Use Baidu framework paddle gesture recognition [hands-on, with source code]

Use Baidu framework paddle gesture recognition

This paper is a real experience
project comes from Baidu aistudio platform, interested can log on, link address:
https://aistudio.baidu.com/

1. depth study of four steps

1. Data processing label
2. Construction of the network model
3. Planning Network hyperparametric
4. Training Evaluation Model

2. code analysis

1. Import library

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

2. Data processing label
   paddle for everyone to prepare data sets is 0-9 gesture, each gesture has 200+ color photographs with a resolution of 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')

The reader module using the paddle to make the training and test sets

# 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) 

3. Build neural networks

Here constructed in a typical neural network structure AlexNet

#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

4. Planning Network hyperparametric

#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

5. Evaluation Model

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. combat experience

In the process of writing code, I learned a lot, this combat has specialized curriculum counseling, feels more important is to have a group of micro-channel exchanges, are heavyweights in the group can learn a lot, we are very good, which in the actual process also encountered many problems, help solve the assistant.
Talk about their issues now may be the basis for their own poor, white is the reason given for the official API documentation looks very strenuous, ha ha ha, have come on their own, but also hope to optimize the official document, yes white can quickly start ~ ~ ~

over！！！