zoukankan      html  css  js  c++  java
  • 使用TransferLearning实现环视图像的角点检测——Tensorflow+MobileNetv2_SSD

    环境说明

    • 依赖环境安装eIQ官方指南:
    name: eiq_auto 
    channels:
      - conda-forge
      - defaults
    dependencies:
      - numpy=1.18.1=py36h4f9e942_0
      - onnx==1.6.0
      - opencv==4.2.0
      - pandas=0.24.2=py36he6710b0_0
      - pillow=7.0.0=py36hb39fc2d_0
      - protobuf=3.9.2=py36he6710b0_0
      - pytest=5.3.0=py36_0
      - python=3.6.10=h0371630_0
      - tensorflow=1.14.0=mkl_py36h2526735_0
    pip:
       - onnxruntime==1.0.0
    

    ==================================================================================

    1.安装tensorflow object detection API

    sudo apt-get install protobuf-compiler python-pil python-lxml python-tk
    pip install --user Cython
    pip install --user contextlib2
    pip install --user jupyter
    pip install --user matplotlib
    
    • 下载models
    git clone https://github.com/tensorflow/models.git
    
    • 安装cocoAPI
    pip install --user pycocotools
    
    • 使用Protobuf Compilation
    protoc object_detection/protos/*.proto --python_out=.
    
    • 添加到PYTHONPATH
    # From tensorflow/models/research/
    export PYTHONPATH=$PYTHONPATH:/mnt/d/0-WORK/models/models-master/research:/mnt/d/0-WORK/models/models-master/research/slim
    source ~/.bashrc
    
    • 注意以上绝对路径填正确
    • 测试是否完成
    python object_detection/builders/model_builder_tf1_test.py
    
    • 如果出现以下结果表示API已成功安装:

    2.使用mobilenetV2_SSD进行训练和预测

    官方使用的版本(ssd_mobilenet_v2_coco_2018_03_29)

    • 首先使用以下flowchart帮助理解transferLearning
    • step1:进入Model目录,执行如下命令:
    cd models/research/
    python setup.py build
    python setup.py install
    
    • step2:配置model并进行训练,首先在object_detection/目录下创建目录ssd_model:
      将下载好的model解压后放在自定义路径下(如object_detection/ssd_model/),下载链接[http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v2_coco_2018_03_29.tar.gz]
      mobileNetv2_SSD使用tfrecord格式的数据进行训练,数据集是使用labelImg工具进行标注的xml格式,需要完成xml转csv再转为record文件。数据集转换工具详见datitran:[https://github.com/datitran/raccoon_dataset]
      把制作好的数据集tfrecords放在路径下(制作步骤详见文末)。复制训练数据用到的文件,我们在这个基础上修改配置,训练我们的数据.coco数据集共有90个class。我们在APA数据标注中使用了3个class,因此打开配置文件ssd_mobilenet_v2_coco.config.需要修改的内容如下:
    ./object_detection/ssd_model/data
    cp object_detection/data/mscoco_label_map.pbtxt object_detection/ssd_model/ cp object_detection/samples/configs/ssd_mobilenet_v2_coco.config object_detection/ssd_model/
    # 修改ssd_mobilenet_v2_coco.config
    num_classes: 3 # 自定义的class数目
    num_steps: 200000 # 设置多少个step后停止,可以mark此行不使用,loss值没有持续下降,可以CTRL-C停止
    batch_size: 8 # 根据算力设置
    fine_tune_checkpoint:/mnt/.../ssd_model/mobilenet_v2_1.4_224/model.ckpt # 上述step中下载的 pre-trained model path,最后固定接上mode.ckpt
    train_input_reader: {
      tf_record_input_reader {
        input_path: "/mnt/.../ssd_model/data/train.record"
            # 之前dataset产生的TFRecord train.record路径
    
    eval_input_reader: {
      tf_record_input_reader {
        input_path: "/mnt/.../ssd_model/data/test.record"
            # 之前dataset产生的TFRecord test.record路径
    
    label_map_path:"/mnt/.../ssd_model/data/mscoco_label_map.pbtxt" # 注意train和eval两处都需要更改.
    
