def _expand_bbox_targets(bbox_target_data):
"""Bounding-box regression targets are stored in a compact form in the
roidb.
This function expands those targets into the 4-of-4*K representation used
by the network (i.e. only one class has non-zero targets). The loss weights
are similarly expanded.
Returns:
bbox_target_data (ndarray): N x 4K blob of regression targets
bbox_inside_weights (ndarray): N x 4K blob of loss weights
"""
num_bbox_reg_classes = cfg.MODEL.NUM_CLASSES
if cfg.MODEL.CLS_AGNOSTIC_BBOX_REG:
num_bbox_reg_classes = 2 # bg and fg
clss = bbox_target_data[:, 0]
bbox_targets = blob_utils.zeros((clss.size, 4 * num_bbox_reg_classes))
bbox_inside_weights = blob_utils.zeros(bbox_targets.shape)
inds = np.where(clss > 0)[0]
for ind in inds:
cls = int(clss[ind])
start = 4 * cls
end = start + 4
bbox_targets[ind, start:end] = bbox_target_data[ind, 1:]
bbox_inside_weights[ind, start:end] = (1.0, 1.0, 1.0, 1.0)
return bbox_targets, bbox_inside_weights
def _expand_bbox_targets(bbox_target_data):
"""Bounding-box regression targets are stored in a compact form in the
roidb.
This function expands those targets into the 4-of-4*K representation used
by the network (i.e. only one class has non-zero targets). The loss weights
are similarly expanded.
Returns:
bbox_target_data (ndarray): N x 4K blob of regression targets
bbox_inside_weights (ndarray): N x 4K blob of loss weights
"""
num_bbox_reg_classes = cfg.MODEL.NUM_CLASSES
if cfg.MODEL.CLS_AGNOSTIC_BBOX_REG:
num_bbox_reg_classes = 2 # bg and fg
clss = bbox_target_data[:, 0]
bbox_targets = blob_utils.zeros((clss.size, 4 * num_bbox_reg_classes))
bbox_inside_weights = blob_utils.zeros(bbox_targets.shape)
inds = np.where(clss > 0)[0]
for ind in inds:
cls = int(clss[ind])
start = 4 * cls
end = start + 4
bbox_targets[ind, start:end] = bbox_target_data[ind, 1:]
bbox_inside_weights[ind, start:end] = (1.0, 1.0, 1.0, 1.0)
return bbox_targets, bbox_inside_weights
def keypoints_to_heatmap_labels(keypoints, rois):
"""Encode keypoint location in the target heatmap for use in
SoftmaxWithLoss.
"""
# Maps keypoints from the half-open interval [x1, x2) on continuous image
# coordinates to the closed interval [0, HEATMAP_SIZE - 1] on discrete image
# coordinates. We use the continuous <-> discrete conversion from Heckbert
# 1990 ("What is the coordinate of a pixel?"): d = floor(c) and c = d + 0.5,
# where d is a discrete coordinate and c is a continuous coordinate.
assert keypoints.shape[2] == cfg.KRCNN.NUM_KEYPOINTS
shape = (len(rois), cfg.KRCNN.NUM_KEYPOINTS)
heatmaps = blob_utils.zeros(shape)
weights = blob_utils.zeros(shape)
offset_x = rois[:, 0]
offset_y = rois[:, 1]
scale_x = cfg.KRCNN.HEATMAP_SIZE / (rois[:, 2] - rois[:, 0])
scale_y = cfg.KRCNN.HEATMAP_SIZE / (rois[:, 3] - rois[:, 1])
for kp in range(keypoints.shape[2]):
vis = keypoints[:, 2, kp] > 0
x = keypoints[:, 0, kp].astype(np.float32)
y = keypoints[:, 1, kp].astype(np.float32)
# Since we use floor below, if a keypoint is exactly on the roi's right
# or bottom boundary, we shift it in by eps (conceptually) to keep it in
# the ground truth heatmap.
x_boundary_inds = np.where(x == rois[:, 2])[0]
y_boundary_inds = np.where(y == rois[:, 3])[0]
x = (x - offset_x) * scale_x
x = np.floor(x)
if len(x_boundary_inds) > 0:
x[x_boundary_inds] = cfg.KRCNN.HEATMAP_SIZE - 1
y = (y - offset_y) * scale_y
y = np.floor(y)
if len(y_boundary_inds) > 0:
y[y_boundary_inds] = cfg.KRCNN.HEATMAP_SIZE - 1
valid_loc = np.logical_and(
np.logical_and(x >= 0, y >= 0),
np.logical_and(
x < cfg.KRCNN.HEATMAP_SIZE, y < cfg.KRCNN.HEATMAP_SIZE))
valid = np.logical_and(valid_loc, vis)
valid = valid.astype(np.int32)
lin_ind = y * cfg.KRCNN.HEATMAP_SIZE + x
heatmaps[:, kp] = lin_ind * valid
weights[:, kp] = valid
return heatmaps, weights
def keypoints_to_heatmap_labels(keypoints, rois):
"""Encode keypoint location in the target heatmap for use in
SoftmaxWithLoss.
"""
# Maps keypoints from the half-open interval [x1, x2) on continuous image
# coordinates to the closed interval [0, HEATMAP_SIZE - 1] on discrete image
# coordinates. We use the continuous <-> discrete conversion from Heckbert
# 1990 ("What is the coordinate of a pixel?"): d = floor(c) and c = d + 0.5,
# where d is a discrete coordinate and c is a continuous coordinate.
assert keypoints.shape[2] == cfg.KRCNN.NUM_KEYPOINTS
shape = (len(rois), cfg.KRCNN.NUM_KEYPOINTS)
heatmaps = blob_utils.zeros(shape)
weights = blob_utils.zeros(shape)
offset_x = rois[:, 0]
offset_y = rois[:, 1]
scale_x = cfg.KRCNN.HEATMAP_SIZE / (rois[:, 2] - rois[:, 0])
scale_y = cfg.KRCNN.HEATMAP_SIZE / (rois[:, 3] - rois[:, 1])
for kp in range(keypoints.shape[2]):
vis = keypoints[:, 2, kp] > 0
x = keypoints[:, 0, kp].astype(np.float32)
y = keypoints[:, 1, kp].astype(np.float32)
