43 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096
BottleneckBlock-13 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0
Conv2D-45 [[1, 1024, 14, 14]] [1, 512, 14, 14] 524,288
BatchNorm2D-45 [[1, 512, 14, 14]] [1, 512, 14, 14] 2,048
ReLU-15 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 0
Conv2D-46 [[1, 512, 14, 14]] [1, 512, 7, 7] 2,359,296
BatchNorm2D-46 [[1, 512, 7, 7]] [1, 512, 7, 7] 2,048
Conv2D-47 [[1, 512, 7, 7]] [1, 2048, 7, 7] 1,048,576
BatchNorm2D-47 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 8,192
Conv2D-44 [[1, 1024, 14, 14]] [1, 2048, 7, 7] 2,097,152
BatchNorm2D-44 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 8,192
BottleneckBlock-14 [[1, 1024, 14, 14]] [1, 2048, 7, 7] 0
Conv2D-48 [[1, 2048, 7, 7]] [1, 512, 7, 7] 1,048,576
BatchNorm2D-48 [[1, 512, 7, 7]] [1, 512, 7, 7] 2,048
ReLU-16 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 0
Conv2D-49 [[1, 512, 7, 7]] [1, 512, 7, 7] 2,359,296
BatchNorm2D-49 [[1, 512, 7, 7]] [1, 512, 7, 7] 2,048
Conv2D-50 [[1, 512, 7, 7]] [1, 2048, 7, 7] 1,048,576
BatchNorm2D-50 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 8,192
BottleneckBlock-15 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 0
Conv2D-51 [[1, 2048, 7, 7]] [1, 512, 7, 7] 1,048,576
BatchNorm2D-51 [[1, 512, 7, 7]] [1, 512, 7, 7] 2,048
ReLU-17 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 0
Conv2D-52 [[1, 512, 7, 7]] [1, 512, 7, 7] 2,359,296
BatchNorm2D-52 [[1, 512, 7, 7]] [1, 512, 7, 7] 2,048
Conv2D-53 [[1, 512, 7, 7]] [1, 2048, 7, 7] 1,048,576
BatchNorm2D-53 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 8,192
BottleneckBlock-16 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 0
AdaptiveAvgPool2D-1 [[1, 2048, 7, 7]] [1, 2048, 1, 1] 0
Linear-1 [[1, 2048]] [1, 12] 24,588
===============================================================================
Total params: 23,585,740
Trainable params: 23,479,500
Non-trainable params: 106,240
-------------------------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 261.48
Params size (MB): 89.97
Estimated Total Size (MB): 352.02
-------------------------------------------------------------------------------
{
'total_params': 23585740, 'trainable_params': 23479500}
CosineAnnealingDecay
class paddle.optimizer.lr.CosineAnnealingDecay(learningrate, Tmax, etamin=0, lastepoch=- 1, verbose=False)[源代码]
该接口使用 cosine annealing 的策略来动态调整学习率。
η t = η min + 1 2 ( η max − η min ) ( 1 + cos ( T c u r T max π ) ) , T c u r ≠ ( 2 k + 1 ) T max η t + 1 = η t + 1 2 ( η max − η min ) ( 1 − cos ( 1 T max π ) ) , T c u r = ( 2 k + 1 ) T max \begin{aligned} \eta_{t} &=\eta_{\min }+\frac{1}{2}\left(\eta_{\max }-\eta_{\min }\right)\left(1+\cos \left(\frac{T_{c u r}}{T_{\max }} \pi\right)\right), & T_{c u r} \neq(2 k+1) T_{\max } \\ \eta_{t+1} &=\eta_{t}+\frac{1}{2}\left(\eta_{\max }-\eta_{\min }\right)\left(1-\cos \left(\frac{1}{T_{\max }} \pi\right)\right), & T_{c u r}=(2 k+1) T_{\max } \end{aligned} ηtηt+1=ηmin+21(ηmax−ηmin)(1+cos(TmaxTcurπ)),=ηt+21(ηmax−ηmin)(1−cos(Tmax1π)),Tcur=(2k+1)TmaxTcur=(2k+1)Tmax
ηmax 的初始值为 learning_rate, Tcur 是SGDR(重启训练SGD)训练过程中的当前训练轮数。SGDR的训练方法可以参考文档 SGDR: Stochastic Gradient Descent with Warm Restarts. 这里只是实现了 cosine annealing 动态学习率,热启训练部分没有实现。
