Object Detection API（4）——?Freeze Model模型導出
博客：https://blog.csdn.net/qq_34106574
簡書：http://www.itdecent.cn/u/fb86cd4f8bf8
上一節(jié)使用自定義record數(shù)據(jù)進行模型訓練和測試，本節(jié)將訓練模型導出為pb格式，方便程序調用，后面還會介紹如何使用opencv的c++程序來調用訓練好的模型。
1，導出模型：
object_detection目錄下還提供了export_inference_graph.py。直接調用執(zhí)行命令如下：
python ../research/object_detection/export_inference_graph.py --input_type image_tensor --pipeline_config_path train/faster_rcnn_resnet101_coco.config --trained_checkpoint_prefix train/model.ckpt-1738 ?--output_directory out
導出完成后，在out目錄下，會生成frozen_inference_graph.pb、model.ckpt.data-00000-of-00001、model.ckpt.meta、model.ckpt.data文件。如下圖：
?
2，調用接口測試：
（1）添加mymodel在object_detection目錄，將pb文件放置在data目錄，將測試圖像放在test_images目錄.
?
(2)修改object_detection_tutorial.ipynb
(3)在object_detection目錄執(zhí)行命令如下：
jupyter notebookobject_detection_tutorial.ipynb
?
（4）測試結果如下：
3,調用方式2：
打開pycharm，建立工程，運行以下程序：
?
import cv2
import numpy as?np
import tensorflow as?tffrom?object_detection.utils import label_map_utilfrom?object_detection.utils import visualization_utils as?vis_util
class?TOD(object):
????def __init__(self):
????????self.PATH_TO_CKPT = r'XXXX\models-master\object_detection\train\frozen_inference_graph.pb'
????????self.PATH_TO_LABELS = r'XXXX\models-master\object_detection\train\my_label_map.pbtxt'
????????self.NUM_CLASSES = 1
????????self.detection_graph = self._load_model()
????????self.category_index = self._load_label_map()
????def _load_model(self):
????????detection_graph = tf.Graph()
????????with detection_graph.as_default():
????????????od_graph_def = tf.GraphDef()
????????????with tf.gfile.GFile(self.PATH_TO_CKPT, 'rb') as?fid:
????????????????serialized_graph = fid.read()
????????????????od_graph_def.ParseFromString(serialized_graph)
????????????????tf.import_graph_def(od_graph_def, name='')
????????return?detection_graph
????def _load_label_map(self):
????????label_map = label_map_util.load_labelmap(self.PATH_TO_LABELS)
????????categories = label_map_util.convert_label_map_to_categories(label_map,
????????????????????????????????????????????????????????????????????max_num_classes=self.NUM_CLASSES,
????????????????????????????????????????????????????????????????????use_display_name=True)
????????category_index = label_map_util.create_category_index(categories)
????????return?category_index
????def detect(self, image):
????????with self.detection_graph.as_default():
????????????with tf.Session(graph=self.detection_graph) as?sess:
????????????????# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
????????????????image_np_expanded = np.expand_dims(image, axis=0)
????????????????image_tensor = self.detection_graph.get_tensor_by_name('image_tensor:0')
????????????????boxes = self.detection_graph.get_tensor_by_name('detection_boxes:0')
????????????????scores = self.detection_graph.get_tensor_by_name('detection_scores:0')
????????????????classes = self.detection_graph.get_tensor_by_name('detection_classes:0')
????????????????num_detections = self.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.squeeze(boxes),
????????????????????np.squeeze(classes).astype(np.int32),
????????????????????np.squeeze(scores),
????????????????????self.category_index,
????????????????????use_normalized_coordinates=True,
????????????????????line_thickness=8)
????????cv2.imshow("Resault", image)
????????cv2.waitKey(0)
if?__name__ == '__main__':
????image = cv2.imread('test.jpg')
????detecotr = TOD()
????detecotr.detect(image)
?
參考資料
[if !supportLists][1]?[endif]https://www.cnblogs.com/qcloud1001/p/7677661.html
?
?
注：更多內容分享及源碼獲取歡迎關注微信公眾號：ML_Study
版權聲明：本文為博主原創(chuàng)文章，轉載請聯(lián)系作者取得授權。https://blog.csdn.net/qq_34106574/article/category/7628923?
