【Demo 1】基於object_detection API的行人檢測 3：模型訓練與測試

訓練准備

模型選擇

選擇ssd_mobilenet_v2_coco模型，下載地址（https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md），解壓到./Pedestrian_Detection/ssd_mobilenet_v2_coco_2018_03_29.

修改object_detection配置文件

進入目錄./Pedestrian_Detection/models/research/object_detection/samples/configs 找到對應的模型配置文件ssd_mobilenet_v2_coco.config修改配置文件。

根據提示信息：

1、第9行，檢測類別把90改為1，因為我們只檢測行人，只有一個類別。

2、修改除提示外所有的

　　2.1、第一個（156行）是我們所需模型的路徑，即上一步下載好的：./Pedestrian_Detection/ssd_mobilenet_v2_coco_2018_03_29/model.ckpt

　　2.2、第二個（175行）是train.record文件的路徑，上一篇中我們准備好的record文件：./Pedestrian_Detection/project/pedestrian_train/data/pascal_train.record

　　2.3、第三個（177行）是上一篇准備好的label_map.pbtxt的路徑：./Pedestrian_Detection/project/pedestrian_train/data/label_map.pbtxt

　　2.4、第四個（189行）是eval.record文件的路徑，上一篇中我們准備好的record文件：./Pedestrian_Detection/project/pedestrian_train/data/pascal_eval.record

　　2.5、第五個（191行）同2.3

這樣config文件就修改完成了。然后把它放到：./Pedestrian_Detection/project/pedestrian_train/models目錄下。最后在該目錄下創建兩個文件夾：train 和 eval，用於儲存訓練和驗證的記錄。

開始訓練

打開命令行窗口

在research目錄下輸入：

(dl) D:\Study\dl\Pedestrian_Detection\models\research>python object_detection/legacy/train.py --train_dir=D:\Study\dl\Pedestrian_Detection\project\pedestrian_train\models\train --pipeline_config_path=D:\Study\dl\Pedestrian_Detection\project\pedestrian_train\models\ssd_mobilenet_v2_coco.config --logtostderr

即可開始訓練。

這里我們選擇2000次之后，按ctrl+c結束訓練。訓練的詳細信息可通過tensorboard來進行查看（這里不再贅述）。

查看我們的訓練記錄：

導出模型

這里我們選擇第2391次的訓練數據來生成模型。

把下圖4個文件放到：./Pedestrian_Detection/pedestrian_data/model  目錄下

 

 

 

 

在命令行窗口下輸入命令：

(dl) D:\Study\dl\Pedestrian_Detection\models\research>python object_detection/export_inference_graph.py --input_type=image_tensor --pipeline_config_path=D:\Study\dl\Pedestrian_Detection\project\pedestrian_train\models\ssd_mobilenet_v2_coco.config --trained_checkpoint_prefix=D:\Study\dl\Pedestrian_Detection\pedestrian_data\model\model.ckpt-2391 --output_directory=D:\Study\dl\Pedestrian_Detection\pedestrian_data\test

查看發現對應的目錄下已經生成了一系列的模型文件：

 

測試模型

測試代碼：

import os
import sys

import cv2
import numpy as np
import tensorflow as tf

sys.path.append("..")
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util

##################################################

##################################################

# Path to frozen detection graph
PATH_TO_CKPT = 'D:/Study/dl/Pedestrian_Detection/pedestrian_data/test/frozen_inference_graph.pb'

# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('D:/Study/dl/Pedestrian_Detection/project/pedestrian_train/data', 'label_map.pbtxt')

NUM_CLASSES = 1
detection_graph = tf.Graph()
with detection_graph.as_default():
    od_graph_def = tf.GraphDef()
    with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
        serialized_graph = fid.read()
        od_graph_def.ParseFromString(serialized_graph)
        tf.import_graph_def(od_graph_def, name='')

label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)


def load_image_into_numpy_array(image):
    (im_width, im_height) = image.size
    return np.array(image.getdata()).reshape(
      (im_height, im_width, 3)).astype(np.uint8)


with detection_graph.as_default():
    with tf.Session(graph=detection_graph) as sess:
        image_np = cv2.imread("D:/Study/dl/Pedestrian_Detection/project/test_images/3600.jpg")
        # image_np = cv2.imread("D:/images/pedestrain.png")
        cv2.imshow("input", image_np)
        print(image_np.shape)
        # image_np == [1, None, None, 3]
        image_np_expanded = np.expand_dims(image_np, axis=0)
        image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
        boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
        scores = detection_graph.get_tensor_by_name('detection_scores:0')
        classes = detection_graph.get_tensor_by_name('detection_classes:0')
        num_detections = detection_graph.get_tensor_by_name('num_detections:0')
        # Actual detection.
        (boxes, scores, classes, num_detections) = sess.run(
            [boxes, scores, classes, num_detections],
            feed_dict={image_tensor: image_np_expanded})
        # Visualization of the results of a detection.
        vis_util.visualize_boxes_and_labels_on_image_array(
              image_np,
              np.squeeze(boxes),
              np.squeeze(classes).astype(np.int32),
              np.squeeze(scores),
              category_index,
              use_normalized_coordinates=True,
              min_score_thresh=0.5,
              line_thickness=1)
        cv2.imshow('object detection', image_np)
        cv2.imwrite("D:/run_result.png", image_np)
        cv2.waitKey(0)
        cv2.destroyAllWindows()

測試效果：