tensorflow检测及分割任务笔记
参考引用：https://blog.csdn.net/csdn_6105/article/details/82933628
准备相关环境。如tensorflow环境和object detection相关环境，可以参考上面的文章
tensorflow models 仓库位置：在github上搜 tensorflow models
准备下载数据（可以使用下面的仓库，根据readme来调整和生成tfrecord）
https://gitee.com/leoluopy/tfrecord_generator
生成配置文件，主要两个，pipconfig 和 labelmap.pbtxt
labelmap.pbtxt：
item {
id: 5
name: 'king'
}
item {
id: 6
name: 'ace'
}piplineconfig 实例位于：
object_detection/samples/configs/
主要修改，学习率，优化器方式，batchsize大小，tfrecord位置，labelmap位置等。
实例中有README和配置文件中有提示。
若遇到下述问题：
“rv = reductor(4)
TypeError: can’t pickle dict_values objects”
解决方案为：我们进入到D:\tensorflow1\models\research\object_detection下，然后打开model_lib.py文件，接着找到下图中所标出的位置，最后将category_index.values()改为list(category_index.values())即可。
训练使用 model_main.py 训练：（会没有打印，但是推荐使用tensorboard进行查看，信息非常全）
python object_detection/model_main.py --pipeline_config_path=object_detection/samples/configs/ssd_resnet50_v1_fpn_shared_box_predictor_640x640_coco14_sync.config --model_dir=./training/ --num_train_steps=5000000 --sample_1_of_n_eval_examples=1 --alsologtostderr导出inference图：
python object_detection/export_inference_graph.py --input_type=image_tensor --pipeline_config_path=object_detection/samples/configs/ssd_mobilenet_v1_coco.config --trained_checkpoint_prefix=/data/self-trained/model-41915/model.ckpt-xxx --output_directory=inference_graph预测使用如下代码（图位置和实例图片位置需要修改）：
######## Image Object Detection Using Tensorflow-trained Classifier #########
#
# Author: Evan Juras
# Date: 1/15/18
# Description:
# This program uses a TensorFlow-trained classifier to perform object detection.
# It loads the classifier uses it to perform object detection on an image.
# It draws boxes and scores around the objects of interest in the image.
## Some of the code is copied from Google's example at
## https://github.com/tensorflow/models/blob/master/research/object_detection/object_detection_tutorial.ipynb
## and some is copied from Dat Tran's example at
## https://github.com/datitran/object_detector_app/blob/master/object_detection_app.py
## but I changed it to make it more understandable to me.
# Import packages
import os
import cv2
import numpy as np
import tensorflow as tf
import sys
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
# Import utilites
from utils import label_map_util
from utils import visualization_utils as vis_util
# Name of the directory containing the object detection module we're using
MODEL_NAME = './inference_graph'
IMAGE_NAME = './test.jpg'
# Grab path to current working directory
CWD_PATH = os.getcwd()
# Path to frozen detection graph .pb file, which contains the model that is used
# for object detection.
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')
# Path to label map file
PATH_TO_LABELS = os.path.join(CWD_PATH,'training','labelmap.pbtxt')
# Path to image
PATH_TO_IMAGE = os.path.join(CWD_PATH,IMAGE_NAME)
# Number of classes the object detector can identify
NUM_CLASSES = 1
# Load the label map.
# Label maps map indices to category names, so that when our convolution
# network predicts `5`, we know that this corresponds to `king`.
# Here we use internal utility functions, but anything that returns a
# dictionary mapping integers to appropriate string labels would be fine
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)
# Load the Tensorflow model into memory.
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='')
sess = tf.Session(graph=detection_graph)
# Define input and output tensors (i.e. data) for the object detection classifier
# Input tensor is the image
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Output tensors are the detection boxes, scores, and classes
# Each box represents a part of the image where a particular object was detected
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represents level of confidence for each of the objects.