# Since we use floor below, if a keypoint is exactly on the roi's right
# or bottom boundary, we shift it in by eps (conceptually) to keep it in
# the ground truth heatmap.
x_boundary_inds = np.where(x == rois[:, 2])[0]
y_boundary_inds = np.where(y == rois[:, 3])[0]
x = (x - offset_x) * scale_x
x = np.floor(x)
if len(x_boundary_inds) > 0:
x[x_boundary_inds] = cfg.KRCNN.HEATMAP_SIZE - 1
y = (y - offset_y) * scale_y
y = np.floor(y)
if len(y_boundary_inds) > 0:
y[y_boundary_inds] = cfg.KRCNN.HEATMAP_SIZE - 1
valid_loc = np.logical_and(
np.logical_and(x >= 0, y >= 0),
np.logical_and(
x < cfg.KRCNN.HEATMAP_SIZE, y < cfg.KRCNN.HEATMAP_SIZE))
valid = np.logical_and(valid_loc, vis)
valid = valid.astype(np.int32)
lin_ind = y * cfg.KRCNN.HEATMAP_SIZE + x
heatmaps[:, kp] = lin_ind * valid
weights[:, kp] = valid
return heatmaps, weights
def add_mask_rcnn_blobs(blobs, sampled_boxes, roidb, im_scale, batch_idx):
"""Add Mask R-CNN specific blobs to the input blob dictionary."""
# Prepare the mask targets by associating one gt mask to each training roi
# that has a fg (non-bg) class label.
M = cfg.MRCNN.RESOLUTION
input_w = roidb['input_width']
input_h = roidb['input_height']
polys_gt_inds = np.where((roidb['gt_classes'] > 0)
& (roidb['is_crowd'] == 0))[0]
polys_gt = [roidb['segms'][i] for i in polys_gt_inds]
boxes_from_polys = segm_utils.polys_to_boxes(polys_gt)
fg_inds = np.where(blobs['labels_int32'] > 0)[0]
roi_has_mask = blobs['labels_int32'].copy()
roi_has_mask[roi_has_mask > 0] = 1
mask_fg_rois_per_this_image = cfg.MRCNN.MAX_ROIS_PER_IM
if fg_inds.shape[0] > 0:
if fg_inds.size > mask_fg_rois_per_this_image:
fg_inds = np.random.choice(fg_inds,
size=mask_fg_rois_per_this_image,
replace=False)
# Class labels for the foreground rois
mask_class_labels = blobs['labels_int32'][fg_inds]
masks = blob_utils.zeros((fg_inds.shape[0], M**2), int32=True)
all_person_masks = np.zeros(
(int(input_h / im_scale), int(input_w / im_scale)),
dtype=np.float32)
# Find overlap between all foreground rois and the bounding boxes
# enclosing each segmentation
rois_fg = sampled_boxes[fg_inds]
overlaps_bbfg_bbpolys = box_utils.bbox_overlaps(
rois_fg.astype(np.float32, copy=False),
boxes_from_polys.astype(np.float32, copy=False))
# Map from each fg rois to the index of the mask with highest overlap
# (measured by bbox overlap)
fg_polys_inds = np.argmax(overlaps_bbfg_bbpolys, axis=1)
# add fg targets
for i in range(rois_fg.shape[0]):
fg_polys_ind = fg_polys_inds[i]
poly_gt = polys_gt[fg_polys_ind]
roi_fg = rois_fg[i]
# Rasterize the portion of the polygon mask within the given fg roi
# to an M x M binary image
mask = segm_utils.polys_to_mask_wrt_box(poly_gt, roi_fg, M)
mask = np.array(mask > 0, dtype=np.int32) # Ensure it's binary
masks[i, :] = np.reshape(mask, M**2)
# to an box_h x box_w binary image
mask_wrt_bbox = segm_utils.convert_polys_to_mask_wrt_box(
poly_gt, roi_fg)
start_y, start_x = int(roi_fg[1]), int(roi_fg[0])
end_y, end_x = start_y + mask_wrt_bbox.shape[
0], start_x + mask_wrt_bbox.shape[1]
all_person_masks[start_y:end_y, start_x:end_x] = mask_wrt_bbox
proposal_all_mask = blob_utils.zeros((fg_inds.shape[0], M, M),
int32=True)
for i in range(rois_fg.shape[0]):
roi_fg = rois_fg[i]
w = roi_fg[2] - roi_fg[0]
h = roi_fg[3] - roi_fg[1]
w = int(np.maximum(w, 1))
h = int(np.maximum(h, 1))
proposal_mask = all_person_masks[int(roi_fg[1]):int(roi_fg[1]) + h,
int(roi_fg[0]):int(roi_fg[0]) + w]
# proposal_mask = proposal_mask.astype(np.float32)
proposal_mask = cv2.resize(proposal_mask, (M, M))
proposal_mask = (proposal_mask > 0.5).astype(np.int32)
proposal_all_mask[i] = proposal_mask
else: # If there are no fg masks (it does happen)
# The network cannot handle empty blobs, so we must provide a mask
# We simply take the first bg roi, given it an all -1's mask (ignore
# label), and label it with class zero (bg).
bg_inds = np.where(blobs['labels_int32'] == 0)[0]
