tf源码中的object_detection_tutorial.ipynb文件

Posted kongweisi

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了tf源码中的object_detection_tutorial.ipynb文件相关的知识,希望对你有一定的参考价值。

今天看到原来下载的tf源码的目标检测源码中test的代码不知道跑哪儿去了,这里记录一下。。。

Imports

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

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 utils import ops as utils_ops

if tf.__version__ < 1.4.0:
  raise ImportError(Please upgrade your tensorflow installation to v1.4.* or later!)
# This is needed to display the images.
%matplotlib inline

Object detection imports

Here are the imports from the object detection module.

from utils import label_map_util

from utils import visualization_utils as vis_util

Model preparation

Variables

Any model exported using the export_inference_graph.py tool can be loaded here simply by changing PATH_TO_CKPT to point to a new .pb file.

By default we use an "SSD with Mobilenet" model here. See the detection model zoo for a list of other models that can be run out-of-the-box with varying speeds and accuracies.

:
# What model to download.
MODEL_NAME = ssd_mobilenet_v1_coco_2017_11_17
MODEL_FILE = MODEL_NAME + .tar.gz
DOWNLOAD_BASE = http://download.tensorflow.org/models/object_detection/

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

Download Model

opener = urllib.request.URLopener()
opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
tar_file = tarfile.open(MODEL_FILE)
for file in tar_file.getmembers():
  file_name = os.path.basename(file.name)
  if frozen_inference_graph.pb in file_name:
    tar_file.extract(file, os.getcwd())

Load a (frozen) 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=‘‘)

Loading label map

Label maps map indices to category names, so that when our convolution network predicts 5, we know that this corresponds to airplane. 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)

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

# For the sake of simplicity we will use only 2 images:
# image1.jpg
# image2.jpg
# If you want to test the code with your images, just add path to the images to the TEST_IMAGE_PATHS.
PATH_TO_TEST_IMAGES_DIR = test_images
TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, image{}.jpg.format(i)) for i in range(1, 3) ]

# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)
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 TEST_IMAGE_PATHS:
  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)

 

总结:实际测试的时候多使用glob模块(或os)读文件,opencv(+矩形框)展示检测效果。

 

以上是关于tf源码中的object_detection_tutorial.ipynb文件的主要内容,如果未能解决你的问题,请参考以下文章

STM32MP157开发笔记 | 04 - TF-Aubootlinux内核源码获取编译烧写

STM32MP157开发笔记 | 04 - TF-Aubootlinux内核源码获取编译烧写

STM32MP157开发笔记 | 04 - TF-Aubootlinux内核源码获取编译烧写

开源词袋模型DBow3原理&源码

附源码TensorFlow动态图(Eager模式)的那些神坑

M283-bsp包问题