【paddlepaddle速成】paddlepaddle图像分类从模型自定义到测试

这是给大家准备的paddlepaddle与visualdl速成例子

这一次我们讲讲paddlepadle这个百度开源的机器学习框架，一个图像分类任务从训练到测试出结果的全流程。

将涉及到paddlepaddle和visualdl，git如下：https://github.com/PaddlePaddle

相关的代码、数据都在我们 Git 上，希望大家 Follow 一下这个 Git 项目，后面会持续更新不同框架下的任务。

https://github.com/longpeng2008/LongPeng_ML_Course

作者&编辑 | 言有三  

01 paddlepaddle是什么

正所谓google有tensorflow，facebook有pytorch，amazon有mxnet，作为国内机器学习的先驱，百度也有PaddlePaddle，其中Paddle即Parallel Distributed Deep Learning(并行分布式深度学习)，整体使用起来与tensorflow非常类似。

sudo pip install paddlepaddle

安装就是一条命令，话不多说上代码。

02 paddlepaddle训练

训练包括三部分，数据的定义，网络的定义，以及可视化和模型的存储。

2.1 数据定义

定义一个图像分类任务的dataset如下：

from multiprocessing import cpu_count
import paddle.v2 as paddle
class Dataset:
    def __init__(self,cropsize,resizesize):
        self.cropsize = cropsize
        self.resizesize = resizesize
    def train_mapper(self,sample):
        img, label = sample
        img = paddle.image.load_image(img)
        img = paddle.image.simple_transform(img, self.resizesize, self.cropsize, True)
        #print "train_mapper",img.shape,label
        return img.flatten().astype('float32'), label
    def test_mapper(self,sample):
        img, label = sample
        img = paddle.image.load_image(img)
        img = paddle.image.simple_transform(img, self.resizesize, self.cropsize, False)
        #print "test_mapper",img.shape,label
        return img.flatten().astype('float32'), label
    def train_reader(self,train_list, buffered_size=1024):
        def reader():
            with open(train_list, 'r') as f:
                lines = [line.strip() for line in f.readlines()]
                print "len of train dataset=",len(lines)
                for line in lines:
                    img_path, lab = line.strip().split(' ')
                    yield img_path, int(lab)
        return paddle.reader.xmap_readers(self.train_mapper, reader,
                                          cpu_count(), buffered_size)
    def test_reader(self,test_list, buffered_size=1024):
        def reader():
            with open(test_list, 'r') as f:
                lines = [line.strip() for line in f.readlines()]
                print "len of val dataset=",len(lines)
                for line in lines:
                    img_path, lab = line.strip().split(' ')
                    yield img_path, int(lab)
        return paddle.reader.xmap_readers(self.test_mapper, reader,
                                          cpu_count(), buffered_size)
 
从上面代码可以看出:
(1) 使用了paddle.image.load_image进行图片的读取，
 paddle.image.simple_transform进行了简单的图像变换，这里只有图像crop操作，更多的使用可以参考API。(2)  使用了paddle.reader.xmap_readers进行数据的映射。
2.2 网络定义
# coding=utf-8
 import paddle.fluid as fluid
 def simplenet(input):
    # 定义卷积块 
    conv1 = fluid.layers.conv2d(input=input, num_filters=12,stride=2,padding=1,filter_size=3,act="relu")
    bn1 = fluid.layers.batch_norm(input=conv1)
    conv2 = fluid.layers.conv2d(input=bn1, num_filters=12,stride=2,padding=1,filter_size=3,act="relu")
    bn2 = fluid.layers.batch_norm(input=conv2)
    conv3 = fluid.layers.conv2d(input=bn2, num_filters=12,stride=2,padding=1,filter_size=3,act="relu")
    bn3 = fluid.layers.batch_norm(input=conv3)
    fc1 = fluid.layers.fc(input=bn3, size=128, act=None)
    return fc1,conv1

与之前的caffe，pytorch，tensorflow框架一样，定义了一个3层卷积与2层全连接的网络。为了能够更好的进行可视化，我们使用了PaddlePaddle Fluid，Fluid的设计也是用来让用户像Pytorch和Tensorflow Eager Execution一样可以执行动态计算而不需要创建图。

