def _get_retinanet_blobs(foas, all_anchors, gt_boxes, gt_classes, im_width,
im_height):
total_anchors = all_anchors.shape[0]
logger.debug('Getting mad blobs: im_height {} im_width: {}'.format(
im_height, im_width))
inds_inside = np.arange(all_anchors.shape[0]) #0, 1... 371349
anchors = all_anchors
num_inside = len(inds_inside) #371349
logger.debug('total_anchors: {}'.format(total_anchors))
logger.debug('inds_inside: {}'.format(num_inside))
logger.debug('anchors.shape: {}'.format(anchors.shape))
# Compute anchor labels:
# label=1 is positive, 0 is negative, -1 is don't care (ignore)
labels = np.empty((num_inside, ), dtype=np.float32)
labels.fill(-1)
if len(gt_boxes) > 0:
# Compute overlaps between the anchors and the gt boxes overlaps
anchor_by_gt_overlap = box_utils.bbox_overlaps(
anchors, gt_boxes) # (371349, 17)
# Map from anchor to gt box that has highest overlap
anchor_to_gt_argmax = anchor_by_gt_overlap.argmax(
axis=1) # (371349,) this is index
# For each anchor, amount of overlap with most overlapping gt box
anchor_to_gt_max = anchor_by_gt_overlap[ # (371349,) this is area
np.arange(num_inside), anchor_to_gt_argmax]
# Map from gt box to an anchor that has highest overlap
gt_to_anchor_argmax = anchor_by_gt_overlap.argmax(
axis=0) # (17,) index
# For each gt box, amount of overlap with most overlapping anchor
gt_to_anchor_max = anchor_by_gt_overlap[ # (17,) area
gt_to_anchor_argmax,
np.arange(anchor_by_gt_overlap.shape[1])]
# Find all anchors that share the max overlap amount
# (this includes many ties)
anchors_with_max_overlap = np.where( # (21,) find all anchors with most overlaps
anchor_by_gt_overlap == gt_to_anchor_max)[0]
# Fg label: for each gt use anchors with highest overlap
# (including ties)
gt_inds = anchor_to_gt_argmax[anchors_with_max_overlap] # 416
labels[anchors_with_max_overlap] = gt_classes[gt_inds]
# Fg label: above threshold IOU
inds = anchor_to_gt_max >= cfg.RETINANET.POSITIVE_OVERLAP
gt_inds = anchor_to_gt_argmax[inds]
labels[inds] = gt_classes[
gt_inds] # for all anchors, inds are valued by gt_inds, this gives class values 1~80
fg_inds = np.where(labels >= 1)[0]
bg_inds = np.where(anchor_to_gt_max < cfg.RETINANET.NEGATIVE_OVERLAP)[0]
labels[bg_inds] = 0
num_fg, num_bg = len(fg_inds), len(bg_inds)
bbox_targets = np.zeros((num_inside, 4), dtype=np.float32)
bbox_targets[fg_inds, :] = data_utils.compute_targets(
anchors[fg_inds, :], gt_boxes[anchor_to_gt_argmax[fg_inds], :])
# Map up to original set of anchors
labels = data_utils.unmap(labels, total_anchors, inds_inside, fill=-1)
bbox_targets = data_utils.unmap(bbox_targets,
total_anchors,
inds_inside,
fill=0)
# Split the generated labels, etc. into labels per each field of anchors
blobs_out = []
start_idx = 0
for foa in foas:
H = foa.field_size
W = foa.field_size
end_idx = start_idx + H * W
_labels = labels[start_idx:end_idx]
triangle_start_idx = start_idx
_bbox_targets = bbox_targets[start_idx:end_idx, :]
start_idx = end_idx
# labels output with shape (1, height, width)
_labels = _labels.reshape((1, 1, H, W))
# bbox_targets output with shape (1, 4 * A, height, width)
_bbox_targets = _bbox_targets.reshape(
(1, H, W, 4)).transpose(0, 3, 1, 2)
stride = foa.stride
w = int(im_width / stride)
h = int(im_height / stride)
# data for select_smooth_l1 loss
num_classes = cfg.MODEL.NUM_CLASSES - 1
inds_4d = np.where(_labels > 0)
M = len(inds_4d)
_roi_bbox_targets = np.zeros((0, 4))
_roi_fg_bbox_locs = np.zeros((0, 4))
if M > 0:
im_inds, y, x = inds_4d[0], inds_4d[2], inds_4d[3]
_roi_bbox_targets = np.zeros((len(im_inds), 4))
_roi_fg_bbox_locs = np.zeros((len(im_inds), 4))
lbls = _labels[im_inds, :, y, x]
for i, lbl in enumerate(lbls):
l = lbl[0] - 1
if not cfg.RETINANET.CLASS_SPECIFIC_BBOX:
l = 0
assert l >= 0 and l < num_classes, 'label out of the range'
_roi_bbox_targets[i, :] = _bbox_targets[:, :, y[i], x[i]]
_roi_fg_bbox_locs[i, :] = np.array([[0, l, y[i], x[i]]])
if _roi_bbox_targets.astype(
np.float32).shape[0] == 0 and _roi_fg_bbox_locs.astype(
np.float32).shape[0] == 0:
blobs_out.append(
dict(
retnet_cls_labels=_labels[:, :, 0:h, 0:w].astype(np.int32),
retnet_roi_bbox_targets=_roi_bbox_targets.astype(
np.float32),
retnet_roi_fg_bbox_locs=_roi_fg_bbox_locs.astype(
np.float32),
# retnet_roi_bbox_targets=np.array([[0, 0, 0, 0]]),
# retnet_roi_fg_bbox_locs=np.array([[0, 0, 0, 0]]),
))
# we don't add zero padding here, because this is inside the loop of foa, we don't
# want every anchor to have padding, instead we want to firstly sum all anchors in a FPN of an image, and then check if it's emtpy
else:
