Fix comments in DetectionTargetLayer (#962)

* fix comment in DetectionTargetLayer
* fix comment of target_deltas' shape
* make parenthesis compatible

mrcnn/model.py

@@ -487,7 +487,7 @@ def detection_targets_graph(proposals, gt_class_ids, gt_boxes, gt_masks, config)
     generates target class IDs, bounding box deltas, and masks for each.
 
     Inputs:
-    proposals: [N, (y1, x1, y2, x2)] in normalized coordinates. Might
+    proposals: [POST_NMS_ROIS_TRAINING, (y1, x1, y2, x2)] in normalized coordinates. Might
                be zero padded if there are not enough proposals.
     gt_class_ids: [MAX_GT_INSTANCES] int class IDs
     gt_boxes: [MAX_GT_INSTANCES, (y1, x1, y2, x2)] in normalized coordinates.
@@ -497,9 +497,8 @@ def detection_targets_graph(proposals, gt_class_ids, gt_boxes, gt_masks, config)
     and masks.
     rois: [TRAIN_ROIS_PER_IMAGE, (y1, x1, y2, x2)] in normalized coordinates
     class_ids: [TRAIN_ROIS_PER_IMAGE]. Integer class IDs. Zero padded.
-    deltas: [TRAIN_ROIS_PER_IMAGE, NUM_CLASSES, (dy, dx, log(dh), log(dw))]
-            Class-specific bbox refinements.
-    masks: [TRAIN_ROIS_PER_IMAGE, height, width). Masks cropped to bbox
+    deltas: [TRAIN_ROIS_PER_IMAGE, (dy, dx, log(dh), log(dw))]
+    masks: [TRAIN_ROIS_PER_IMAGE, height, width]. Masks cropped to bbox
            boundaries and resized to neural network output size.
 
     Note: Returned arrays might be zero padded if not enough target ROIs.
@@ -534,7 +533,7 @@ def detection_targets_graph(proposals, gt_class_ids, gt_boxes, gt_masks, config)
     # Compute overlaps matrix [proposals, gt_boxes]
     overlaps = overlaps_graph(proposals, gt_boxes)
 
-    # Compute overlaps with crowd boxes [anchors, crowds]
+    # Compute overlaps with crowd boxes [proposals, crowd_boxes]
     crowd_overlaps = overlaps_graph(proposals, crowd_boxes)
     crowd_iou_max = tf.reduce_max(crowd_overlaps, axis=1)
     no_crowd_bool = (crowd_iou_max < 0.001)
@@ -637,10 +636,8 @@ class DetectionTargetLayer(KE.Layer):
     rois: [batch, TRAIN_ROIS_PER_IMAGE, (y1, x1, y2, x2)] in normalized
           coordinates
     target_class_ids: [batch, TRAIN_ROIS_PER_IMAGE]. Integer class IDs.
-    target_deltas: [batch, TRAIN_ROIS_PER_IMAGE, NUM_CLASSES,
-                    (dy, dx, log(dh), log(dw), class_id)]
-                   Class-specific bbox refinements.
-    target_mask: [batch, TRAIN_ROIS_PER_IMAGE, height, width)
+    target_deltas: [batch, TRAIN_ROIS_PER_IMAGE, (dy, dx, log(dh), log(dw)]
+    target_mask: [batch, TRAIN_ROIS_PER_IMAGE, height, width]
                  Masks cropped to bbox boundaries and resized to neural
                  network output size.