# rois_fg is actually one background roi, but that's ok because ...
rois_fg = sampled_boxes[bg_inds[0]].reshape((1, -1))
# We give it an -1's blob (ignore label)
masks = -blob_utils.ones((1, M**2), int32=True)
# We label it with class = 0 (background)
mask_class_labels = blob_utils.zeros((1, ))
# Mark that the first roi has a mask
roi_has_mask[0] = 1
proposal_all_mask = -blob_utils.ones((1, M, M), int32=True)
if cfg.MRCNN.CLS_SPECIFIC_MASK:
masks = _expand_to_class_specific_mask_targets(masks,
mask_class_labels)
# Scale rois_fg and format as (batch_idx, x1, y1, x2, y2)
rois_fg *= im_scale
repeated_batch_idx = batch_idx * blob_utils.ones((rois_fg.shape[0], 1))
rois_fg = np.hstack((repeated_batch_idx, rois_fg))
# Update blobs dict with Mask R-CNN blobs
blobs['mask_rois'] = rois_fg
blobs['roi_has_mask_int32'] = roi_has_mask
blobs['masks_int32'] = masks
# blobs['mask_labels'] = np.argmax(masks.reshape((-1,cfg.MODEL.NUM_CLASSES,M,M)),axis=1).reshape((-1,M,M)).astype(np.int32)
# blobs['mask_weights'] = np.ones(blobs['mask_labels'].shape, dtype=np.float32)
# add by wxh
if cfg.MRCNN.USE_CLS_EMBS:
fg_embs, bg_embs, fg_weights, bg_weights = masks_to_embs(
masks.reshape((-1, cfg.MODEL.NUM_CLASSES, M, M)))
# print('fg',fg_embs.max(), fg_embs.min())
# print('bg',bg_embs.max(), bg_embs.min())
fg_norms = np.sum(fg_embs, axis=(1, 2))
fg_norms[fg_norms != 0] = 28. * 28. / (fg_norms[fg_norms != 0] + 1e-6)
bg_norms = np.sum(bg_embs, axis=(1, 2))
bg_norms[bg_norms != 0] = 28. * 28. / (bg_norms[bg_norms != 0] + 1e-6)
blobs['fg_mask'] = np.repeat(np.reshape(fg_embs, (-1, 1, M, M)),
2,
axis=1)
blobs['bg_mask'] = np.repeat(np.reshape(bg_embs, (-1, 1, M, M)),
2,
axis=1)
blobs['fg_norm'] = np.repeat(np.reshape(fg_norms, (-1, 1)), 2, axis=1)
blobs['bg_norm'] = np.repeat(np.reshape(bg_norms, (-1, 1)), 2, axis=1)
blobs['mask_emb_fg_labels'] = np.ones((fg_embs.shape[0], 1),
dtype=np.int32)
blobs['mask_emb_bg_labels'] = np.zeros((bg_embs.shape[0], 1),
dtype=np.int32)
# blobs['mask_emb_weights'] = np.vstack([fg_weights, bg_weights]).reshape((-1,1)).astype(np.float32)
if cfg.MRCNN.BBOX_CASCADE_MASK_ON:
blobs['inter_masks_int32'] = proposal_all_mask
def keypoints_to_global_heatmap_labels(keypoints, rois, input_h, input_w):
assert keypoints.shape[2] == cfg.KRCNN.NUM_KEYPOINTS
M = cfg.KRCNN.HEATMAP_SIZE
shape = (len(rois), cfg.KRCNN.NUM_KEYPOINTS)
heatmaps = blob_utils.zeros(shape)
weights = blob_utils.zeros(shape)
global_heatmaps = np.zeros((input_h, input_w, cfg.KRCNN.NUM_KEYPOINTS),
dtype=np.float32)
offset_x = rois[:, 0]
offset_y = rois[:, 1]
scale_x = cfg.KRCNN.HEATMAP_SIZE / (rois[:, 2] - rois[:, 0])
scale_y = cfg.KRCNN.HEATMAP_SIZE / (rois[:, 3] - rois[:, 1])
for kp in range(keypoints.shape[2]):
vis = keypoints[:, 2, kp] > 0
x = keypoints[:, 0, kp].astype(np.float32)
y = keypoints[:, 1, kp].astype(np.float32)
# valid_loc = np.logical_and(x<input_w,y<input_h)
# vis = np.logical_and(vis, valid_loc)
# valid_x = x[vis].astype(np.int32)
# valid_y = y[vis].astype(np.int32)
# for i_loc in range(valid_x.shape[0]):
# mu_x = valid_x[i_loc]
# mu_y = valid_y[i_loc]
# range_x = np.arange(mu_x - 1, mu_x + 2)
# range_y = np.arange(mu_y - 1, mu_y + 2)
# range_x[range_x<0] = 0
# range_x[range_x>=input_w]=input_w-1
# range_y[range_y<1] = 0
# range_y[range_y>=input_h]=input_h-1
# global_heatmaps[range_y, range_x, kp] = 1
# Since we use floor below, if a keypoint is exactly on the roi's right
# or bottom boundary, we shift it in by eps (conceptually) to keep it in
# the ground truth heatmap.
x_boundary_inds = np.where(x == rois[:, 2])[0]
y_boundary_inds = np.where(y == rois[:, 3])[0]
x = (x - offset_x) * scale_x
x = np.floor(x)
if len(x_boundary_inds) > 0:
x[x_boundary_inds] = cfg.KRCNN.HEATMAP_SIZE - 1
y = (y - offset_y) * scale_y
y = np.floor(y)
if len(y_boundary_inds) > 0:
y[y_boundary_inds] = cfg.KRCNN.HEATMAP_SIZE - 1
valid_loc = np.logical_and(
np.logical_and(x >= 0, y >= 0),
np.logical_and(x < cfg.KRCNN.HEATMAP_SIZE,
y < cfg.KRCNN.HEATMAP_SIZE))
valid = np.logical_and(valid_loc, vis)
valid_x = x[valid] / scale_x[valid] + offset_x[valid]
valid_x = valid_x.astype(np.int32)
valid_y = y[valid] / scale_y[valid] + offset_y[valid]
valid_y = valid_y.astype(np.int32)
global_heatmaps[valid_y, valid_x, kp] = 1
valid = valid.astype(np.int32)
lin_ind = y * cfg.KRCNN.HEATMAP_SIZE + x
heatmaps[:, kp] = lin_ind * valid
weights[:, kp] = valid
proposal_all_heatmaps = blob_utils.zeros(
(rois.shape[0], cfg.KRCNN.NUM_KEYPOINTS, M, M), int32=True)
for i in range(rois.shape[0]):
roi_fg = rois[i]
w = roi_fg[2] - roi_fg[0]
h = roi_fg[3] - roi_fg[1]
w = int(np.maximum(w, 1))
h = int(np.maximum(h, 1))
proposal_hm = global_heatmaps[int(roi_fg[1]):int(roi_fg[1]) + h,
int(roi_fg[0]):int(roi_fg[0]) + w, :]
proposal_hm = cv2.resize(proposal_hm, (M, M))
proposal_hm = (proposal_hm > 0.5).astype(np.int32)
proposal_all_heatmaps[i] = proposal_hm.transpose((2, 0, 1))
return heatmaps, weights, proposal_all_heatmaps
def _sample_rois(roidb, im_scale, batch_idx, stage):
"""Generate a random sample of RoIs comprising foreground and background
examples.