blobs_out.append(
dict(
retnet_cls_labels=_labels[:, :, 0:h, 0:w].astype(np.int32),
retnet_roi_bbox_targets=_roi_bbox_targets.astype(
np.float32),
retnet_roi_fg_bbox_locs=_roi_fg_bbox_locs.astype(
np.float32),
))
out_num_fg = np.array([num_fg + 1.0], dtype=np.float32)
out_num_bg = (np.array([num_bg + 1.0]) * (cfg.MODEL.NUM_CLASSES - 1) +
out_num_fg * (cfg.MODEL.NUM_CLASSES - 2))
return blobs_out, out_num_fg, out_num_bg
def _get_rpn_blobs(im_height, im_width, foas, all_anchors, gt_boxes):
total_anchors = all_anchors.shape[0]
straddle_thresh = cfg.TRAIN.RPN_STRADDLE_THRESH
if straddle_thresh >= 0:
# Only keep anchors inside the image by a margin of straddle_thresh
# Set TRAIN.RPN_STRADDLE_THRESH to -1 (or a large value) to keep all
# anchors
inds_inside = np.where(
(all_anchors[:, 0] >= -straddle_thresh) &
(all_anchors[:, 1] >= -straddle_thresh) &
(all_anchors[:, 2] < im_width + straddle_thresh) &
(all_anchors[:, 3] < im_height + straddle_thresh)
)[0]
# keep only inside anchors
anchors = all_anchors[inds_inside, :]
else:
inds_inside = np.arange(all_anchors.shape[0])
anchors = all_anchors
num_inside = len(inds_inside)
logger.debug('total_anchors: {}'.format(total_anchors))
logger.debug('inds_inside: {}'.format(num_inside))
logger.debug('anchors.shape: {}'.format(anchors.shape))
# Compute anchor labels:
# label=1 is positive, 0 is negative, -1 is don't care (ignore)
labels = np.empty((num_inside, ), dtype=np.int32)
labels.fill(-1)
if len(gt_boxes) > 0:
# Compute overlaps between the anchors and the gt boxes overlaps
anchor_by_gt_overlap = box_utils.bbox_overlaps(anchors, gt_boxes)
# Map from anchor to gt box that has highest overlap
anchor_to_gt_argmax = anchor_by_gt_overlap.argmax(axis=1)
# For each anchor, amount of overlap with most overlapping gt box
anchor_to_gt_max = anchor_by_gt_overlap[np.arange(num_inside),
anchor_to_gt_argmax]
# Map from gt box to an anchor that has highest overlap
gt_to_anchor_argmax = anchor_by_gt_overlap.argmax(axis=0)
# For each gt box, amount of overlap with most overlapping anchor
gt_to_anchor_max = anchor_by_gt_overlap[
gt_to_anchor_argmax,
np.arange(anchor_by_gt_overlap.shape[1])
]
# Find all anchors that share the max overlap amount
# (this includes many ties)
anchors_with_max_overlap = np.where(
anchor_by_gt_overlap == gt_to_anchor_max
)[0]
# Fg label: for each gt use anchors with highest overlap
# (including ties)
labels[anchors_with_max_overlap] = 1
# Fg label: above threshold IOU
labels[anchor_to_gt_max >= cfg.TRAIN.RPN_POSITIVE_OVERLAP] = 1
# subsample positive labels if we have too many
num_fg = int(cfg.TRAIN.RPN_FG_FRACTION * cfg.TRAIN.RPN_BATCH_SIZE_PER_IM)
fg_inds = np.where(labels == 1)[0]
if len(fg_inds) > num_fg:
disable_inds = npr.choice(
fg_inds, size=(len(fg_inds) - num_fg), replace=False
)
labels[disable_inds] = -1
fg_inds = np.where(labels == 1)[0]
# subsample negative labels if we have too many
# (samples with replacement, but since the set of bg inds is large most
# samples will not have repeats)
num_bg = cfg.TRAIN.RPN_BATCH_SIZE_PER_IM - np.sum(labels == 1)
bg_inds = np.where(anchor_to_gt_max < cfg.TRAIN.RPN_NEGATIVE_OVERLAP)[0]
if len(bg_inds) > num_bg:
enable_inds = bg_inds[npr.randint(len(bg_inds), size=num_bg)]
labels[enable_inds] = 0
bg_inds = np.where(labels == 0)[0]
bbox_targets = np.zeros((num_inside, 4), dtype=np.float32)
bbox_targets[fg_inds, :] = data_utils.compute_targets(
anchors[fg_inds, :], gt_boxes[anchor_to_gt_argmax[fg_inds], :]
)
# Bbox regression loss has the form:
# loss(x) = weight_outside * L(weight_inside * x)
# Inside weights allow us to set zero loss on an element-wise basis
# Bbox regression is only trained on positive examples so we set their
# weights to 1.0 (or otherwise if config is different) and 0 otherwise
bbox_inside_weights = np.zeros((num_inside, 4), dtype=np.float32)
bbox_inside_weights[labels == 1, :] = (1.0, 1.0, 1.0, 1.0)
# The bbox regression loss only averages by the number of images in the
# mini-batch, whereas we need to average by the total number of example
# anchors selected
# Outside weights are used to scale each element-wise loss so the final
# average over the mini-batch is correct
bbox_outside_weights = np.zeros((num_inside, 4), dtype=np.float32)
# uniform weighting of examples (given non-uniform sampling)
num_examples = np.sum(labels >= 0)
bbox_outside_weights[labels == 1, :] = 1.0 / num_examples
bbox_outside_weights[labels == 0, :] = 1.0 / num_examples