    • step3:训练开始,新版的API中train.py在legacy目录下,先把它copy到research下。
      回到research目录下 执行
    python train.py --logtostderr --train_dir=training/ --pipeline_config_path=ssd_model/data/ssd_mobilenet_v2_coco.config
    

    训练过程如下 (没有GPU时间会比较长,可以在观察到loss不再下降的时候CTRL+C停止训练)



    训练完成后,结果会在-–train_dir指定的path下:


    • step4:模型效果评估:
      我们使用tensorboard工具查看训练效果。首先browser打开tensorbord的address,即可看到training及validate的信息:
      执行以下命令(=后添加刚刚训练的路径)
    tensorboard --logdir=/mnt/d/0-WORK/models/models-master/research/training
    

    成功打开会出现以下地址:



    将地址复制粘贴到浏览器中即可看到训练可视化结果:http://desktop-0vqus2j:6006/#scalars


    • step5: 使用eavl.py查看在验证集上的效果

    • step6:保存模型:
    python object_detection/export_inference_graph.py --pipeline_config_path=/mnt/d/0-WORK/models/models-master/research/object_detection/ssd_model/data/ssd_mobilenet_v2_coco.config --trained_checkpoint_prefix=/mnt/d/0-WORK/models/models-master/research/training/model.ckpt-77133 --output_directory /mnt/d/0-WORK/models/models-master/research/training/
    

    执行完毕后出现:

    OK,得到pb模型啦。

    Model_output
    - saved_model
      - saved_model.pb
    - checkpoint
    - frozen_inference_graph.pb     # Main model 
    - model.ckpt.data-00000-of-00001
    - model.ckpt.index
    - model.ckpt.meta
    - pipeline.config
    

    保存前述data中的mscoco_label_map.pbtxt和本步骤中的frozen_inference_graph.pb,后续使用。

    • step7:使用训练好的模型进行预测:
      使用如下脚本进行单帧图片检测:
    # test.py
    import numpy as np
    import tensorflow as tf
    import cv2 as cv
    
    model_path = "/mnt/d/0-WORK/models/models-master/research/training/frozen_inference_graph.pb"
    pbtxt_path = "/mnt/d/0-WORKmodels/models-master/research/object_detection/ssd_model/data/mscoco_label_map.pbtxt"
    testimg = "/mnt/d/0-WORK/models/models-master/research/testing/114.jpg"
    
    # Read the graph.
    #with tf.compat.v1.gfile.FastGFile(model_path, 'rb') as f:
    #    graph_def = tf.compat.v1.GraphDef()
    #    graph_def.ParseFromString(f.read())
    
    with tf.gfile.FastGFile(model_path, 'rb') as f:
        graph_def = tf.GraphDef()
        graph_def.ParseFromString(f.read())
    
    
    with tf.Session() as sess:
        # Restore session
        sess.graph.as_default()
        tf.import_graph_def(graph_def, name='')
    
        # Read and preprocess an image.
        img = cv.imread(testimg)
        rows = img.shape[0]
        cols = img.shape[1]
        inp = cv.resize(img, (450, 450))
        inp = inp[:, :, [2, 1, 0]]  # BGR2RGB
    
        # Run the model
        out = sess.run([sess.graph.get_tensor_by_name('num_detections:0'),
                        sess.graph.get_tensor_by_name('detection_scores:0'),
                        sess.graph.get_tensor_by_name('detection_boxes:0'),
                        sess.graph.get_tensor_by_name('detection_classes:0')],
                       feed_dict={'image_tensor:0': inp.reshape(1, inp.shape[0], inp.shape[1], 3)})
    
        # Visualize detected bounding boxes.
        num_detections = int(out[0][0])
        for i in range(num_detections):
            classId = int(out[3][0][i])
            
    
            score = float(out[1][0][i])
            bbox = [float(v) for v in out[2][0][i]]
    
            if score > 0.5:
    
                x = bbox[1] * cols
                y = bbox[0] * rows
                right = bbox[3] * cols
                bottom = bbox[2] * rows
                cv.rectangle(img, (int(x), int(y)), (int(right), int(bottom)), (125, 255, 51), thickness=2)
                print(classId, "-->", score, x, y)
                
      
    cv.imwrite('/mnt/d/0-WORK/models/models-master/research/testing/result_114.jpg', img)
    cv.waitKey()
    

    效果如下:


    • step7: 模型评测

    附:voc转tfrecord

    参考博文

  • 相关阅读:
    跨公司销售利润中心替代
    [WCF学习笔记] 我的WCF之旅(1):创建一个简单的WCF程序
    linux操作常用命令
    java lambda表达式
    关于lock和synchronized的选择
    ssh免密登陆(简单快捷)
    su和sudo的区别
    Linux常用查找命令
    vmware完整克隆(linux)
    springboot2.0拦截器和webconfigure配置
  • 原文地址:https://www.cnblogs.com/hayley111/p/12918678.html
Copyright © 2011-2022 走看看