"""
fg_thresh = cfg.CASCADE_RCNN.FG_THRESHS[stage - 1]
bg_thresh_hi = cfg.CASCADE_RCNN.BG_THRESHS_HI[stage - 1]
bg_thresh_lo = cfg.CASCADE_RCNN.BG_THRESHS_LO[stage - 1]
max_overlaps = roidb["max_overlaps"]
# Select foreground RoIs as those with >= FG_THRESH overlap
fg_inds = np.where(max_overlaps >= fg_thresh)[0]
fg_rois_per_this_image = fg_inds.size
# Select background RoIs as those within [BG_THRESH_LO, BG_THRESH_HI)
bg_inds = np.where((max_overlaps < bg_thresh_hi)
& (max_overlaps >= bg_thresh_lo))[0]
# The indices that we're selecting (both fg and bg)
keep_inds = np.append(fg_inds, bg_inds)
# Label is the class each RoI has max overlap with
sampled_labels = roidb["max_classes"][keep_inds]
sampled_labels[fg_rois_per_this_image:] = 0 # Label bg RoIs with class 0
sampled_boxes = roidb["boxes"][keep_inds]
gt_inds = np.where(roidb["gt_classes"] > 0)[0]
gt_boxes = roidb["boxes"][gt_inds, :]
gt_assignments = gt_inds[roidb["box_to_gt_ind_map"][keep_inds]]
# [mapped_gt_boxes, max_overlaps]
mapped_gt_boxes = blob_utils.zeros((keep_inds.size, 5))
mapped_gt_boxes[:, :4] = gt_boxes[gt_assignments, :] * im_scale
mapped_gt_boxes[:, 4] = max_overlaps[keep_inds]
mapped_gt_boxes[fg_rois_per_this_image:, :] = 0
if "bbox_targets" not in roidb:
bbox_targets = _compute_targets(sampled_boxes,
gt_boxes[gt_assignments, :],
sampled_labels, stage)
else:
bbox_targets = roidb['bbox_targets'][keep_inds, :]
bbox_targets, bbox_inside_weights = _expand_bbox_targets(bbox_targets)
bbox_outside_weights = np.array(bbox_inside_weights > 0,
dtype=bbox_inside_weights.dtype)
# Scale rois and format as (batch_idx, x1, y1, x2, y2)
sampled_rois = sampled_boxes * im_scale
repeated_batch_idx = batch_idx * blob_utils.ones(
(sampled_rois.shape[0], 1))
sampled_rois = np.hstack((repeated_batch_idx, sampled_rois))
# Base Cascade R-CNN blobs
blob_dict = dict(
labels_int32=sampled_labels.astype(np.int32, copy=False),
rois=sampled_rois,
bbox_targets=bbox_targets,
bbox_inside_weights=bbox_inside_weights,
bbox_outside_weights=bbox_outside_weights,
mapped_gt_boxes=mapped_gt_boxes,
)
# Optionally add Mask R-CNN blobs
if cfg.MODEL.MASK_ON and cfg.MRCNN.AT_STAGE == stage:
mask_rcnn_roi_data.add_mask_rcnn_blobs(blob_dict, sampled_boxes, roidb,
im_scale, batch_idx)
# Optionally add Keypoint R-CNN blobs
if cfg.MODEL.KEYPOINTS_ON and cfg.KRCNN.AT_STAGE == stage:
keypoint_rcnn_roi_data.add_keypoint_rcnn_blobs(blob_dict, roidb,
fg_rois_per_this_image,
fg_inds, im_scale,
batch_idx, fg_thresh)
return blob_dict
def add_rpn_blobs(blobs, im_scales, roidb):
"""Add blobs needed training RPN-only and end-to-end Faster R-CNN models."""
if cfg.FPN.FPN_ON and cfg.FPN.MULTILEVEL_RPN:
# RPN applied to many feature levels, as in the FPN paper
k_max = cfg.FPN.RPN_MAX_LEVEL
k_min = cfg.FPN.RPN_MIN_LEVEL
foas = []
# fetch the spatial scales for every FPN level except fpn6
#fpn_spatial_scales = globals().get('fpn_level_info_' + cfg.MODEL.BACKBONE_NAME + '_conv5')().spatial_scales
fpn_spatial_scales = getattr(FPN, 'fpn_level_info_' + cfg.MODEL.BACKBONE_NAME + '_conv5')().spatial_scales
for lvl in range(k_min, k_max):
field_stride = 1. / fpn_spatial_scales[k_max-lvl-1]
#field_stride = 2.**(lvl - int(math.log(cfg.FPN.FINEST_LEVEL_SCALE,2))-2)
anchor_sizes = (cfg.FPN.RPN_ANCHOR_START_SIZE * 2.**(lvl - k_min), )
anchor_aspect_ratios = cfg.FPN.RPN_ASPECT_RATIOS
foa = data_utils.get_field_of_anchors(
field_stride, anchor_sizes, anchor_aspect_ratios
)
foas.append(foa)
# for p6, the scale should be the corest level divided by 2
if k_max == 6:
field_stride = 2 * (1. / fpn_spatial_scales[0])
anchor_sizes = (cfg.FPN.RPN_ANCHOR_START_SIZE * 2.**(k_max - k_min), )
anchor_aspect_ratios = cfg.FPN.RPN_ASPECT_RATIOS
foa = data_utils.get_field_of_anchors(
field_stride, anchor_sizes, anchor_aspect_ratios
)
foas.append(foa)
all_anchors = np.concatenate([f.field_of_anchors for f in foas])
else:
foa = data_utils.get_field_of_anchors(
cfg.RPN.STRIDE, cfg.RPN.SIZES, cfg.RPN.ASPECT_RATIOS
)
all_anchors = foa.field_of_anchors
for im_i, entry in enumerate(roidb):
scale = im_scales[im_i]
im_height = np.round(entry['height'] * scale)
im_width = np.round(entry['width'] * scale)
gt_inds = np.where(
(entry['gt_classes'] > 0) & (entry['is_crowd'] == 0)
)[0]
gt_rois = entry['boxes'][gt_inds, :] * scale
# TODO(rbg): gt_boxes is poorly named;
# should be something like 'gt_rois_info'
gt_boxes = blob_utils.zeros((len(gt_inds), 6))
gt_boxes[:, 0] = im_i # batch inds
gt_boxes[:, 1:5] = gt_rois
gt_boxes[:, 5] = entry['gt_classes'][gt_inds]
im_info = np.array([[im_height, im_width, scale]], dtype=np.float32)
blobs['im_info'].append(im_info)
# Add RPN targets
if cfg.FPN.FPN_ON and cfg.FPN.MULTILEVEL_RPN:
# RPN applied to many feature levels, as in the FPN paper
rpn_blobs = _get_rpn_blobs(
im_height, im_width, foas, all_anchors, gt_rois
)
for i, lvl in enumerate(range(k_min, k_max + 1)):
for k, v in rpn_blobs[i].items():
blobs[k + '_fpn' + str(lvl)].append(v)
else:
# Classical RPN, applied to a single feature level
rpn_blobs = _get_rpn_blobs(
im_height, im_width, [foa], all_anchors, gt_rois
)
for k, v in rpn_blobs.items():
blobs[k].append(v)
for k, v in blobs.items():
if isinstance(v, list) and len(v) > 0:
blobs[k] = np.concatenate(v)
valid_keys = [
'has_visible_keypoints', 'boxes', 'segms', 'seg_areas', 'gt_classes',
'gt_overlaps', 'is_crowd', 'box_to_gt_ind_map', 'gt_keypoints'
]
minimal_roidb = [{} for _ in range(len(roidb))]
for i, e in enumerate(roidb):
for k in valid_keys:
if k in e:
minimal_roidb[i][k] = e[k]
blobs['roidb'] = blob_utils.serialize(minimal_roidb)
# Always return valid=True, since RPN minibatches are valid by design
return True
def _sample_rois(roidb, im_scale, batch_idx):
"""Generate a random sample of RoIs comprising foreground and background
examples.