# Map up to original set of anchors
labels = data_utils.unmap(labels, total_anchors, inds_inside, fill=-1)
bbox_targets = data_utils.unmap(
bbox_targets, total_anchors, inds_inside, fill=0
)
bbox_inside_weights = data_utils.unmap(
bbox_inside_weights, total_anchors, inds_inside, fill=0
)
bbox_outside_weights = data_utils.unmap(
bbox_outside_weights, total_anchors, inds_inside, fill=0
)
# Split the generated labels, etc. into labels per each field of anchors
blobs_out = []
start_idx = 0
for foa in foas:
H = foa.field_size
W = foa.field_size
A = foa.num_cell_anchors
end_idx = start_idx + H * W * A
_labels = labels[start_idx:end_idx]
_bbox_targets = bbox_targets[start_idx:end_idx, :]
_bbox_inside_weights = bbox_inside_weights[start_idx:end_idx, :]
_bbox_outside_weights = bbox_outside_weights[start_idx:end_idx, :]
start_idx = end_idx
# labels output with shape (1, A, height, width)
_labels = _labels.reshape((1, H, W, A)).transpose(0, 3, 1, 2)
# bbox_targets output with shape (1, 4 * A, height, width)
_bbox_targets = _bbox_targets.reshape(
(1, H, W, A * 4)).transpose(0, 3, 1, 2)
# bbox_inside_weights output with shape (1, 4 * A, height, width)
_bbox_inside_weights = _bbox_inside_weights.reshape(
(1, H, W, A * 4)).transpose(0, 3, 1, 2)
# bbox_outside_weights output with shape (1, 4 * A, height, width)
_bbox_outside_weights = _bbox_outside_weights.reshape(
(1, H, W, A * 4)).transpose(0, 3, 1, 2)
blobs_out.append(
dict(
rpn_labels_int32_wide=_labels,
rpn_bbox_targets_wide=_bbox_targets,
rpn_bbox_inside_weights_wide=_bbox_inside_weights,
rpn_bbox_outside_weights_wide=_bbox_outside_weights
)
)
return blobs_out[0] if len(blobs_out) == 1 else blobs_out
def _get_retinanet_blobs(
foas, all_anchors, gt_boxes, gt_classes, im_width, im_height):
total_anchors = all_anchors.shape[0]
logger.debug('Getting mad blobs: im_height {} im_width: {}'.format(
im_height, im_width))
inds_inside = np.arange(all_anchors.shape[0])
anchors = all_anchors
num_inside = len(inds_inside)
logger.debug('total_anchors: {}'.format(total_anchors))
logger.debug('inds_inside: {}'.format(num_inside))
logger.debug('anchors.shape: {}'.format(anchors.shape))
# Compute anchor labels:
# label=1 is positive, 0 is negative, -1 is don't care (ignore)
labels = np.empty((num_inside, ), dtype=np.float32)
labels.fill(-1)
if len(gt_boxes) > 0:
# Compute overlaps between the anchors and the gt boxes overlaps
anchor_by_gt_overlap = box_utils.bbox_overlaps(anchors, gt_boxes)
# Map from anchor to gt box that has highest overlap
anchor_to_gt_argmax = anchor_by_gt_overlap.argmax(axis=1)
# For each anchor, amount of overlap with most overlapping gt box
anchor_to_gt_max = anchor_by_gt_overlap[
np.arange(num_inside), anchor_to_gt_argmax]
# Map from gt box to an anchor that has highest overlap
gt_to_anchor_argmax = anchor_by_gt_overlap.argmax(axis=0)
# For each gt box, amount of overlap with most overlapping anchor
gt_to_anchor_max = anchor_by_gt_overlap[
gt_to_anchor_argmax, np.arange(anchor_by_gt_overlap.shape[1])]
# Find all anchors that share the max overlap amount
# (this includes many ties)
anchors_with_max_overlap = np.where(
anchor_by_gt_overlap == gt_to_anchor_max)[0]
# Fg label: for each gt use anchors with highest overlap
# (including ties)
gt_inds = anchor_to_gt_argmax[anchors_with_max_overlap]
labels[anchors_with_max_overlap] = gt_classes[gt_inds]
# Fg label: above threshold IOU
inds = anchor_to_gt_max >= cfg.RETINANET.POSITIVE_OVERLAP
gt_inds = anchor_to_gt_argmax[inds]
labels[inds] = gt_classes[gt_inds]
fg_inds = np.where(labels >= 1)[0]
bg_inds = np.where(anchor_to_gt_max < cfg.RETINANET.NEGATIVE_OVERLAP)[0]
labels[bg_inds] = 0
num_fg, num_bg = len(fg_inds), len(bg_inds)
bbox_targets = np.zeros((num_inside, 4), dtype=np.float32)
bbox_targets[fg_inds, :] = data_utils.compute_targets(
anchors[fg_inds, :], gt_boxes[anchor_to_gt_argmax[fg_inds], :])
# Map up to original set of anchors
labels = data_utils.unmap(labels, total_anchors, inds_inside, fill=-1)
bbox_targets = data_utils.unmap(bbox_targets, total_anchors, inds_inside, fill=0)
# Split the generated labels, etc. into labels per each field of anchors
blobs_out = []
start_idx = 0
for foa in foas:
H = foa.field_size
W = foa.field_size
end_idx = start_idx + H * W
_labels = labels[start_idx:end_idx]
_bbox_targets = bbox_targets[start_idx:end_idx, :]
start_idx = end_idx
# labels output with shape (1, height, width)
_labels = _labels.reshape((1, 1, H, W))
# bbox_targets output with shape (1, 4 * A, height, width)
_bbox_targets = _bbox_targets.reshape((1, H, W, 4)).transpose(0, 3, 1, 2)
