Test script for TF's Object Detection API

object_detection_tutorial.py

# coding: utf-8

# NOTE: PUT THIS FILE IN models/research/object_detection/

# Object Detection Demo
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

from tqdm import tqdm
import cv2
import argparse

argparser = argparse.ArgumentParser(description='Test script for models')
argparser.add_argument('-i','--input',
                        help='path to an image or a video (mp4 format)')
argparser.add_argument('-n','--num_classes',
                        help='number of classes in your dataset')
argparser.add_argument('-m','--modelname',
                        help='name of generated detection graph')
argparser.add_argument('-l','--labelmap',
                        help='name of label map (.pbtxt)')
argparser.add_argument('-o','--output_video',
                        help='name of output video',
                        default='out.mp4')

args = argparser.parse_args()

MODEL_INPUT = args.input
MODEL_NAME = args.modelname
LABEL_MAP = args.labelmap
NUM_CLASSES = int(args.num_classes)
OUTPUT_VIDEO = args.output_video

# start the input feed
cap = cv2.VideoCapture(MODEL_INPUT)

# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
from object_detection.utils import ops as utils_ops

if tf.__version__ < '1.4.0':
  raise ImportError('Please upgrade your tensorflow installation to v1.4.* or later!')

## 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
# 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', LABEL_MAP)

## 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)

# # Detection
# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)
with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
    # Definite input and output Tensors for detection_graph
    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.
    detection_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.
    detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
    detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
    num_detections = detection_graph.get_tensor_by_name('num_detections:0')

    nb_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
    frame_h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
    frame_w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))

    video_writer = cv2.VideoWriter(OUTPUT_VIDEO,
                           cv2.VideoWriter_fourcc(*'MPEG'),
                           50.0,
                           (frame_w, frame_h))

    for i in tqdm(list(range(nb_frames))):
        ret, image_np = cap.read()
        if ret:
            # 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.
            (boxes, scores, classes, num) = sess.run(
              [detection_boxes, detection_scores, detection_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,
              min_score_thresh=0.5,
              line_thickness=10)
            video_writer.write(np.uint8(image_np))

    cap.release()
    video_writer.release()