tensorflow検出および分割タスクノート

参照:https://blog.csdn.net/csdn_6105/article/details/82933628
関連環境を準備します.tensorflow環境やobject detection関連環境などは、上記の記事を参照してください.
tensorflow models倉庫位置:githubでtensorflow modelsを検索する
ダウンロードデータの準備(readmeに基づいてtfrecordを調整および生成するには、次の倉庫を使用します)
https://gitee.com/leoluopy/tfrecord_generator
プロファイルを生成し、主に2つ、pipconfigとlabelmap.pbtxt
labelmap.pbtxt:

item {
  id: 5
  name: 'king'
}

item {
  id: 6
  name: 'ace'
}

piplineconfigインスタンスは次のとおりです.
object_detection/samples/configs/
主な修正,学習率,オプティマイザ方式,batchsizeサイズ,tfrecord位置,labelmap位置などである.
インスタンスにはREADMEとプロファイルにヒントがあります.
 
「rv=reductor(4)TypeError:can't pickle dict_values objects」ソリューションは、D:tensorflow 1modelsresearchobject_に進みます.detectionでmodelを開きますlib.pyファイル、次に次の図に示す場所を見つけてcategory_index.values()はlist(category_index.values()に変更すればよい. 
訓練使用モデル_main.pyトレーニング:(印刷はありませんがtensorboardで表示することをお勧めします.情報は非常に完備しています)

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

inference図をエクスポートするには、次の手順に従います.

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

予測には、次のコードが使用されます(図の位置とインスタンスのピクチャの位置を変更する必要があります).

######## 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()

 
PILライブラリを使用したロード

######## 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()