Tensorflow Object Detection之Mask R-CNN

Tensorflow的目标检测API中除了提供基本的目标检测之外还提供了物体的实例分割。API中提供的实例分割算法是Mask R-CNN，网上很多关于该算法的讲解，这里就不献丑了，直接看看如何使用，上代码：

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

# Matplotlib chooses Xwindows backend by default.  
matplotlib.use('Agg')  

from collections import defaultdict  
from io import StringIO  
from matplotlib import pyplot as plt  
from PIL import Image  
from utils import label_map_util  
from utils import visualization_utils as vis_util  
from object_detection.utils import ops as utils_ops

# Path to frozen detection graph. This is the actual model that is used for the object detection.  
PATH_TO_CKPT = 'mask_rcnn_inception_v2_coco_2018_01_28' + '/frozen_inference_graph.pb'

# List of the strings that is used to add correct label for each box.  
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')  

NUM_CLASSES = 90  


##################### Load a (frozen) Tensorflow model into memory.  
print('Loading model...')  
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='')  

##################### Loading label map  
print('Loading label map...')  
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)  

##################### Helper code  
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)  

##################### Detection  
# Path to test image    （windows下）
TEST_IMAGE_PATH = 'test_images'

# 检测后的图片的保存路径。
PATH = r'C:\Users\gulin\Desktop\bbb'
# Size, in inches, of the output images.  
IMAGE_SIZE = (12, 8)

#读取测试文件夹下所有图片的全路径，并将这些路径放到一个列表（datas）中。
datas=[]
allfilelist=os.listdir(TEST_IMAGE_PATH)
for file in allfilelist:
    file_path=os.path.join(TEST_IMAGE_PATH,file)
    datas.append(file_path)


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


for image_path in datas:
  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)
  # 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=8)
  plt.figure(figsize=IMAGE_SIZE)
  plt.imshow(image_np)
  arr = image_path.split('\\')
  arr = arr[-1]
  plt.savefig(PATH + '\\' + arr.split('.')[0] + '_labeled.jpg')

这里里使用：mask_rcnn_inception_resnet_v2_atrous_coco_2018_01_28/frozen_inference_graph.pb ，使用其它的自行下载替换即可，测试图如下：

检测视频：：

import numpy as np  
import os  
import six.moves.urllib as urllib  
import sys  
import tarfile  
import tensorflow as tf  
import zipfile  
import matplotlib  
import cv2
# Matplotlib chooses Xwindows backend by default.  
matplotlib.use('Agg')  

from collections import defaultdict  
from io import StringIO  
from matplotlib import pyplot as plt  
from PIL import Image  
from utils import label_map_util  
from utils import visualization_utils as vis_util  
from object_detection.utils import ops as utils_ops
'''
    检测视频
'''
##################### Download Model  
cap = cv2.VideoCapture(0)  #打开摄像头

# Path to frozen detection graph. This is the actual model that is used for the object detection.  
PATH_TO_CKPT = 'mask_rcnn_inception_v2_coco_2018_01_28' + '/frozen_inference_graph.pb'

# List of the strings that is used to add correct label for each box.  
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')  

NUM_CLASSES = 90  


##################### Load a (frozen) Tensorflow model into memory.  
print('Loading model...')  
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='')  

##################### Loading label map  
print('Loading label map...')  
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)  

##################### Helper code  
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)  

##################### Detection  

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

while True:
  ret, image_np = cap.read()

  image_np_expanded = np.expand_dims(image_np, axis=0)
  # Actual detection.
  output_dict = run_inference_for_single_image(image_np, detection_graph)
  # 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=8)
  cv2.imshow('object detection', cv2.resize(image_np, (800, 600)))
  # cv2.waitKey(0)
  if cv2.waitKey(25) & 0xFF == ord('q'):
      cv2.destroyAllWindows()
      break