stride = foa.stride
w = int(im_width / stride)
h = int(im_height / stride)
# data for select_smooth_l1 loss
num_classes = cfg.MODEL.NUM_CLASSES - 1
inds_4d = np.where(_labels > 0)
M = len(inds_4d)
_roi_bbox_targets = np.zeros((0, 4))
_roi_fg_bbox_locs = np.zeros((0, 4))
if M > 0:
im_inds, y, x = inds_4d[0], inds_4d[2], inds_4d[3]
_roi_bbox_targets = np.zeros((len(im_inds), 4))
_roi_fg_bbox_locs = np.zeros((len(im_inds), 4))
lbls = _labels[im_inds, :, y, x]
for i, lbl in enumerate(lbls):
l = lbl[0] - 1
if not cfg.RETINANET.CLASS_SPECIFIC_BBOX:
l = 0
assert l >= 0 and l < num_classes, 'label out of the range'
_roi_bbox_targets[i, :] = _bbox_targets[:, :, y[i], x[i]]
_roi_fg_bbox_locs[i, :] = np.array([[0, l, y[i], x[i]]])
blobs_out.append(
dict(
retnet_cls_labels=_labels[:, :, 0:h, 0:w].astype(np.int32),
retnet_roi_bbox_targets=_roi_bbox_targets.astype(np.float32),
retnet_roi_fg_bbox_locs=_roi_fg_bbox_locs.astype(np.float32),
))
out_num_fg = np.array([num_fg + 1.0], dtype=np.float32)
out_num_bg = (
np.array([num_bg + 1.0]) * (cfg.MODEL.NUM_CLASSES - 1) +
out_num_fg * (cfg.MODEL.NUM_CLASSES - 2))
return blobs_out, out_num_fg, out_num_bg
def _get_retinanet_blobs(foas, all_anchors, gt_boxes, gt_classes, im_width,
im_height):
total_anchors = all_anchors.shape[0]
logger.debug('Getting mad blobs: im_height {} im_width: {}'.format(
im_height, im_width))
inds_inside = np.arange(all_anchors.shape[0])
anchors = all_anchors
num_inside = len(inds_inside)
logger.debug('total_anchors: {}'.format(total_anchors))
logger.debug('inds_inside: {}'.format(num_inside))
logger.debug('anchors.shape: {}'.format(anchors.shape))
# Compute anchor labels:
# label=1 is positive, 0 is negative, -1 is don't care (ignore)
labels = np.empty((num_inside, ), dtype=np.float32)
labels.fill(-1)
if len(gt_boxes) > 0:
# Compute overlaps between the anchors and the gt boxes overlaps
anchor_by_gt_overlap = box_utils.bbox_overlaps(anchors, gt_boxes)
# Map from anchor to gt box that has highest overlap
anchor_to_gt_argmax = anchor_by_gt_overlap.argmax(axis=1)
# For each anchor, amount of overlap with most overlapping gt box
anchor_to_gt_max = anchor_by_gt_overlap[np.arange(num_inside),
anchor_to_gt_argmax]
# Map from gt box to an anchor that has highest overlap
gt_to_anchor_argmax = anchor_by_gt_overlap.argmax(axis=0)
# For each gt box, amount of overlap with most overlapping anchor
gt_to_anchor_max = anchor_by_gt_overlap[
gt_to_anchor_argmax,
np.arange(anchor_by_gt_overlap.shape[1])]
# Find all anchors that share the max overlap amount
# (this includes many ties)
anchors_with_max_overlap = np.where(
anchor_by_gt_overlap == gt_to_anchor_max)[0]
# Fg label: for each gt use anchors with highest overlap
# (including ties)
gt_inds = anchor_to_gt_argmax[anchors_with_max_overlap]
labels[anchors_with_max_overlap] = gt_classes[gt_inds]
# Fg label: above threshold IOU
inds = anchor_to_gt_max >= cfg.RETINANET.POSITIVE_OVERLAP
gt_inds = anchor_to_gt_argmax[inds]
labels[inds] = gt_classes[gt_inds]
fg_inds = np.where(labels >= 1)[0]
bg_inds = np.where(anchor_to_gt_max < cfg.RETINANET.NEGATIVE_OVERLAP)[0]
labels[bg_inds] = 0
num_fg, num_bg = len(fg_inds), len(bg_inds)
bbox_targets = np.zeros((num_inside, 4), dtype=np.float32)
bbox_targets[fg_inds, :] = data_utils.compute_targets(
anchors[fg_inds, :], gt_boxes[anchor_to_gt_argmax[fg_inds], :])
# Bbox regression loss has the form:
# loss(x) = weight_outside * L(weight_inside * x)
# Inside weights allow us to set zero loss on an element-wise basis
# Bbox regression is only trained on positive examples so we set their
# weights to 1.0 (or otherwise if config is different) and 0 otherwise
bbox_inside_weights = np.zeros((num_inside, 4), dtype=np.float32)
bbox_inside_weights[labels >= 1, :] = (1.0, 1.0, 1.0, 1.0)
# Map up to original set of anchors
labels = data_utils.unmap(labels, total_anchors, inds_inside, fill=-1)
bbox_inside_weights = data_utils.unmap(bbox_inside_weights,
total_anchors,
inds_inside,
fill=0)
bbox_targets = data_utils.unmap(bbox_targets,
total_anchors,
inds_inside,
fill=0)
# Split the generated labels, etc. into labels per each field of anchors
blobs_out = []
start_idx = 0
for i, foa in enumerate(foas):
H = foa.field_size
W = foa.field_size
end_idx = start_idx + H * W
_labels = labels[start_idx:end_idx]
_bbox_targets = bbox_targets[start_idx:end_idx, :]
_bbox_inside_weights = bbox_inside_weights[start_idx:end_idx, :]
start_idx = end_idx