"""
rois_per_image = int(cfg.TRAIN.BATCH_SIZE_PER_IM)
fg_rois_per_image = int(np.round(cfg.TRAIN.FG_FRACTION * rois_per_image))
max_overlaps = roidb['max_overlaps']
# Select foreground RoIs as those with >= FG_THRESH overlap
fg_inds = np.where(max_overlaps >= cfg.TRAIN.FG_THRESH)[0]
# Guard against the case when an image has fewer than fg_rois_per_image
# foreground RoIs
fg_rois_per_this_image = np.minimum(fg_rois_per_image, fg_inds.size)
# Sample foreground regions without replacement
if fg_inds.size > 0:
fg_inds = npr.choice(fg_inds,
size=fg_rois_per_this_image,
replace=False)
# Select background RoIs as those within [BG_THRESH_LO, BG_THRESH_HI)
bg_inds = np.where((max_overlaps < cfg.TRAIN.BG_THRESH_HI)
& (max_overlaps >= cfg.TRAIN.BG_THRESH_LO))[0]
# Compute number of background RoIs to take from this image (guarding
# against there being fewer than desired)
bg_rois_per_this_image = rois_per_image - fg_rois_per_this_image
bg_rois_per_this_image = np.minimum(bg_rois_per_this_image, bg_inds.size)
# Sample foreground regions without replacement
if bg_inds.size > 0:
bg_inds = npr.choice(bg_inds,
size=bg_rois_per_this_image,
replace=False)
# The indices that we're selecting (both fg and bg)
keep_inds = np.append(fg_inds, bg_inds)
# Label is the class each RoI has max overlap with
sampled_labels = roidb['max_classes'][keep_inds]
sampled_labels[fg_rois_per_this_image:] = 0 # Label bg RoIs with class 0
sampled_boxes = roidb['boxes'][keep_inds]
gt_inds = np.where(roidb['gt_classes'] > 0)[0]
gt_boxes = roidb['boxes'][gt_inds, :]
gt_assignments = gt_inds[roidb['box_to_gt_ind_map'][keep_inds]]
# [mapped_gt_boxes, max_overlaps]
mapped_gt_boxes = blob_utils.zeros((keep_inds.size, 5))
mapped_gt_boxes[:, :4] = gt_boxes[gt_assignments, :] * im_scale
mapped_gt_boxes[:, 4] = max_overlaps[keep_inds]
mapped_gt_boxes[fg_rois_per_this_image:, :] = 0
bbox_targets, bbox_inside_weights = _expand_bbox_targets(
roidb['bbox_targets'][keep_inds, :])
bbox_outside_weights = np.array(bbox_inside_weights > 0,
dtype=bbox_inside_weights.dtype)
# Scale rois and format as (batch_idx, x1, y1, x2, y2)
sampled_rois = sampled_boxes * im_scale
repeated_batch_idx = batch_idx * blob_utils.ones(
(sampled_rois.shape[0], 1))
sampled_rois = np.hstack((repeated_batch_idx, sampled_rois))
# Base Fast R-CNN blobs
blob_dict = dict(labels_int32=sampled_labels.astype(np.int32, copy=False),
rois=sampled_rois,
bbox_targets=bbox_targets,
bbox_inside_weights=bbox_inside_weights,
bbox_outside_weights=bbox_outside_weights,
mapped_gt_boxes=mapped_gt_boxes)
# Optionally add Mask R-CNN blobs
if cfg.MODEL.MASK_ON and cfg.MRCNN.AT_STAGE == 1:
mask_rcnn_roi_data.add_mask_rcnn_blobs(blob_dict, sampled_boxes, roidb,
im_scale, batch_idx)
# Optionally add Keypoint R-CNN blobs
if cfg.MODEL.KEYPOINTS_ON and cfg.KRCNN.AT_STAGE == 1:
keypoint_rcnn_roi_data.add_keypoint_rcnn_blobs(blob_dict, roidb,
fg_rois_per_image,
fg_inds, im_scale,
batch_idx,
cfg.TRAIN.FG_THRESH)
return blob_dict
def add_rpn_blobs(blobs, im_scales, roidb):
"""Add blobs needed training RPN-only and end-to-end Faster R-CNN models."""
