Object_Detection_API之Inference

导入包

import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile

from distutils.version import StrictVersion
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image

# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("../../")
from object_detection.utils import ops as utils_ops

if StrictVersion(tf.__version__) < StrictVersion('1.9.0'):
  raise ImportError('Please upgrade your TensorFlow installation to v1.9.* or later!')

%matplotlib inline
from utils import label_map_util
from utils import visualization_utils as vis_util

设置模型目录

MODEL_DIR = './model_from_200000_steps'
PATH_TO_FROZEN_GRAPH = MODEL_DIR + '/frozen_inference_graph.pb'
PATH_TO_LABELS = os.path.join('./dataset', 'traffic_light_label_map.pbtxt')

恢复计算图

detection_graph = tf.Graph()
with detection_graph.as_default():
    od_graph_def=tf.GraphDef()
    with tf.gfile.GFile(PATH_TO_FROZEN_GRAPH, 'rb') as fid:
        serialized_graph = fid.read()
        od_graph_def.ParseFromString(serialized_graph)
        tf.import_graph_def(od_graph_def, name='')
        ops = tf.get_default_graph().get_operations()
        all_tensor_names = {output.name for op in ops for output in op.outputs}
#         print(all_tensor_names)
        print(len(all_tensor_names))
for name in all_tensor_names:
#     if name.startswith('SecondStage'):
#         print(name)
    if name.find('bottleneck')==-1:
        pass
    else:
        print(name)

读取labelmap

category_index=label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS)
print(category_index)
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)

定义推理函数

def run_inference_for_single_image(image, graph):
  with graph.as_default():
    with tf.Session() as sess:
      # Get handles to input and output tensors
      ops = tf.get_default_graph().get_operations()
      all_tensor_names = {output.name for op in ops for output in op.outputs}
      tensor_dict = {}
      for key in [
          'num_detections', 'detection_boxes', 'detection_scores',
          'detection_classes', 'detection_masks'
      ]:
        tensor_name = key + ':0'
        if tensor_name in all_tensor_names:
          tensor_dict[key] = tf.get_default_graph().get_tensor_by_name(
              tensor_name)
      if 'detection_masks' in tensor_dict:
        # The following processing is only for single image
        detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0])
        detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0])
        # Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
        real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32)
        detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1])
        detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1])
        detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
            detection_masks, detection_boxes, image.shape[0], image.shape[1])
        detection_masks_reframed = tf.cast(
            tf.greater(detection_masks_reframed, 0.5), tf.uint8)
        # Follow the convention by adding back the batch dimension
        tensor_dict['detection_masks'] = tf.expand_dims(
            detection_masks_reframed, 0)
      image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0')

      # Run inference
      output_dict = sess.run(tensor_dict,
                             feed_dict={image_tensor: np.expand_dims(image, 0)})

      # all outputs are float32 numpy arrays, so convert types as appropriate
      output_dict['num_detections'] = int(output_dict['num_detections'][0])
      output_dict['detection_classes'] = output_dict[
          'detection_classes'][0].astype(np.uint8)
      output_dict['detection_boxes'] = output_dict['detection_boxes'][0]
      output_dict['detection_scores'] = output_dict['detection_scores'][0]
      if 'detection_masks' in output_dict:
        output_dict['detection_masks'] = output_dict['detection_masks'][0]
  return output_dict

进行推理

import random
import cv2
import glob
PATH_TO_TEST_IMAGES_DIR = './images_for_test'
TEST_IMAGE_PATHS = glob.glob(os.path.join(PATH_TO_TEST_IMAGES_DIR, "*.jpg"))
print(len(TEST_IMAGE_PATHS))
IMAGE_SIZE=(12,8)

推理

count=0
saved_dir_for_predicted_images="./images_predicted"
for count in range(10):
  chx = random.randint(0, len(TEST_IMAGE_PATHS)-1)
  image_path = TEST_IMAGE_PATHS[chx]
  image = Image.open(image_path)
  # the array based representation of the image will be used later in order to prepare the
  # result image with boxes and labels on it.
  image_np = load_image_into_numpy_array(image)
  # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
  image_np_expanded = np.expand_dims(image_np, axis=0)
  # Actual detection.
  output_dict = run_inference_for_single_image(image_np, detection_graph)
  # print(output_dict)
  # Visualization of the results of a detection.
  vis_util.visualize_boxes_and_labels_on_image_array(
      image_np,
      output_dict['detection_boxes'],
      output_dict['detection_classes'],
      output_dict['detection_scores'],
      category_index,
      instance_masks=output_dict.get('detection_masks'),
      use_normalized_coordinates=True,
      line_thickness=4)
  im = Image.fromarray(image_np.astype('uint8'))
  saved_name = os.path.basename(image_path).split('.')[0]
  im.save(os.path.join(saved_dir_for_predicted_images, saved_name+'.jpg'))
#   image_np = cv2.cvtColor(image_np, cv2.COLOR_RGB2BGR)
#   cv2.imshow('image',image_np)
#   cv2.waitKey(10)
#   cv2.destroyAllWindows()
#   if cv2.waitKey(1000)&0xff == 113:
#     cv2.destroyAllWindows()
#   plt.figure(figsize=IMAGE_SIZE)
#   plt.imshow(image_np)
#   plt.show()