這邊其實主要是因為程式碼撰寫方便 所以才拆成Detection Target Layer與Detection Layer 前者是在訓練時用到的,後者是在測試時用的,

Detection Layer

refine_detections_graph

根據rois和probs(每個ROI都有總類別個數的probs)和deltas進行檢測的優化，得到固定數量的優化目標。 

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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
def refine_detections_graph(rois, probs, deltas, window, config):
    """Refine classified proposals and filter overlaps and return final
    detections.
    # 輸入為N個rois、N個具有num_classes的probs，scores由probs得出 
    Inputs:
        rois: [N, (y1, x1, y2, x2)] in normalized coordinates
        probs: [N, num_classes]. Class probabilities.
        deltas: [N, num_classes, (dy, dx, log(dh), log(dw))]. Class-specific
                bounding box deltas.
        window: (y1, x1, y2, x2) in image coordinates. The part of the image
            that contains the image excluding the padding.
    Returns detections shaped: [N, (y1, x1, y2, x2, class_id, score)] where
        coordinates are normalized.
    """
    # Class IDs per ROI
    class_ids = tf.argmax(probs, axis=1, output_type=tf.int32)
    # Class probability of the top class of each ROI
    indices = tf.stack([tf.range(probs.shape[0]), class_ids], axis=1)
    class_scores = tf.gather_nd(probs, indices)
    # Class-specific bounding box deltas
    deltas_specific = tf.gather_nd(deltas, indices)
    # Apply bounding box deltas
    # Shape: [boxes, (y1, x1, y2, x2)] in normalized coordinates
    refined_rois = apply_box_deltas_graph(
        rois, deltas_specific * config.BBOX_STD_DEV)
    # Clip boxes to image window
    refined_rois = clip_boxes_graph(refined_rois, window)
    # TODO: Filter out boxes with zero area
    # Filter out background boxes
    keep = tf.where(class_ids > 0)[:, 0]
    # Filter out low confidence boxes
    if config.DETECTION_MIN_CONFIDENCE:
        conf_keep = tf.where(class_scores >= config.DETECTION_MIN_CONFIDENCE)[:, 0]
        keep = tf.sets.set_intersection(tf.expand_dims(keep, 0),
                                        tf.expand_dims(conf_keep, 0))
        keep = tf.sparse_tensor_to_dense(keep)[0]
    
    # 留下既滿足是前景又滿足scores大於MIN_CONFIDENCE的  
    # Apply per-class NMS
    # 1. Prepare variables
    pre_nms_class_ids = tf.gather(class_ids, keep)
    pre_nms_scores = tf.gather(class_scores, keep)
    pre_nms_rois = tf.gather(refined_rois,   keep)
    unique_pre_nms_class_ids = tf.unique(pre_nms_class_ids)[0]
    def nms_keep_map(class_id):
        """Apply Non-Maximum Suppression on ROIs of the given class."""
        # Indices of ROIs of the given class
        ixs = tf.where(tf.equal(pre_nms_class_ids, class_id))[:, 0]
        # Apply NMS
        class_keep = tf.image.non_max_suppression(
                tf.gather(pre_nms_rois, ixs),
                tf.gather(pre_nms_scores, ixs),
                max_output_size=config.DETECTION_MAX_INSTANCES,
                iou_threshold=config.DETECTION_NMS_THRESHOLD)
        # Map indicies
        class_keep = tf.gather(keep, tf.gather(ixs, class_keep))
        # Pad with -1 so returned tensors have the same shape
        gap = config.DETECTION_MAX_INSTANCES - tf.shape(class_keep)[0]
        class_keep = tf.pad(class_keep, [(0, gap)],
                            mode='CONSTANT', constant_values=-1)
        # Set shape so map_fn() can infer result shape
        class_keep.set_shape([config.DETECTION_MAX_INSTANCES])
        return class_keep
    # 2. Map over class IDs
    # 在nms_keep_map內分類別的進行NMS。 
    nms_keep = tf.map_fn(nms_keep_map, unique_pre_nms_class_ids,
                         dtype=tf.int64)
    # 3. Merge results into one list, and remove -1 padding
    nms_keep = tf.reshape(nms_keep, [-1])
    nms_keep = tf.gather(nms_keep, tf.where(nms_keep > -1)[:, 0])
    # 4. Compute intersection between keep and nms_keep
    keep = tf.sets.set_intersection(tf.expand_dims(keep, 0),
                                    tf.expand_dims(nms_keep, 0))
    keep = tf.sparse_tensor_to_dense(keep)[0]
    # Keep top detections
    roi_count = config.DETECTION_MAX_INSTANCES
    class_scores_keep = tf.gather(class_scores, keep)
    num_keep = tf.minimum(tf.shape(class_scores_keep)[0], roi_count)
    top_ids = tf.nn.top_k(class_scores_keep, k=num_keep, sorted=True)[1]
    keep = tf.gather(keep, top_ids)
    # Arrange output as [N, (y1, x1, y2, x2, class_id, score)]
    # Coordinates are normalized.
    detections = tf.concat([
        tf.gather(refined_rois, keep),
        tf.to_float(tf.gather(class_ids, keep))[..., tf.newaxis],
        tf.gather(class_scores, keep)[..., tf.newaxis]
        ], axis=1)
    # Pad with zeros if detections < DETECTION_MAX_INSTANCES
    gap = config.DETECTION_MAX_INSTANCES - tf.shape(detections)[0]
    detections = tf.pad(detections, [(0, gap), (0, 0)], "CONSTANT")
    return detections
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
class DetectionLayer(KE.Layer):
    """Takes classified proposal boxes and their bounding box deltas and
    returns the final detection boxes.
    Returns:
    [batch, num_detections, (y1, x1, y2, x2, class_id, class_score)] where
    coordinates are normalized.
    """
    def __init__(self, config=None, **kwargs):
        super(DetectionLayer, self).__init__(**kwargs)
        self.config = config
    def call(self, inputs):
        rois = inputs[0]
        mrcnn_class = inputs[1]
        mrcnn_bbox = inputs[2]
        image_meta = inputs[3]
        # Get windows of images in normalized coordinates. Windows are the area
        # in the image that excludes the padding.
        # Use the shape of the first image in the batch to normalize the window
        # because we know that all images get resized to the same size.
        m = parse_image_meta_graph(image_meta)
        image_shape = m['image_shape'][0]
        window = norm_boxes_graph(m['window'], image_shape[:2])
        
        # Run detection refinement graph on each item in the batch
        detections_batch = utils.batch_slice(
            [rois, mrcnn_class, mrcnn_bbox, window],
            lambda x, y, w, z: refine_detections_graph(x, y, w, z, self.config),
            self.config.IMAGES_PER_GPU)
        # Reshape output
        # [batch, num_detections, (y1, x1, y2, x2, class_score)] in
        # normalized coordinates
        return tf.reshape(
            detections_batch,
            [self.config.BATCH_SIZE, self.config.DETECTION_MAX_INSTANCES, 6])
    def compute_output_shape(self, input_shape):
        return (None, self.config.DETECTION_MAX_INSTANCES, 6)