if cfg.FPN.FPN_ON and cfg.FPN.MULTILEVEL_RPN:
# RPN applied to many feature levels, as in the FPN paper
k_max = cfg.FPN.RPN_MAX_LEVEL
k_min = cfg.FPN.RPN_MIN_LEVEL
foas = []
for lvl in range(k_min, k_max + 1):
field_stride = 2.**lvl
anchor_sizes = (cfg.FPN.RPN_ANCHOR_START_SIZE *
2.**(lvl - k_min), )
anchor_aspect_ratios = cfg.FPN.RPN_ASPECT_RATIOS
foa = data_utils.get_field_of_anchors(field_stride, anchor_sizes,
anchor_aspect_ratios)
foas.append(foa)
all_anchors = np.concatenate([f.field_of_anchors for f in foas])
else:
foa = data_utils.get_field_of_anchors(cfg.RPN.STRIDE, cfg.RPN.SIZES,
cfg.RPN.ASPECT_RATIOS)
all_anchors = foa.field_of_anchors
for im_i, entry in enumerate(roidb):
scale = im_scales[im_i]
input_data = blobs['data'][im_i]
# print(input_data.shape)
im_height = np.round(entry['height'] * scale)
im_width = np.round(entry['width'] * scale)
entry['input_width'] = input_data.shape[2]
entry['input_height'] = input_data.shape[1]
gt_inds = np.where((entry['gt_classes'] > 0)
& (entry['is_crowd'] == 0))[0]
gt_rois = entry['boxes'][gt_inds, :] * scale
# TODO(rbg): gt_boxes is poorly named;
# should be something like 'gt_rois_info'
gt_boxes = blob_utils.zeros((len(gt_inds), 6))
gt_boxes[:, 0] = im_i # batch inds
gt_boxes[:, 1:5] = gt_rois
gt_boxes[:, 5] = entry['gt_classes'][gt_inds]
im_info = np.array([[im_height, im_width, scale]], dtype=np.float32)
blobs['im_info'].append(im_info)
# Add RPN targets
if cfg.FPN.FPN_ON and cfg.FPN.MULTILEVEL_RPN:
# RPN applied to many feature levels, as in the FPN paper
rpn_blobs = _get_rpn_blobs(im_height, im_width, foas, all_anchors,
gt_rois)
for i, lvl in enumerate(range(k_min, k_max + 1)):
for k, v in rpn_blobs[i].items():
blobs[k + '_fpn' + str(lvl)].append(v)
else:
# Classical RPN, applied to a single feature level
rpn_blobs = _get_rpn_blobs(im_height, im_width, [foa], all_anchors,
gt_rois)
for k, v in rpn_blobs.items():
blobs[k].append(v)
for k, v in blobs.items():
if isinstance(v, list) and len(v) > 0:
blobs[k] = np.concatenate(v)
valid_keys = [
'has_visible_keypoints', 'boxes', 'segms', 'seg_areas', 'gt_classes',
'gt_overlaps', 'is_crowd', 'box_to_gt_ind_map', 'gt_keypoints',
'flipped', 'ignore_UV_body', 'dp_x', 'dp_y', 'dp_I', 'dp_U', 'dp_V',
'dp_masks', 'input_width', 'input_height'
]
minimal_roidb = [{} for _ in range(len(roidb))]
for i, e in enumerate(roidb):
for k in valid_keys:
if k in e:
minimal_roidb[i][k] = e[k]
blobs['roidb'] = blob_utils.serialize(minimal_roidb)
# Always return valid=True, since RPN minibatches are valid by design
return True
def _sample_rois(roidb, im_scale, batch_idx, stage):
# 随机产生包含前景和背景的正负样本，即rois集合
"""Generate a random sample of RoIs comprising foreground and background
examples.
"""
fg_thresh = cfg.CASCADE_RCNN.FG_THRESHS[stage - 1]
bg_thresh_hi = cfg.CASCADE_RCNN.BG_THRESHS_HI[stage - 1]
bg_thresh_lo = cfg.CASCADE_RCNN.BG_THRESHS_LO[stage - 1]
#### 这个变量很关键：定义了每一个roi与所有gt-bboxes所对应的最大的iou ???
max_overlaps = roidb["max_overlaps"]
# Select foreground RoIs as those with >= FG_THRESH overlap
#### 选择最大iou高于fg_thresh的那些rois，作为前景的indexes-->fg_inds
fg_inds = np.where(max_overlaps >= fg_thresh)[0]
#### 一张img所包含的所有fg_rois数量
fg_rois_per_this_image = fg_inds.size
# Select background RoIs as those within [BG_THRESH_LO, BG_THRESH_HI)
#### 选择那些对应的最大iou值介于（bg_thesh_lo, bg_thresh_hi）的那些rois，采样为背景
bg_inds = np.where((max_overlaps < bg_thresh_hi)
& (max_overlaps >= bg_thresh_lo))[0]
# The indices that we're selecting (both fg and bg)
#### keep_inds为我们将要采样的样本的索引列表（包括正，负样本）
keep_inds = np.append(fg_inds, bg_inds)
# Label is the class each RoI has max overlap with
#### sampled_labels即为roidb中采样的rois所对应的标签值labels
sampled_labels = roidb["max_classes"][keep_inds]
#### 将采样的负样本所对应的标签值都置为0
sampled_labels[fg_rois_per_this_image:] = 0 # Label bg RoIs with class 0
#### sampled_boxes即为roidb中采样的所有正负样本，shape为(, 4)
sampled_boxes = roidb["boxes"][keep_inds]
#### 得到roidb中所有的gt_bbox的index
gt_inds = np.where(roidb["gt_classes"] > 0)[0]
#### 得到gt_bbox构成的集合，shape为(, 4)
gt_boxes = roidb["boxes"][gt_inds, :]
#### 这个有点不太理解了，gt_assignments为所有采样的作为正样本的rois所对应的gt_bboxes集合
gt_assignments = gt_inds[roidb["box_to_gt_ind_map"][keep_inds]]
# [mapped_gt_boxes, max_overlaps]
#### 初始化mapped_gt_boxes变量，保存所有采样的rois所对应的gt_bboxes的坐标（
# 疑问：对于负样本也有gt_bbox??? ）
mapped_gt_boxes = blob_utils.zeros((keep_inds.size, 5))
#### mapped_gt_boxes
#### 将原图对应的
mapped_gt_boxes[:, :4] = gt_boxes[gt_assignments, :] * im_scale
mapped_gt_boxes[:, 4] = max_overlaps[keep_inds]
####对于负样本所对应的行（fg_rois_per_this_image之后的）的数据，全部置为0
mapped_gt_boxes[fg_rois_per_this_image:, :] = 0
if "bbox_targets" not in roidb:
bbox_targets = _compute_targets(sampled_boxes,
gt_boxes[gt_assignments, :],
sampled_labels, stage)
else:
bbox_targets = roidb['bbox_targets'][keep_inds, :]
bbox_targets, bbox_inside_weights = _expand_bbox_targets(bbox_targets)
bbox_outside_weights = np.array(bbox_inside_weights > 0,
dtype=bbox_inside_weights.dtype)
# Scale rois and format as (batch_idx, x1, y1, x2, y2)
sampled_rois = sampled_boxes * im_scale
repeated_batch_idx = batch_idx * blob_utils.ones(
(sampled_rois.shape[0], 1))
sampled_rois = np.hstack((repeated_batch_idx, sampled_rois))
# Base Cascade R-CNN blobs
blob_dict = dict(
labels_int32=sampled_labels.astype(np.int32, copy=False),
rois=sampled_rois,
bbox_targets=bbox_targets,
bbox_inside_weights=bbox_inside_weights,
bbox_outside_weights=bbox_outside_weights,
mapped_gt_boxes=mapped_gt_boxes,
)
# Optionally add Mask R-CNN blobs
if cfg.MODEL.MASK_ON and cfg.MRCNN.AT_STAGE == stage:
mask_rcnn_roi_data.add_mask_rcnn_blobs(blob_dict, sampled_boxes, roidb,
im_scale, batch_idx)
# Optionally add Keypoint R-CNN blobs
if cfg.MODEL.KEYPOINTS_ON and cfg.KRCNN.AT_STAGE == stage:
keypoint_rcnn_roi_data.add_keypoint_rcnn_blobs(blob_dict, roidb,
fg_rois_per_this_image,
fg_inds, im_scale,
batch_idx, fg_thresh)
return blob_dict
def add_mask_rcnn_blobs(blobs, sampled_boxes, roidb, im_scale, batch_idx):
"""Add Mask R-CNN specific blobs to the input blob dictionary."""