# labels output with shape (1, height, width)
_labels = _labels.reshape((1, 1, H, W))
# bbox_targets output with shape (1, 4 * A, height, width)
_bbox_targets = _bbox_targets.reshape(
(1, 1, H, W, 4)).transpose(0, 1, 4, 2, 3)
# bbox_inside_weights output with shape (1, 4 * A, height, width)
_bbox_inside_weights = _bbox_inside_weights.reshape(
(1, H, W, 4)).transpose(0, 3, 1, 2)
blobs_out.append(
dict(retnet_cls_labels=_labels.astype(np.int32),
retnet_roi_bbox_targets=_bbox_targets.astype(np.float32),
retnet_bbox_inside_weights_wide=_bbox_inside_weights))
out_num_fg = np.array([num_fg + 1.0], dtype=np.float32)
out_num_bg = (np.array([num_bg + 1.0]) * (cfg.MODEL.NUM_CLASSES - 1) +
out_num_fg * (cfg.MODEL.NUM_CLASSES - 2))
return blobs_out, out_num_fg, out_num_bg
def _get_rpn_blobs(im_height, im_width, foas, all_anchors, gt_boxes):
total_anchors = all_anchors.shape[0]
straddle_thresh = cfg.TRAIN.RPN_STRADDLE_THRESH
if straddle_thresh >= 0:
# Only keep anchors inside the image by a margin of straddle_thresh
# Set TRAIN.RPN_STRADDLE_THRESH to -1 (or a large value) to keep all
# anchors
inds_inside = np.where(
(all_anchors[:, 0] >= -straddle_thresh) &
(all_anchors[:, 1] >= -straddle_thresh) &
(all_anchors[:, 2] < im_width + straddle_thresh) &
(all_anchors[:, 3] < im_height + straddle_thresh)
)[0]
# keep only inside anchors
anchors = all_anchors[inds_inside, :]
else:
inds_inside = np.arange(all_anchors.shape[0])
anchors = all_anchors
num_inside = len(inds_inside)
logger.debug('total_anchors: {}'.format(total_anchors))
logger.debug('inds_inside: {}'.format(num_inside))
logger.debug('anchors.shape: {}'.format(anchors.shape))
# Compute anchor labels:
# label=1 is positive, 0 is negative, -1 is don't care (ignore)
labels = np.empty((num_inside, ), dtype=np.int32)
labels.fill(-1)
if len(gt_boxes) > 0:
# Compute overlaps between the anchors and the gt boxes overlaps
anchor_by_gt_overlap = box_utils.bbox_overlaps(anchors, gt_boxes)
# Map from anchor to gt box that has highest overlap
anchor_to_gt_argmax = anchor_by_gt_overlap.argmax(axis=1)
# For each anchor, amount of overlap with most overlapping gt box
anchor_to_gt_max = anchor_by_gt_overlap[np.arange(num_inside),
anchor_to_gt_argmax]
# Map from gt box to an anchor that has highest overlap
gt_to_anchor_argmax = anchor_by_gt_overlap.argmax(axis=0)
# For each gt box, amount of overlap with most overlapping anchor
gt_to_anchor_max = anchor_by_gt_overlap[
gt_to_anchor_argmax,
np.arange(anchor_by_gt_overlap.shape[1])
]
# Find all anchors that share the max overlap amount
# (this includes many ties)
anchors_with_max_overlap = np.where(
anchor_by_gt_overlap == gt_to_anchor_max
)[0]
# Fg label: for each gt use anchors with highest overlap
# (including ties)
labels[anchors_with_max_overlap] = 1
# Fg label: above threshold IOU
labels[anchor_to_gt_max >= cfg.TRAIN.RPN_POSITIVE_OVERLAP] = 1
# subsample positive labels if we have too many
num_fg = int(cfg.TRAIN.RPN_FG_FRACTION * cfg.TRAIN.RPN_BATCH_SIZE_PER_IM)
fg_inds = np.where(labels == 1)[0]
if len(fg_inds) > num_fg:
disable_inds = npr.choice(
fg_inds, size=(len(fg_inds) - num_fg), replace=False
)
labels[disable_inds] = -1
fg_inds = np.where(labels == 1)[0]
# subsample negative labels if we have too many
# (samples with replacement, but since the set of bg inds is large most
# samples will not have repeats)
num_bg = cfg.TRAIN.RPN_BATCH_SIZE_PER_IM - np.sum(labels == 1)
bg_inds = np.where(anchor_to_gt_max < cfg.TRAIN.RPN_NEGATIVE_OVERLAP)[0]
if len(bg_inds) > num_bg:
enable_inds = bg_inds[npr.randint(len(bg_inds), size=num_bg)]
labels[enable_inds] = 0
bg_inds = np.where(labels == 0)[0]
bbox_targets = np.zeros((num_inside, 4), dtype=np.float32)
bbox_targets[fg_inds, :] = data_utils.compute_targets(
anchors[fg_inds, :], gt_boxes[anchor_to_gt_argmax[fg_inds], :]
)
# Bbox regression loss has the form:
# loss(x) = weight_outside * L(weight_inside * x)
# Inside weights allow us to set zero loss on an element-wise basis
# Bbox regression is only trained on positive examples so we set their
# weights to 1.0 (or otherwise if config is different) and 0 otherwise
bbox_inside_weights = np.zeros((num_inside, 4), dtype=np.float32)
bbox_inside_weights[labels == 1, :] = (1.0, 1.0, 1.0, 1.0)
# The bbox regression loss only averages by the number of images in the
# mini-batch, whereas we need to average by the total number of example
# anchors selected
# Outside weights are used to scale each element-wise loss so the final
# average over the mini-batch is correct
bbox_outside_weights = np.zeros((num_inside, 4), dtype=np.float32)
