In [26]:

    

import os
import time
import argparse
import multiprocessing
import numpy as np
import tensorflow as tf
from matplotlib import pyplot as plt


    

In [27]:

    

from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util


    

In [28]:

    

CWD_PATH = os.getcwd()

# Path to frozen detection graph. This is the actual model that is used for the object detection.
MODEL_NAME = 'ssd_mobilenet_v1_coco_11_06_2017'
PATH_TO_CKPT = os.path.join(CWD_PATH, 'object_detection', 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(CWD_PATH, 'object_detection', 'data', 'mscoco_label_map.pbtxt')


    

In [29]:

    

NUM_CLASSES = 90


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)


    

In [30]:

    

def detect_objects(image_np, sess, detection_graph):
    image_np_expanded = np.expand_dims(image_np, axis=0)
    image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')

    
    boxes = detection_graph.get_tensor_by_name('detection_boxes:0')

   
    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')

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


    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


    

In [31]:

    

PATH_TO_TEST_IMAGES_DIR = 'object_detection/test_images'
TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image{}.jpg'.format(i)) for i in range(1, 3) ]

IMAGE_SIZE = (12, 8)


    

In [32]:

    

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)


    

In [33]:

    

from PIL import Image
for image_path in TEST_IMAGE_PATHS:
    image = Image.open(image_path)
    image_np = load_image_into_numpy_array(image)
    plt.imshow(image_np)
    print(image.size, image_np.shape)


    

    




((1024, 636), (636, 1024, 3))
((1024, 636), (636, 1024, 3))

In [ ]:

    

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='')


    

In [ ]:

    

with detection_graph.as_default():
    with tf.Session(graph=detection_graph) as sess:
        for image_path in TEST_IMAGE_PATHS:
            image = Image.open(image_path)
            image_np = load_image_into_numpy_array(image)
            image_process = detect_objects(image_np, sess, detection_graph)
            print(image_process.shape)
            plt.figure(figsize=IMAGE_SIZE)
            plt.imshow(image_process)


    

In [ ]:

    

from moviepy.editor import VideoFileClip
from IPython.display import HTML


    

In [ ]:

    

def process_image(image):
    with detection_graph.as_default():
        with tf.Session(graph=detection_graph) as sess:
            image_process = detect_objects(image, sess, detection_graph)
            return image_process


    

In [ ]:

    

white_output = 'output.mp4'
clip1 = VideoFileClip("input.mp4").subclip(2,3)
white_clip = clip1.fl_image(process_image) #NOTE: this function expects color images!!s
%time white_clip.write_videofile(white_output, audio=False)