2.3可视化

paddlepaddle有与之配套使用的可视化框架，即visualdl。

visualdl是百度数据可视化实验室发布的深度学习可视化平台，它的定位与tensorboard很像，可视化内容包含了向量，参数直方图分布，模型结构，图像等功能，以后我们会详细给大家讲述，这次直接在代码中展示如何使用。

安装使用pip install --upgrade visualdl，使用下面的命令可以查看官方例子：

vdl_create_scratch_log

visualDL --logdir ./scratch_log --port 8080

http://127.0.0.1:8080

下面是loss和直方图的查看

在咱们项目中，具体使用方法如下

# 首先定义相关变量
 # 创建VisualDL，并指定log存储路径
 logdir = "./logs"
 logwriter = LogWriter(logdir, sync_cycle=10)

 # 创建loss的趋势图
 with logwriter.mode("train") as writer:
    loss_scalar = writer.scalar("loss")

 # 创建acc的趋势图
 with logwriter.mode("train") as writer:
    acc_scalar = writer.scalar("acc")

 # 定义输出频率
 num_samples = 4
 # 创建卷积层和输出图像的图形化展示
 with logwriter.mode("train") as writer:
    conv_image = writer.image("conv_image", num_samples, 1)
    input_image = writer.image("input_image", num_samples, 1)

 # 创建可视化的训练模型结构
 with logwriter.mode("train") as writer:
    param1_histgram = writer.histogram("param1", 100)然后在训练过程中进行记录，这是完整的训练代码，红色部分就是记录结果。
# coding=utf-8
 import numpy as np
 import os
 import paddle.fluid as fluid
 import paddle.fluid.framework as framework
 import paddle.v2 as paddle
 from paddle.fluid.initializer import NormalInitializer
 from paddle.fluid.param_attr import ParamAttr
 from visualdl import LogWriter
 from dataset import Dataset
 from net_fluid import simplenet

 # 创建VisualDL，并指定当前该项目的VisualDL的路径
 logdir = "./logs"
 logwriter = LogWriter(logdir, sync_cycle=10)

 # 创建loss的趋势图
 with logwriter.mode("train") as writer:
    loss_scalar = writer.scalar("loss")

 # 创建acc的趋势图
 with logwriter.mode("train") as writer:
    acc_scalar = writer.scalar("acc")

 # 定义输出频率
 num_samples = 4
 # 创建卷积层和输出图像的图形化展示
 with logwriter.mode("train") as writer:
    conv_image = writer.image("conv_image", num_samples, 1)
    input_image = writer.image("input_image", num_samples, 1)

 # 创建可视化的训练模型结构
 with logwriter.mode("train") as writer:
    param1_histgram = writer.histogram("param1", 100)

 def train(use_cuda, learning_rate, num_passes, BATCH_SIZE=128):
    class_dim = 2
    image_shape = [3, 48, 48]
    image = fluid.layers.data(name='image', shape=image_shape, dtype='float32')
    label = fluid.layers.data(name='label', shape=[1], dtype='int64')

    net, conv1 = simplenet(image)
    # 获取全连接输出
    predict = fluid.layers.fc(
        input=net,
        size=class_dim,
        act='softmax',
        param_attr=ParamAttr(name="param1", initializer=NormalInitializer()))

    # 获取损失
    cost = fluid.layers.cross_entropy(input=predict, label=label)
    avg_cost = fluid.layers.mean(x=cost)

    # 计算batch，从而来求平均的准确率
    batch_size = fluid.layers.create_tensor(dtype='int64')
    print "batchsize=",batch_size
    batch_acc = fluid.layers.accuracy(input=predict, label=label, total=batch_size)

    # 定义优化方法
    optimizer = fluid.optimizer.Momentum(
        learning_rate=learning_rate,
        momentum=0.9,
        regularization=fluid.regularizer.L2Decay(5 * 1e-5))

    opts = optimizer.minimize(avg_cost)

    # 是否使用GPU
    place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
    # 创建调试器
    exe = fluid.Executor(place)
    # 初始化调试器
    exe.run(fluid.default_startup_program())
    # 保存结果
    model_save_dir = "./models"

    # 获取训练数据
    resizesize = 60
    cropsize = 48
    mydata = Dataset(cropsize=cropsize,resizesize=resizesize)
    mydatareader = mydata.train_reader(train_list='./all_shuffle_train.txt')
    train_reader = paddle.batch(reader=paddle.reader.shuffle(reader=mydatareader,buf_size=50000),batch_size=128)
    