# uniform weighting of examples (given non-uniform sampling)
num_examples = np.sum(labels >= 0)
bbox_outside_weights[labels == 1, :] = 1.0 / num_examples
bbox_outside_weights[labels == 0, :] = 1.0 / num_examples
# Map up to original set of anchors
labels = data_utils.unmap(labels, total_anchors, inds_inside, fill=-1)
bbox_targets = data_utils.unmap(
bbox_targets, total_anchors, inds_inside, fill=0
)
bbox_inside_weights = data_utils.unmap(
bbox_inside_weights, total_anchors, inds_inside, fill=0
)
bbox_outside_weights = data_utils.unmap(
bbox_outside_weights, total_anchors, inds_inside, fill=0
)
# Split the generated labels, etc. into labels per each field of anchors
blobs_out = []
start_idx = 0
for foa in foas:
H = foa.field_size
W = foa.field_size
A = foa.num_cell_anchors
end_idx = start_idx + H * W * A
_labels = labels[start_idx:end_idx]
_bbox_targets = bbox_targets[start_idx:end_idx, :]
_bbox_inside_weights = bbox_inside_weights[start_idx:end_idx, :]
_bbox_outside_weights = bbox_outside_weights[start_idx:end_idx, :]
start_idx = end_idx
# labels output with shape (1, A, height, width)
_labels = _labels.reshape((1, H, W, A)).transpose(0, 3, 1, 2)
# bbox_targets output with shape (1, 4 * A, height, width)
_bbox_targets = _bbox_targets.reshape(
(1, H, W, A * 4)).transpose(0, 3, 1, 2)
# bbox_inside_weights output with shape (1, 4 * A, height, width)
_bbox_inside_weights = _bbox_inside_weights.reshape(
(1, H, W, A * 4)).transpose(0, 3, 1, 2)
# bbox_outside_weights output with shape (1, 4 * A, height, width)
_bbox_outside_weights = _bbox_outside_weights.reshape(
(1, H, W, A * 4)).transpose(0, 3, 1, 2)
blobs_out.append(
dict(
rpn_labels_int32_wide=_labels,
rpn_bbox_targets_wide=_bbox_targets,
rpn_bbox_inside_weights_wide=_bbox_inside_weights,
rpn_bbox_outside_weights_wide=_bbox_outside_weights
)
)
return blobs_out[0] if len(blobs_out) == 1 else blobs_out
def _get_rpn_blobs(im_height, im_width, foas, all_anchors, gt_boxes=None):
total_anchors = all_anchors.shape[0]
straddle_thresh = cfg.TRAIN.RPN_STRADDLE_THRESH
if straddle_thresh >= 0:
# Only keep anchors inside the image by a margin of straddle_thresh
# Set TRAIN.RPN_STRADDLE_THRESH to -1 (or a large value) to keep all
# anchors
inds_inside = np.where(
(all_anchors[:, 0] >= -straddle_thresh)
& (all_anchors[:, 1] >= -straddle_thresh)
& (all_anchors[:, 2] < im_width + straddle_thresh)
& (all_anchors[:, 3] < im_height + straddle_thresh))[0]
# keep only inside anchors
anchors = all_anchors[inds_inside, :]
else:
inds_inside = np.arange(all_anchors.shape[0])
anchors = all_anchors
num_inside = len(inds_inside)
logger.debug('total_anchors: %d', total_anchors)
logger.debug('inds_inside: %d', num_inside)
logger.debug('anchors.shape: %s', str(anchors.shape))
# Compute anchor labels:
# label=1 is positive, 0 is negative, -1 is don't care (ignore)
labels = np.empty((num_inside, ), dtype=np.int32)
labels.fill(-1)
# subsample positive labels if we have too many
fg_inds = np.where(labels == 1)[0]
bg_inds = np.where(labels == 0)[0]
bbox_targets = np.zeros((num_inside, 4), dtype=np.float32)
bbox_targets[fg_inds, :] = data_utils.compute_targets(
anchors[fg_inds, :], gt_boxes[anchor_to_gt_argmax[fg_inds], :])
# Bbox regression loss has the form:
# loss(x) = weight_outside * L(weight_inside * x)
# Inside weights allow us to set zero loss on an element-wise basis
# Bbox regression is only trained on positive examples so we set their
# weights to 1.0 (or otherwise if config is different) and 0 otherwise
bbox_inside_weights = np.zeros((num_inside, 4), dtype=np.float32)
bbox_inside_weights[labels == 1, :] = (1.0, 1.0, 1.0, 1.0)
# The bbox regression loss only averages by the number of images in the
# mini-batch, whereas we need to average by the total number of example
# anchors selected
# Outside weights are used to scale each element-wise loss so the final
# average over the mini-batch is correct
bbox_outside_weights = np.zeros((num_inside, 4), dtype=np.float32)
# uniform weighting of examples (given non-uniform sampling)
num_examples = np.sum(labels >= 0)
bbox_outside_weights[labels == 1, :] = 1.0 / num_examples
bbox_outside_weights[labels == 0, :] = 1.0 / num_examples
# Map up to original set of anchors
labels = data_utils.unmap(labels, total_anchors, inds_inside, fill=-1)
bbox_targets = data_utils.unmap(bbox_targets,
total_anchors,
inds_inside,
fill=0)
bbox_inside_weights = data_utils.unmap(bbox_inside_weights,
total_anchors,
inds_inside,
fill=0)
