log("target_rpn_match", target_rpn_match)
log("target_rpn_bbox", target_rpn_bbox)
positive_anchor_ix = np.where(target_rpn_match[:] == 1)[0]
negative_anchor_ix = np.where(target_rpn_match[:] == -1)[0]
neutral_anchor_ix = np.where(target_rpn_match[:] == 0)[0]
positive_anchors = model.anchors[positive_anchor_ix]
negative_anchors = model.anchors[negative_anchor_ix]
neutral_anchors = model.anchors[neutral_anchor_ix]
log("positive_anchors", positive_anchors)
log("negative_anchors", negative_anchors)
log("neutral anchors", neutral_anchors)
# Apply refinement deltas to positive anchors
refined_anchors = utils.apply_box_deltas(
positive_anchors, target_rpn_bbox[:positive_anchors.shape[0]] *
model.config.RPN_BBOX_STD_DEV)
log(
"refined_anchors",
refined_anchors,
)
# In[12]:
# Display positive anchors before refinement (dotted) and
# after refinement (solid).
visualize.draw_boxes(image,
boxes=positive_anchors,
refined_boxes=refined_anchors,
ax=get_ax())
print("image_id: ", image_id, dataset.image_reference(image_id))
# Remove the last dim in mrcnn_class_ids. It's only added
# to satisfy Keras restriction on target shape.
mrcnn_class_ids = mrcnn_class_ids[:, :, 0]
# In[16]:
b = 0
# Restore original image (reverse normalization)
sample_image = modellib.unmold_image(normalized_images[b], config)
# Compute anchor shifts.
indices = np.where(rpn_match[b] == 1)[0]
refined_anchors = utils.apply_box_deltas(
anchors[indices], rpn_bbox[b, :len(indices)] * config.RPN_BBOX_STD_DEV)
log("anchors", anchors)
log("refined_anchors", refined_anchors)
# Get list of positive anchors
positive_anchor_ids = np.where(rpn_match[b] == 1)[0]
print("Positive anchors: {}".format(len(positive_anchor_ids)))
negative_anchor_ids = np.where(rpn_match[b] == -1)[0]
print("Negative anchors: {}".format(len(negative_anchor_ids)))
neutral_anchor_ids = np.where(rpn_match[b] == 0)[0]
print("Neutral anchors: {}".format(len(neutral_anchor_ids)))
# ROI breakdown by class
for c, n in zip(dataset.class_names,
np.bincount(mrcnn_class_ids[b].flatten())):
if n:
def refine_detections(rois, probs, deltas, window, config):
"""Refine classified proposals and filter overlaps and return final
detections.
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)]
"""
# Class IDs per ROI
class_ids = np.argmax(probs, axis=1)
# Class probability of the top class of each ROI
class_scores = probs[np.arange(class_ids.shape[0]), class_ids]
# Class-specific bounding box deltas
deltas_specific = deltas[np.arange(deltas.shape[0]), class_ids]
# Apply bounding box deltas
# Shape: [boxes, (y1, x1, y2, x2)] in normalized coordinates
refined_rois = utils.apply_box_deltas(
rois, deltas_specific * config.BBOX_STD_DEV)
# Convert coordiates to image domain
# TODO: better to keep them normalized until later
height, width = config.IMAGE_SHAPE[:2]
refined_rois *= np.array([height, width, height, width])
# Clip boxes to image window
refined_rois = clip_to_window(window, refined_rois)
# Round and cast to int since we're deadling with pixels now
refined_rois = np.rint(refined_rois).astype(np.int32)
# TODO: Filter out boxes with zero area
# Filter out background boxes
keep = np.where(class_ids > 0)[0]
# Filter out low confidence boxes
if config.DETECTION_MIN_CONFIDENCE:
keep = np.intersect1d(
keep, np.where(class_scores >= config.DETECTION_MIN_CONFIDENCE)[0])
# Apply per-class NMS
pre_nms_class_ids = class_ids[keep]
pre_nms_scores = class_scores[keep]
pre_nms_rois = refined_rois[keep]
nms_keep = []
for class_id in np.unique(pre_nms_class_ids):
# Pick detections of this class
ixs = np.where(pre_nms_class_ids == class_id)[0]
# Apply NMS
class_keep = utils.non_max_suppression(
pre_nms_rois[ixs], pre_nms_scores[ixs],
config.DETECTION_NMS_THRESHOLD)
# Map indicies
class_keep = keep[ixs[class_keep]]
nms_keep = np.union1d(nms_keep, class_keep)
keep = np.intersect1d(keep, nms_keep).astype(np.int32)
# Keep top detections
roi_count = config.DETECTION_MAX_INSTANCES
top_ids = np.argsort(class_scores[keep])[::-1][:roi_count]
keep = keep[top_ids]
# Arrange output as [N, (y1, x1, y2, x2, class_id, score)]
# Coordinates are in image domain.
result = np.hstack((refined_rois[keep],
class_ids[keep][..., np.newaxis],
class_scores[keep][..., np.newaxis]))
return result
ixs = np.random.randint(0, proposals.shape[0], limit)
captions = ["{} {:.3f}".format(class_names[c], s) if c > 0 else ""
for c, s in zip(roi_class_ids[ixs], roi_scores[ixs])]
visualize.draw_boxes(image, boxes=proposals[ixs],
visibilities=np.where(roi_class_ids[ixs] > 0, 2, 1),
captions=captions, title="ROIs Before Refinement",
ax=get_ax())
# Class-specific bounding box shifts.
roi_bbox_specific = mrcnn["deltas"][0, np.arange(proposals.shape[0]), roi_class_ids]
log("roi_bbox_specific", roi_bbox_specific)
# Apply bounding box transformations
# Shape: [N, (y1, x1, y2, x2)]
refined_proposals = utils.apply_box_deltas(
proposals, roi_bbox_specific * config.BBOX_STD_DEV).astype(np.int32)
log("refined_proposals", refined_proposals)
# Show positive proposals
# ids = np.arange(roi_boxes.shape[0]) # Display all
limit = 5
ids = np.random.randint(0, len(roi_positive_ixs), limit) # Display random sample
captions = ["{} {:.3f}".format(class_names[c], s) if c > 0 else ""
for c, s in zip(roi_class_ids[roi_positive_ixs][ids], roi_scores[roi_positive_ixs][ids])]
visualize.draw_boxes(image, boxes=proposals[roi_positive_ixs][ids],
refined_boxes=refined_proposals[roi_positive_ixs][ids],
visibilities=np.where(roi_class_ids[roi_positive_ixs][ids] > 0, 1, 0),
captions=captions, title="ROIs After Refinement",
ax=get_ax())
# Remove boxes classified as background