Object Detection using Tensorflow

Question

I am following tensorflow object detection tutorial for Oxford-IIIT Pets Dataset: https://github.com/tensorflow/models/blob/master/object_detection/g3doc/running_pets.md

I have successfully generated the "frozen_inference_graph.pb" from the latest checkpoint. How I can test the inference graph - "frozen_inference_graph.pb" and pet labels - "pet_label_map.pbtxt" on an image.

I have tried using jupytor notebook but nothing gets detected in the image. I have also used following python code for detecting "dog" and "cat" but nothing gets detected. Python code is given below:

import os
import cv2
import time
import argparse
import multiprocessing
import numpy as np
import tensorflow as tf

from utils import FPS, WebcamVideoStream
from multiprocessing import Queue, Pool
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util

PATH_TO_CKPT = os.path.join('frozen_inference_graph.pb')

PATH_TO_LABELS = os.path.join('pet_label_map.pbtxt')

NUM_CLASSES = 37

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)


def detect_objects(image_np, sess, detection_graph):
    # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
    image_np_expanded = np.expand_dims(image_np, axis=0)
    image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')

    # Each box represents a part of the image where a particular object was detected.
    boxes = detection_graph.get_tensor_by_name('detection_boxes:0')

    # Each score represent how level of confidence for each of the objects.
    # Score is shown on the result image, together with the class label.
    scores = detection_graph.get_tensor_by_name('detection_scores:0')
    classes = detection_graph.get_tensor_by_name('detection_classes:0')
    num_detections = detection_graph.get_tensor_by_name('num_detections:0')

    # Actual detection.
    (boxes, scores, classes, num_detections) = sess.run(
        [boxes, scores, classes, num_detections],
        feed_dict={image_tensor: image_np_expanded})

    # Visualization of the results of a detection.
    vis_util.visualize_boxes_and_labels_on_image_array(
        image_np,
        np.squeeze(boxes),
        np.squeeze(classes).astype(np.int32),
        np.squeeze(scores),
        category_index,
        use_normalized_coordinates=True,
        line_thickness=8)
    return image_np


def worker(input_q, output_q):
    # 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='')

        sess = tf.Session(graph=detection_graph)
    frame = input_q.get()
    output_q.put(detect_objects(frame, sess, detection_graph))

    sess.close()


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('-src', '--source', dest='video_source', type=int,
                        default=0, help='Device index of the camera.')
    parser.add_argument('-wd', '--width', dest='width', type=int,
                        default=20, help='Width of the frames in the video stream.')
    parser.add_argument('-ht', '--height', dest='height', type=int,
                        default=20, help='Height of the frames in the video stream.')
    parser.add_argument('-num-w', '--num-workers', dest='num_workers', type=int,
                        default=2, help='Number of workers.')
    parser.add_argument('-q-size', '--queue-size', dest='queue_size', type=int,
                        default=5, help='Size of the queue.')
    args = parser.parse_args()

    logger = multiprocessing.log_to_stderr()
    logger.setLevel(multiprocessing.SUBDEBUG)

    input_q = Queue(maxsize=args.queue_size)
    output_q = Queue(maxsize=args.queue_size)
    pool = Pool(args.num_workers, worker, (input_q, output_q))


    frame = cv2.imread("image2.jpg");

    input_q.put(frame)


    cv2.imshow('Video', output_q.get())


    cv2.waitKey(0)
    cv2.destroyAllWindows()

Any help will be greatly appreciated related to running the inference graph on actual image or debugging if nothing gets detected.

Answer 1

if you are using Tensorflow API, go to the folder models/research, open there a console.

In the research folder run command protoc object_detection/protos/*.proto --python_out=. and then export PYTHONPATH=$PYTHONPATH:pwd:pwd/slim.

Then run cd object_detection to change folder in the console and open jupyter notebook in current folder.

In jupyter notebook's home find the file object_detection_tutorial.ipynb, modify it so that it suits your purposes.

Answer 2

What are the outputs of boxes, scores and classes? Can you print them? If you get numbers from them, maybe you just need to change a few lines in your code to properly visualize the results.

For test, you can use:

        vis_util.save_image_array_as_png(image,'./outputImg.png')
        #print(image.shape)
        print('image saved')
        img=mpimg.imread('./outputImg.png')
        imgplot = plt.imshow(img)
        plt.show()