bbox_outside_weights = data_utils.unmap(bbox_outside_weights,
total_anchors,
inds_inside,
fill=0)
# Split the generated labels, etc. into labels per each field of anchors
blobs_out = []
start_idx = 0
for foa in foas:
H = foa.field_size
W = foa.field_size
A = foa.num_cell_anchors
end_idx = start_idx + H * W * A
_labels = labels[start_idx:end_idx]
_bbox_targets = bbox_targets[start_idx:end_idx, :]
_bbox_inside_weights = bbox_inside_weights[start_idx:end_idx, :]
_bbox_outside_weights = bbox_outside_weights[start_idx:end_idx, :]
start_idx = end_idx
# labels output with shape (1, A, height, width)
_labels = _labels.reshape((1, H, W, A)).transpose(0, 3, 1, 2)
# bbox_targets output with shape (1, 4 * A, height, width)
_bbox_targets = _bbox_targets.reshape(
(1, H, W, A * 4)).transpose(0, 3, 1, 2)
# bbox_inside_weights output with shape (1, 4 * A, height, width)
_bbox_inside_weights = _bbox_inside_weights.reshape(
(1, H, W, A * 4)).transpose(0, 3, 1, 2)
# bbox_outside_weights output with shape (1, 4 * A, height, width)
_bbox_outside_weights = _bbox_outside_weights.reshape(
(1, H, W, A * 4)).transpose(0, 3, 1, 2)
blobs_out.append(
dict(rpn_labels_int32_wide=_labels,
rpn_bbox_targets_wide=_bbox_targets,
rpn_bbox_inside_weights_wide=_bbox_inside_weights,
rpn_bbox_outside_weights_wide=_bbox_outside_weights))
return blobs_out[0] if len(blobs_out) == 1 else blobs_out
def _get_rpn_blobs(im_height, im_width, foas, all_anchors, gt_boxes):
total_anchors = all_anchors.shape[0]
straddle_thresh = cfg.TRAIN.RPN_STRADDLE_THRESH
if straddle_thresh >= 0:
# Only keep anchors inside the image by a margin of straddle_thresh
# Set TRAIN.RPN_STRADDLE_THRESH to -1 (or a large value) to keep all
# anchors
inds_inside = np.where(
(all_anchors[:, 0] >= -straddle_thresh)
& (all_anchors[:, 1] >= -straddle_thresh)
& (all_anchors[:, 2] < im_width + straddle_thresh)
& (all_anchors[:, 3] < im_height + straddle_thresh))[0]
# keep only inside anchors
anchors = all_anchors[inds_inside, :]
else:
inds_inside = np.arange(all_anchors.shape[0])
anchors = all_anchors
# 创造一个map维护范围缩小之后的映射关系，reverse_map[i] = j，表示大范围中的i对应小范围中的j
reverse_map = {}
if cfg.RPN.QUANT_TARGET:
for inds, item in enumerate(inds_inside):
reverse_map[item] = inds
num_inside = len(inds_inside)
logger.debug('total_anchors: %d', total_anchors)
logger.debug('inds_inside: %d', num_inside)
logger.debug('anchors.shape: %s', str(anchors.shape))
# Compute anchor labels:
# label=1 is positive, 0 is negative, -1 is don't care (ignore)
labels = np.empty((num_inside, ), dtype=np.int32)
labels.fill(-1)
if len(gt_boxes) > 0:
# Compute overlaps between the anchors and the gt boxes overlaps
anchor_by_gt_overlap = box_utils.bbox_overlaps(anchors, gt_boxes)
# Map from anchor to gt box that has highest overlap
anchor_to_gt_argmax = anchor_by_gt_overlap.argmax(axis=1)
# For each anchor, amount of overlap with most overlapping gt box
anchor_to_gt_max = anchor_by_gt_overlap[np.arange(num_inside),
anchor_to_gt_argmax]
# Map from gt box to an anchor that has highest overlap
gt_to_anchor_argmax = anchor_by_gt_overlap.argmax(axis=0)
# For each gt box, amount of overlap with most overlapping anchor
gt_to_anchor_max = anchor_by_gt_overlap[
gt_to_anchor_argmax,
np.arange(anchor_by_gt_overlap.shape[1])]
# Find all anchors that share the max overlap amount
# (this includes many ties)
anchors_with_max_overlap = np.where(
anchor_by_gt_overlap == gt_to_anchor_max)[0]
# Fg label: for each gt use anchors with highest overlap
# (including ties)
labels[anchors_with_max_overlap] = 1
# Fg label: above threshold IOU
labels[anchor_to_gt_max >= cfg.TRAIN.RPN_POSITIVE_OVERLAP] = 1
# subsample positive labels if we have too many
num_fg = int(cfg.TRAIN.RPN_FG_FRACTION * cfg.TRAIN.RPN_BATCH_SIZE_PER_IM)
fg_inds = np.where(labels == 1)[0]
if len(fg_inds) > num_fg:
disable_inds = npr.choice(fg_inds,
size=(len(fg_inds) - num_fg),
replace=False)
labels[disable_inds] = -1
fg_inds = np.where(labels == 1)[0]
# subsample negative labels if we have too many
# (samples with replacement, but since the set of bg inds is large most
# samples will not have repeats)
num_bg = cfg.TRAIN.RPN_BATCH_SIZE_PER_IM - np.sum(labels == 1)
bg_inds = np.where(anchor_to_gt_max < cfg.TRAIN.RPN_NEGATIVE_OVERLAP)[0]
if len(bg_inds) > num_bg:
enable_inds = bg_inds[npr.randint(len(bg_inds), size=num_bg)]
labels[enable_inds] = 0
bg_inds = np.where(labels == 0)[0]
bbox_targets = np.zeros((num_inside, 4), dtype=np.float32)
if cfg.RPN.QUANT_TARGET:
start_idx = 0
# 1:336, 2:168, 3:84
stride_list = [4, 8, 16, 32, 64]
