运用百度框架paddle进行手势识别
本文为一篇实战心得
项目来源于百度aistudio平台，感兴趣可以登录，地址链接：
https://aistudio.baidu.com/
1. 深度学习的四个步骤
- 数据标签处理
- 构建网络模型
- 规划网络超参
- 训练评估模型
2. 代码解析
- 导入库文件
import os
import time
import random
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
import paddle
import paddle.fluid as fluid
import paddle.fluid.layers as layers
from multiprocessing import cpu_count
from paddle.fluid.dygraph import Pool2D,Conv2D
from paddle.fluid.dygraph import Linear
- 数据标签处理
paddle为大家准备的数据集是0-9的手势，每个手势有200+张彩色图片，分辨率为100x100
# 生成图像列表
data_path = 'Dataset'#这里是你的数据集路径
character_folders = os.listdir(data_path)
# print(character_folders)
if(os.path.exists('./train_data.list')):
os.remove('./train_data.list')
if(os.path.exists('./test_data.list')):
os.remove('./test_data.list')
for character_folder in character_folders:
with open('./train_data.list', 'a') as f_train:
with open('./test_data.list', 'a') as f_test:
if character_folder == '.DS_Store':
continue
character_imgs = os.listdir(os.path.join(data_path,character_folder))
count = 0
for img in character_imgs:
if img =='.DS_Store':
continue
if count%10 == 0:
f_test.write(os.path.join(data_path,character_folder,img) + '\t' + character_folder + '\n')
else:
f_train.write(os.path.join(data_path,character_folder,img) + '\t' + character_folder + '\n')
count +=1
print('列表已生成')
使用paddle的reader模块制作训练集和测试集
# 定义训练集和测试集的reader
def data_mapper(sample):
img, label = sample
img = Image.open(img)
img = img.resize((100, 100), Image.ANTIALIAS)
img = np.array(img).astype('float32')
img = img.transpose((2, 0, 1))
img = img/255.0
return img, label
def data_reader(data_list_path):
def reader():
with open(data_list_path, 'r') as f:
lines = f.readlines()
for line in lines:
img, label = line.split('\t')
yield img, int(label)
return paddle.reader.xmap_readers(data_mapper, reader, cpu_count(), 512)
# 用于训练的数据提供器
#buf_size是打乱数据集的参数,size越大,图片顺序越乱
train_reader = paddle.batch(reader=paddle.reader.shuffle(reader=data_reader('./train_data.list'), buf_size=1024), batch_size=32)
# 用于测试的数据提供器
test_reader = paddle.batch(reader=data_reader('./test_data.list'), batch_size=32)
- 构建神经网络
这里以典型的AlexNet构建神经网络结构
#定义DNN网络
class MyDNN(fluid.dygraph.Layer):
def __init__(self, name_scope, num_classes=10):
super(MyDNN, self).__init__(name_scope)
name_scope = self.full_name()
self.conv1 = Conv2D(num_channels=3, num_filters=96, filter_size=11, stride=4, padding=5, act='relu')
self.pool1 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
self.conv2 = Conv2D(num_channels=96, num_filters=256, filter_size=5, stride=1, padding=2, act='relu')
self.pool2 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
self.conv3 = Conv2D(num_channels=256, num_filters=384, filter_size=3, stride=1, padding=1, act='relu')
self.conv4 = Conv2D(num_channels=384, num_filters=384, filter_size=3, stride=1, padding=1, act='relu')
self.conv5 = Conv2D(num_channels=384, num_filters=256, filter_size=3, stride=1, padding=1, act='relu')
self.pool5 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
self.fc1 = Linear(input_dim=9216, output_dim=4096, act='relu')
self.drop_ratio1 = 0.5
self.fc2 = Linear(input_dim=4096, output_dim=4096, act='relu')
self.drop_ratio2 = 0.5
self.fc3 = Linear(input_dim=4096, output_dim=num_classes)
def forward(self, x):
x = self.conv1(x)
x = self.pool1(x)
x = self.conv2(x)
x = self.pool2(x)
x = self.conv3(x)
x = self.conv4(x)
x = self.conv5(x)
x = self.pool5(x)
x = fluid.layers.reshape(x, [x.shape[0], -1])
x = self.fc1(x)
# 在全连接之后使用dropout抑制过拟合
x= fluid.layers.dropout(x, self.drop_ratio1)
x = self.fc2(x)
# 在全连接之后使用dropout抑制过拟合
x = fluid.layers.dropout(x, self.drop_ratio2)
x = self.fc3(x)
return x
- 规划网络超参
#用动态图进行训练
with fluid.dygraph.guard():
model=MyDNN('Alexnet') #模型实例化
model.train() #训练模式
opt = fluid.optimizer.Momentum(learning_rate=0.001,momentum=0.9,parameter_list=model.parameters())
epochs_num=50 #迭代次数
for pass_num in range(epochs_num):
for batch_id,data in enumerate(train_reader()):
images=np.array([x[0].reshape(3,100,100) for x in data],np.float32)
labels = np.array([x[1] for x in data]).astype('int64')
labels = labels[:, np.newaxis]
image=fluid.dygraph.to_variable(images)
label=fluid.dygraph.to_variable(labels)
predict=model(image)#预测
loss=fluid.layers.softmax_with_cross_entropy(predict,label)
avg_loss=fluid.layers.mean(loss)#获取loss值
acc=fluid.layers.accuracy(predict,label)#计算精度
if batch_id!=0 and batch_id%50==0:
print("train_pass:{},batch_id:{},train_loss:{},train_acc:{}".format(pass_num,batch_id,avg_loss.numpy(),acc.numpy()))
avg_loss.backward()
opt.minimize(avg_loss)
model.clear_gradients()
fluid.save_dygraph(model.state_dict(),'MyDNN')#保存模型
- 评估模型
with fluid.dygraph.guard():
accs = []
model_dict, _ = fluid.load_dygraph('MyDNN')
model = MyDNN('Alexnet')
model.load_dict(model_dict) #加载模型参数
model.eval() #训练模式
for batch_id,data in enumerate(test_reader()):#测试集
images=np.array([x[0].reshape(3,100,100) for x in data],np.float32)
labels = np.array([x[1] for x in data]).astype('int64')
labels = labels[:, np.newaxis]
image=fluid.dygraph.to_variable(images)
label=fluid.dygraph.to_variable(labels)
predict=model(image)
acc=fluid.layers.accuracy(predict,label)
accs.append(acc.numpy()[0])
avg_acc = np.mean(accs)
print(avg_acc)
3.实战心得
在写代码的过程中，学到了很多知识，本次实战有专门的课程辅导，更重要感觉是有个微信群交流，在群里都是大佬，能学到很多东西，大家都很优秀，其中在实战过程中也遇到了很多问题，助教帮忙解决了。
说说自己的问题吧，可能是自己的基础太差，是小白的原因，对于官方给出的API文档看起来很费劲，哈哈哈，自己还得加油，也希望官方能优化文档，是的小白也能快速入手～～～
over！！！
