backend/detector_utils.py at master · CleanEarthIO/backend · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
from object_detection.utils import ops as utils_ops
import tensorflow as tf
import numpy as np


def load_inference_graph():
    detection_graph = tf.Graph()
    with detection_graph.as_default():
        od_graph_def = tf.compat.v1.GraphDef()
        with tf.io.gfile.GFile('frozen_inference_graph.pb', 'rb') as fid:
            serialized_graph = fid.read()
            od_graph_def.ParseFromString(serialized_graph)
            tf.import_graph_def(od_graph_def, name='')
        sess = tf.compat.v1.Session(graph=detection_graph)
    return detection_graph, sess


def load_image_into_numpy_array(img):
    (im_width, im_height) = img.size
    return np.array(img.getdata()).reshape((im_height, im_width, 3)).astype(np.uint8)


def rescale(im_width, im_height, img):
    aspect = im_width / im_height
    new_width = (640 * aspect)
    new_height = (new_width / aspect)
    img = img.resize((int(new_width), int(new_height)), resample=0)
    return img


def run_inference_image(image_np, sess):
    ops = tf.compat.v1.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.compat.v1.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_np.shape[0], image_np.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.compat.v1.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_np, 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