参数:
返回:用于调整学习率的 CosineAnnealingDecay 实例对象
Momentum
class paddle.optimizer.Momentum(learningrate=0.001, momentum=0.9, parameters=None, usenesterov=False, weightdecay=None, gradclip=None, name=None)[源代码]
该接口实现含有速度状态的Simple Momentum 优化器
该优化器含有牛顿动量标志,公式更新如下:
更新公式如下:
参数:
API参考链接
https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/optimizer/momentum/Momentum_cn.html
EPOCHS = get('epochs')
BATCH_SIZE = get('batch_size')
def create_optim(parameters):
step_each_epoch = get('total_images') // get('batch_size')
lr = paddle.optimizer.lr.CosineAnnealingDecay(learning_rate=get('LEARNING_RATE.params.lr'),
T_max=step_each_epoch * EPOCHS)
return paddle.optimizer.Momentum(learning_rate=lr,
parameters=parameters,
weight_decay=paddle.regularizer.L2Decay(get('OPTIMIZER.regularizer.factor'))) #正则化来提升精度
# 模型训练配置
model.prepare(create_optim(network.parameters()), # 优化器
paddle.nn.CrossEntropyLoss(), # 损失函数
paddle.metric.Accuracy(topk=(1, 5))) # 评估指标
# 训练可视化VisualDL工具的回调函数
visualdl = paddle.callbacks.VisualDL(log_dir='visualdl_log')
# 启动模型全流程训练
model.fit(train_dataset, # 训练数据集
valid_dataset, # 评估数据集
epochs=EPOCHS, # 总的训练轮次
batch_size=BATCH_SIZE, # 批次计算的样本量大小
shuffle=True, # 是否打乱样本集
verbose=1, # 日志展示格式
save_dir='./chk_points/', # 分阶段的训练模型存储路径
callbacks=[visualdl]) # 回调函数使用
top1 表示预测的第一个答案就是正确答案的准确率
top5 表示预测里面前五个包含正确答案的准确率
预测可视化:
将我们训练得到的模型进行保存,以便后续评估和测试使用。
model.save(get('model_save_dir'))
predict_dataset = ZodiacDataset(mode='test')
print('测试数据集样本量:{}'.format(len(predict_dataset)))
from paddle.static import InputSpec
# 网络结构示例化
network = paddle.vision.models.resnet50(num_classes=get('num_classes'))
# 模型封装
model_2 = paddle.Model(network, inputs=[InputSpec(shape=[-1] + get('image_shape'), dtype='float32', name='image')])
# 训练好的模型加载
model_2.load(get('model_save_dir'))
# 模型配置
model_2.prepare()
# 执行预测
result = model_2.predict(predict_dataset)
import matplotlib.pyplot as plt
# 样本映射
LABEL_MAP = get('LABEL_MAP')
def show_img(img, predict):
plt.figure()
plt.title('predict: {}'.format(LABEL_MAP[predict_label]))
image_file, label = predict_dataset.data[idx]
image = Image.open(image_file)
plt.imshow(image)
plt.show()
# 随机取样本展示
indexs = [50,150 , 250, 350, 450, 00]
for idx in indexs:
predict_label = np.argmax(result[0][idx])
real_label = predict_dataset[idx][1]
show_img(real_label,predict_label )
print('样本ID:{}, 真实标签:{}, 预测值:{}'.format(idx, LABEL_MAP[real_label], LABEL_MAP[predict_label]))
#或者不定义函数:
"""
import matplotlib.pyplot as plt
# 样本映射
LABEL_MAP = get('LABEL_MAP')
# # 抽样展示
indexs = [50,150 , 250, 350, 450, 00]
for idx in indexs:
predict_label = np.argmax(result[0][idx])
real_label = predict_dataset[idx][1]
print('样本ID:{}, 真实标签:{}, 预测值:{}'.format(idx, LABEL_MAP[real_label], LABEL_MAP[predict_label]))
image_file, label = predict_dataset.data[idx]
image = Image.open(image_file)
plt.figure()
plt.title('predict: {}'.format(LABEL_MAP[predict_label]))
plt.imshow(image)
plt.show()
"""
样本ID:50, 真实标签:monkey, 预测值:monkey
样本ID:150, 真实标签:ratt, 预测值:ratt
样本ID:450, 真实标签:tiger, 预测值:tiger
model_2.save('infer/zodiac', training=False)
本次讲解了四种卷积神经网络的由来,以及采用resnet50实现了十二生肖分类项目
本次项目重点在于数据集自定义、以及创建优化器。来使模型更加灵活可改动也提高准确率和有助于模型快速收敛。
这里还是推荐模型封装不要采用高层api 自己用Sub Class写法或者用Sequential写法。尝试写写看虽然层数比较多!