for foa_ind, foa in enumerate(foas):
end_idx = start_idx + foa.field_size * foa.field_size * foa.num_cell_anchors
# 这里取出的是inds_inside里面符合range的框的位置，我们还要将这些index提取出来
inds = np.intersect1d(
np.where(inds_inside < end_idx)[0],
np.where(inds_inside >= start_idx)[0])
if inds.size == 0:
continue
# level_range_inds中保存的是符合start_ids <= [....] < end_idx这一个indices序列
level_range_inds = inds_inside[inds]
start_idx = end_idx
short_level_range_inds = []
# 这个尺度是40W的，要映射回20W这个尺度。
# 即level_range_inds中存的每一个元素都是0~40W范围的，我们需要知道其每个元素i，对应在短序列（0~20W这个序列）中的位置
for item in level_range_inds:
short_level_range_inds.append(reverse_map[item])
# 其中每个元素都是符合range的短序列。
short_level_range_inds = np.array(short_level_range_inds)
level_range_fg_inds = np.intersect1d(short_level_range_inds,
fg_inds)
# logger.info("lvl index: {}".format(level_range_fg_inds.shape))
bbox_targets[
level_range_fg_inds, :] = data_utils.quant_compute_targets(
anchors[level_range_fg_inds, :],
gt_boxes[anchor_to_gt_argmax[level_range_fg_inds], :],
stride_list[foa_ind])
else:
bbox_targets[fg_inds, :] = data_utils.compute_targets(
anchors[fg_inds, :], gt_boxes[anchor_to_gt_argmax[fg_inds], :])
# Bbox regression loss has the form:
# loss(x) = weight_outside * L(weight_inside * x)
# Inside weights allow us to set zero loss on an element-wise basis
# Bbox regression is only trained on positive examples so we set their
# weights to 1.0 (or otherwise if config is different) and 0 otherwise
bbox_inside_weights = np.zeros((num_inside, 4), dtype=np.float32)
bbox_inside_weights[labels == 1, :] = (1.0, 1.0, 1.0, 1.0)
# The bbox regression loss only averages by the number of images in the
# mini-batch, whereas we need to average by the total number of example
# anchors selected
# Outside weights are used to scale each element-wise loss so the final
# average over the mini-batch is correct
bbox_outside_weights = np.zeros((num_inside, 4), dtype=np.float32)
# uniform weighting of examples (given non-uniform sampling)
num_examples = np.sum(labels >= 0)
bbox_outside_weights[labels == 1, :] = 1.0 / num_examples
bbox_outside_weights[labels == 0, :] = 1.0 / num_examples
# Map up to original set of anchors
labels = data_utils.unmap(labels, total_anchors, inds_inside, fill=-1)
bbox_targets = data_utils.unmap(bbox_targets,
total_anchors,
inds_inside,
fill=0)
bbox_inside_weights = data_utils.unmap(bbox_inside_weights,
total_anchors,
inds_inside,
fill=0)
bbox_outside_weights = data_utils.unmap(bbox_outside_weights,
total_anchors,
inds_inside,
fill=0)
# Split the generated labels, etc. into labels per each field of anchors
blobs_out = []
start_idx = 0
if cfg.RPN.VIS_QUANT_TARGET:
sample_start_idx = 336 * 336 * 3
sample_end_idx = 336 * 336 * 3 + 168 * 168 * 3
sample_anchors = all_anchors[sample_start_idx:sample_end_idx]
import json
import os
path = "/nfs/project/libo_i/Boosting/Targets_Info"
if not os.path.exists(path):
os.makedirs(path)
# 这里有3个尺度的框，只留中间尺度的框
sample_anchors = sample_anchors[1::3, :]
sample_anchors = sample_anchors.reshape(168, 168, 4)
with open(os.path.join(path, "quant_anchors.json"), "w") as fp:
json.dump(sample_anchors.tolist(), fp)
if cfg.RPN.DOWNSAMPLE_TARGET:
start_idx = 0
# 1:336, 2:168, 3:84 4:42 5:21
for inds, foa in enumerate(foas):
end_idx = start_idx + foa.field_size * foa.field_size * foa.num_cell_anchors
for foa in foas:
H = foa.field_size
W = foa.field_size
A = foa.num_cell_anchors
end_idx = start_idx + H * W * A
_labels = labels[start_idx:end_idx]
_bbox_targets = bbox_targets[start_idx:end_idx, :]
_bbox_inside_weights = bbox_inside_weights[start_idx:end_idx, :]
_bbox_outside_weights = bbox_outside_weights[start_idx:end_idx, :]
start_idx = end_idx
# labels output with shape (1, A, height, width)
_labels = _labels.reshape((1, H, W, A)).transpose(0, 3, 1, 2)
# bbox_targets output with shape (1, 4 * A, height, width)
_bbox_targets = _bbox_targets.reshape(
(1, H, W, A * 4)).transpose(0, 3, 1, 2)
# bbox_inside_weights output with shape (1, 4 * A, height, width)
_bbox_inside_weights = _bbox_inside_weights.reshape(
(1, H, W, A * 4)).transpose(0, 3, 1, 2)
# bbox_outside_weights output with shape (1, 4 * A, height, width)
_bbox_outside_weights = _bbox_outside_weights.reshape(
(1, H, W, A * 4)).transpose(0, 3, 1, 2)
blobs_out.append(
dict(rpn_labels_int32_wide=_labels,
rpn_bbox_targets_wide=_bbox_targets,
rpn_bbox_inside_weights_wide=_bbox_inside_weights,
rpn_bbox_outside_weights_wide=_bbox_outside_weights))
return blobs_out[0] if len(blobs_out) == 1 else blobs_out