    # 指定数据和label的对应关系
    feeder = fluid.DataFeeder(place=place, feed_list=[image, label])

    step = 0
    sample_num = 0
    start_up_program = framework.default_startup_program()
    param1_var = start_up_program.global_block().var("param1")

    accuracy = fluid.average.WeightedAverage()
    # 开始训练，使用循环的方式来指定训多少个Pass
    for pass_id in range(num_passes):
        # 从训练数据中按照一个个batch来读取数据
        accuracy.reset()
        for batch_id, data in enumerate(train_reader()):
            loss, conv1_out, param1, acc, weight = exe.run(fluid.default_main_program(),
                                                           feed=feeder.feed(data),
                                                           fetch_list=[avg_cost, conv1, param1_var, batch_acc,batch_size])
            accuracy.add(value=acc, weight=weight)
            pass_acc = accuracy.eval（)

            # 重新启动图形化展示组件
            if sample_num == 0:
                input_image.start_sampling()
                conv_image.start_sampling()
            # 获取taken
            idx1 = input_image.is_sample_taken()
            idx2 = conv_image.is_sample_taken()
            # 保证它们的taken是一样的
            assert idx1 == idx2
            idx = idx1
            if idx != -1:
                # 加载输入图像的数据数据
                image_data = data[0][0]
                input_image_data = np.transpose(
                    image_data.reshape(image_shape), axes=[1, 2, 0])
                input_image.set_sample(idx, input_image_data.shape,
                                       input_image_data.flatten())
                # 加载卷积数据
                conv_image_data = conv1_out[0][0]
                conv_image.set_sample(idx, conv_image_data.shape,
                                      conv_image_data.flatten())
                # 完成输出一次
                sample_num += 1
                if sample_num % num_samples == 0:
                    input_image.finish_sampling()
                    conv_image.finish_sampling()
                    sample_num = 0

           # 加载趋势图的数据
            loss_scalar.add_record(step, loss)
            acc_scalar.add_record(step, acc)
            # 添加模型结构数据
            param1_histgram.add_record(step, param1.flatten())
                      # 输出训练日志
            print("loss:" + str(loss) + " acc:" + str(acc) + " pass_acc:" + str(pass_acc))
            step += 1
            model_path = os.path.join(model_save_dir,str(pass_id))
            if not os.path.exists(model_save_dir):
                os.mkdir(model_save_dir)
            fluid.io.save_inference_model(model_path,['image'],[predict],exe)

 if __name__ == '__main__':
    # 开始训练
    train(use_cuda=False, learning_rate=0.005, num_passes=300)

2.4训练结果

看看acc和loss的曲线，可见已经收敛

03 paddlepaddle测试

训练的时候使用了fluid，测试的时候也需要定义调试器，加载训练好的模型，完整的代码如下

# encoding:utf-8
 import sys
 import numpy as np
 import paddle.v2 as paddle
 from PIL import Image
 import os
 import cv2
 # coding=utf-8
 import numpy as np
 import paddle.fluid as fluid
 import paddle.fluid.framework as framework
 import paddle.v2 as paddle
 from paddle.fluid.initializer import NormalInitializer
 from paddle.fluid.param_attr import ParamAttr
 from visualdl import LogWriter
 from net_fluid import simplenet

 if __name__ == "__main__":
    # 开始预测
    type_size = 2
    testsize = 48

    imagedir = sys.argv[1]
    images = os.listdir(imagedir)
           # 定义调试器
    save_dirname = "./models/299"
    exe = fluid.Executor(fluid.CPUPlace())
    inference_scope = fluid.core.Scope()
    with fluid.scope_guard(inference_scope):
    # 加载模型 [inference_program,feed_target_names,fetch_targets] = fluid.io.load_inference_model(save_dirname,exe)

        predicts = np.zeros((type_size,1))
        for image in images:
            imagepath = os.path.join(imagedir,image)
            img = paddle.image.load_image(imagepath)
            img = paddle.image.simple_transform(img,testsize,testsize,False)
            img = img[np.newaxis,:]

            #print img.shape

            results = np.argsort(-exe.run(inference_program,feed={feed_target_names[0]:img},
                    fetch_list=fetch_targets)[0])
            label = results[0][0]
            predicts[label] += 1
    
    print predicts

由于所有框架的测试流程都差不多，所以就不对每一部分进行解释了，大家可以自行去看代码。