# The score is shown on the result image, together with the class label.
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
# Number of objects detected
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# Load image using OpenCV and
# expand image dimensions to have shape: [1, None, None, 3]
# i.e. a single-column array, where each item in the column has the pixel RGB value
image = cv2.imread(PATH_TO_IMAGE)
cv2.imshow("image", image)
image_expanded = np.expand_dims(image, axis=0)
# Perform the actual detection by running the model with the image as input
import time
start = time.time()
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict={image_tensor: image_expanded})
print("using time for first:{}".format(time.time()-start))
for i in range(100):
start = time.time()
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict={image_tensor: image_expanded})
print("using time for {}:{}".format(i,time.time() - start))
# Draw the results of the detection (aka 'visulaize the results')
vis_util.visualize_boxes_and_labels_on_image_array(
image,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8,
min_score_thresh=0.80)
# All the results have been drawn on image. Now display the image.
cv2.imshow('Object detector', image)
# Press any key to close the image
cv2.waitKey(0)
# Clean up
cv2.destroyAllWindows()
使用PIL库加载
######## Image Object Detection Using Tensorflow-trained Classifier #########
#
# Author: Evan Juras
# Date: 1/15/18
# Description:
# This program uses a TensorFlow-trained classifier to perform object detection.
# It loads the classifier uses it to perform object detection on an image.
# It draws boxes and scores around the objects of interest in the image.
## Some of the code is copied from Google's example at
## https://github.com/tensorflow/models/blob/master/research/object_detection/object_detection_tutorial.ipynb
## and some is copied from Dat Tran's example at
## https://github.com/datitran/object_detector_app/blob/master/object_detection_app.py
## but I changed it to make it more understandable to me.
# Import packages
import os
import numpy as np
import tensorflow as tf
import sys
import PIL
from pylab import *
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
# Import utilites
from utils import label_map_util
from utils import visualization_utils as vis_util
# Name of the directory containing the object detection module we're using
# MODEL_NAME = '../inference_graph_ssd_resnet_119741/'
# MODEL_NAME = '../inference_graph_ssd_mobilev1_fpn/'
# MODEL_NAME = '../inference_graph'
MODEL_NAME = '../inference_graph_mobile512_MOM'
# MODEL_NAME = '../inference_graph_mobile512157K'
IMAGE_NAME = './test.jpg'
show_image = True
# Grab path to current working directory
CWD_PATH = os.getcwd()
# Path to frozen detection graph .pb file, which contains the model that is used
# for object detection.
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')
# Path to label map file
PATH_TO_LABELS = os.path.join(CWD_PATH,'training','labelmap.pbtxt')
# Path to image
PATH_TO_IMAGE = os.path.join(CWD_PATH,IMAGE_NAME)
# Number of classes the object detector can identify
NUM_CLASSES = 1
# Load the label map.
# Label maps map indices to category names, so that when our convolution
# network predicts `5`, we know that this corresponds to `king`.
# Here we use internal utility functions, but anything that returns a
# dictionary mapping integers to appropriate string labels would be fine
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)
# Load the Tensorflow model into memory.
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='')
cpu_num = int(os.environ.get('CPU_NUM', 3))
config = tf.ConfigProto(device_count={"CPU": cpu_num},
inter_op_parallelism_threads=cpu_num,
intra_op_parallelism_threads=cpu_num,
log_device_placement=True)
sess = tf.Session(graph=detection_graph,config=config)
# Define input and output tensors (i.e. data) for the object detection classifier
# Input tensor is the image
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Output tensors are the detection boxes, scores, and classes
# Each box represents a part of the image where a particular object was detected
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represents level of confidence for each of the objects.
# The score is shown on the result image, together with the class label.
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
# Number of objects detected
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# Load image using OpenCV and
# expand image dimensions to have shape: [1, None, None, 3]
# i.e. a single-column array, where each item in the column has the pixel RGB value
# image = cv2.imread(PATH_TO_IMAGE)
image = PIL.Image.open(IMAGE_NAME)
image = array(image)
# cv2.imshow("image", image)
image_expanded = np.expand_dims(image, axis=0)
# Perform the actual detection by running the model with the image as input
import time
start = time.time()
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict={image_tensor: image_expanded})
print("using time for first:{}".format(time.time()-start))
for i in range(10):
start = time.time()
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict={image_tensor: image_expanded})
print("using time for {} : {}".format(i,time.time() - start))
# Draw the results of the detection (aka 'visulaize the results')
vis_util.visualize_boxes_and_labels_on_image_array(
image,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8,
min_score_thresh=0.80)
if show_image:
imshow(image)
plt.show()