# Prepare the mask targets by associating one gt mask to each training roi
# that has a fg (non-bg) class label.
M = cfg.MRCNN.RESOLUTION
polys_gt_inds = np.where(
(roidb['gt_classes'] > 0) & (roidb['is_crowd'] == 0)
)[0]
polys_gt = [roidb['segms'][i] for i in polys_gt_inds]
boxes_from_polys = segm_utils.polys_to_boxes(polys_gt)
fg_inds = np.where(blobs['labels_int32'] > 0)[0]
roi_has_mask = blobs['labels_int32'].copy()
roi_has_mask[roi_has_mask > 0] = 1
if fg_inds.shape[0] > 0:
# Class labels for the foreground rois
mask_class_labels = blobs['labels_int32'][fg_inds]
masks = blob_utils.zeros((fg_inds.shape[0], M**2), int32=True)
# Find overlap between all foreground rois and the bounding boxes
# enclosing each segmentation
rois_fg = sampled_boxes[fg_inds]
overlaps_bbfg_bbpolys = box_utils.bbox_overlaps(
rois_fg.astype(np.float32, copy=False),
boxes_from_polys.astype(np.float32, copy=False)
)
# Map from each fg rois to the index of the mask with highest overlap
# (measured by bbox overlap)
fg_polys_inds = np.argmax(overlaps_bbfg_bbpolys, axis=1)
# add fg targets
for i in range(rois_fg.shape[0]):
fg_polys_ind = fg_polys_inds[i]
poly_gt = polys_gt[fg_polys_ind]
roi_fg = rois_fg[i]
# Rasterize the portion of the polygon mask within the given fg roi
# to an M x M binary image
mask = segm_utils.polys_to_mask_wrt_box(poly_gt, roi_fg, M)
mask = np.array(mask > 0, dtype=np.int32) # Ensure it's binary
masks[i, :] = np.reshape(mask, M**2)
else: # If there are no fg masks (it does happen)
# The network cannot handle empty blobs, so we must provide a mask
# We simply take the first bg roi, given it an all -1's mask (ignore
# label), and label it with class zero (bg).
bg_inds = np.where(blobs['labels_int32'] == 0)[0]
# rois_fg is actually one background roi, but that's ok because ...
rois_fg = sampled_boxes[bg_inds[0]].reshape((1, -1))
# We give it an -1's blob (ignore label)
masks = -blob_utils.ones((1, M**2), int32=True)
# We label it with class = 0 (background)
mask_class_labels = blob_utils.zeros((1, ))
# Mark that the first roi has a mask
roi_has_mask[0] = 1
if cfg.MRCNN.CLS_SPECIFIC_MASK:
masks = _expand_to_class_specific_mask_targets(masks, mask_class_labels)
# Scale rois_fg and format as (batch_idx, x1, y1, x2, y2)
rois_fg *= im_scale
repeated_batch_idx = batch_idx * blob_utils.ones((rois_fg.shape[0], 1))
rois_fg = np.hstack((repeated_batch_idx, rois_fg))
# Update blobs dict with Mask R-CNN blobs
blobs['mask_rois'] = rois_fg
blobs['roi_has_mask_int32'] = roi_has_mask
blobs['masks_int32'] = masks
def add_mask_rcnn_blobs(blobs, sampled_boxes, roidb, im_scale, batch_idx):
"""Add Mask R-CNN specific blobs to the input blob dictionary."""
# Prepare the mask targets by associating one gt mask to each training roi
# that has a fg (non-bg) class label.
M = cfg.MRCNN.RESOLUTION
polys_gt_inds = np.where(
(roidb['gt_classes'] > 0) & (roidb['is_crowd'] == 0)
)[0]
polys_gt = [roidb['segms'][i] for i in polys_gt_inds]
boxes_from_polys = segm_utils.polys_to_boxes(polys_gt)
fg_inds = np.where(blobs['labels_int32'] > 0)[0]
roi_has_mask = blobs['labels_int32'].copy()
roi_has_mask[roi_has_mask > 0] = 1
if fg_inds.shape[0] > 0:
# Class labels for the foreground rois
mask_class_labels = blobs['labels_int32'][fg_inds]
masks = blob_utils.zeros((fg_inds.shape[0], M**2), int32=True)
# Find overlap between all foreground rois and the bounding boxes
# enclosing each segmentation
rois_fg = sampled_boxes[fg_inds]
overlaps_bbfg_bbpolys = box_utils.bbox_overlaps(
rois_fg.astype(np.float32, copy=False),
boxes_from_polys.astype(np.float32, copy=False)
)
# Map from each fg rois to the index of the mask with highest overlap
# (measured by bbox overlap)
fg_polys_inds = np.argmax(overlaps_bbfg_bbpolys, axis=1)
# add fg targets
for i in range(rois_fg.shape[0]):
fg_polys_ind = fg_polys_inds[i]
poly_gt = polys_gt[fg_polys_ind]
roi_fg = rois_fg[i]
# Rasterize the portion of the polygon mask within the given fg roi
# to an M x M binary image
mask = segm_utils.polys_to_mask_wrt_box(poly_gt, roi_fg, M)
mask = np.array(mask > 0, dtype=np.int32) # Ensure it's binary
masks[i, :] = np.reshape(mask, M**2)
else: # If there are no fg masks (it does happen)
# The network cannot handle empty blobs, so we must provide a mask
# We simply take the first bg roi, given it an all -1's mask (ignore
# label), and label it with class zero (bg).
bg_inds = np.where(blobs['labels_int32'] == 0)[0]
# rois_fg is actually one background roi, but that's ok because ...
rois_fg = sampled_boxes[bg_inds[0]].reshape((1, -1))
# We give it an -1's blob (ignore label)
masks = -blob_utils.ones((1, M**2), int32=True)
# We label it with class = 0 (background)
mask_class_labels = blob_utils.zeros((1, ))
# Mark that the first roi has a mask
roi_has_mask[0] = 1
if cfg.MRCNN.CLS_SPECIFIC_MASK:
masks = _expand_to_class_specific_mask_targets(masks, mask_class_labels)
# Scale rois_fg and format as (batch_idx, x1, y1, x2, y2)
rois_fg *= im_scale
repeated_batch_idx = batch_idx * blob_utils.ones((rois_fg.shape[0], 1))
rois_fg = np.hstack((repeated_batch_idx, rois_fg))
# Update blobs dict with Mask R-CNN blobs
blobs['mask_rois'] = rois_fg
blobs['roi_has_mask_int32'] = roi_has_mask
blobs['masks_int32'] = masks
def add_rpn_blobs(blobs, im_scales, roidb):
"""Add blobs needed training RPN-only and end-to-end Faster R-CNN models."""
"""
添加训练faster rcnn需要的blobs
"""
if cfg.FPN.FPN_ON and cfg.FPN.MULTILEVEL_RPN:
# RPN applied to many feature levels, as in the FPN paper
k_max = cfg.FPN.RPN_MAX_LEVEL
k_min = cfg.FPN.RPN_MIN_LEVEL
foas = []
for lvl in range(k_min, k_max + 1):
# lvl = 2 => 4.0
field_stride = 2.**lvl
# 32.0
anchor_sizes = (cfg.FPN.RPN_ANCHOR_START_SIZE *
2.**(lvl - k_min), )
# [0.5, 1.0, 2.0]
anchor_aspect_ratios = cfg.FPN.RPN_ASPECT_RATIOS
# 对于一个特征图，获得特征图上每一个cell所对应的anchor，
# 该anchor对应于网络输入的大小
foa = data_utils.get_field_of_anchors(field_stride, anchor_sizes,
anchor_aspect_ratios)
foas.append(foa)
all_anchors = np.concatenate([f.field_of_anchors for f in foas])
else:
foa = data_utils.get_field_of_anchors(cfg.RPN.STRIDE, cfg.RPN.SIZES,
cfg.RPN.ASPECT_RATIOS)
all_anchors = foa.field_of_anchors
for im_i, entry in enumerate(roidb):
scale = im_scales[im_i]
# * scale获得相对于网络输入的信息
im_height = np.round(entry['height'] * scale)
im_width = np.round(entry['width'] * scale)
gt_inds = np.where((entry['gt_classes'] > 0)
& (entry['is_crowd'] == 0))[0]
# gt box
gt_rois = entry['boxes'][gt_inds, :] * scale
# TODO(rbg): gt_boxes is poorly named;
# should be something like 'gt_rois_info'
gt_boxes = blob_utils.zeros((len(gt_inds), 6))
# 属于哪个图片
gt_boxes[:, 0] = im_i # batch inds
# box
gt_boxes[:, 1:5] = gt_rois
# 类别信息
gt_boxes[:, 5] = entry['gt_classes'][gt_inds]
# 写入blob
im_info = np.array([[im_height, im_width, scale]], dtype=np.float32)
blobs['im_info'].append(im_info)
# Add RPN targets
# 添加RPN的目标值
if cfg.FPN.FPN_ON and cfg.FPN.MULTILEVEL_RPN:
# RPN applied to many feature levels, as in the FPN paper
rpn_blobs = _get_rpn_blobs(im_height, im_width, foas, all_anchors,
gt_rois)
for i, lvl in enumerate(range(k_min, k_max + 1)):
for k, v in rpn_blobs[i].items():
blobs[k + '_fpn' + str(lvl)].append(v)
else:
# Classical RPN, applied to a single feature level
rpn_blobs = _get_rpn_blobs(im_height, im_width, [foa], all_anchors,
gt_rois)
for k, v in rpn_blobs.items():
blobs[k].append(v)
for k, v in blobs.items():
if isinstance(v, list) and len(v) > 0:
blobs[k] = np.concatenate(v)
valid_keys = [
'has_visible_keypoints', 'boxes', 'segms', 'seg_areas', 'gt_classes',
'gt_overlaps', 'is_crowd', 'box_to_gt_ind_map', 'gt_keypoints'
]
minimal_roidb = [{} for _ in range(len(roidb))]
for i, e in enumerate(roidb):
for k in valid_keys:
if k in e:
minimal_roidb[i][k] = e[k]
blobs['roidb'] = blob_utils.serialize(minimal_roidb)
# Always return valid=True, since RPN minibatches are valid by design
return True
def add_rpn_blobs(blobs, im_scales, roidb):
"""Add blobs needed training RPN-only and end-to-end Faster R-CNN models."""
if cfg.FPN.FPN_ON and cfg.FPN.MULTILEVEL_RPN:
# RPN applied to many feature levels, as in the FPN paper
k_max = cfg.FPN.RPN_MAX_LEVEL
k_min = cfg.FPN.RPN_MIN_LEVEL
foas = []
for lvl in range(k_min, k_max + 1):
field_stride = 2.**lvl
anchor_sizes = (cfg.FPN.RPN_ANCHOR_START_SIZE * 2.**(lvl - k_min), )
anchor_aspect_ratios = cfg.FPN.RPN_ASPECT_RATIOS
foa = data_utils.get_field_of_anchors(
field_stride, anchor_sizes, anchor_aspect_ratios
)
foas.append(foa)
all_anchors = np.concatenate([f.field_of_anchors for f in foas])
else:
foa = data_utils.get_field_of_anchors(
cfg.RPN.STRIDE, cfg.RPN.SIZES, cfg.RPN.ASPECT_RATIOS
)
all_anchors = foa.field_of_anchors
for im_i, entry in enumerate(roidb):
scale = im_scales[im_i]
im_height = np.round(entry['height'] * scale)
im_width = np.round(entry['width'] * scale)
gt_inds = np.where(
(entry['gt_classes'] > 0) & (entry['is_crowd'] == 0)
)[0]
gt_rois = entry['boxes'][gt_inds, :] * scale
# TODO(rbg): gt_boxes is poorly named;
# should be something like 'gt_rois_info'
gt_boxes = blob_utils.zeros((len(gt_inds), 6))
gt_boxes[:, 0] = im_i # batch inds
gt_boxes[:, 1:5] = gt_rois
gt_boxes[:, 5] = entry['gt_classes'][gt_inds]
im_info = np.array([[im_height, im_width, scale]], dtype=np.float32)
blobs['im_info'].append(im_info)
# Add RPN targets
if cfg.FPN.FPN_ON and cfg.FPN.MULTILEVEL_RPN:
# RPN applied to many feature levels, as in the FPN paper
rpn_blobs = _get_rpn_blobs(
im_height, im_width, foas, all_anchors, gt_rois
)
for i, lvl in enumerate(range(k_min, k_max + 1)):
for k, v in rpn_blobs[i].items():
blobs[k + '_fpn' + str(lvl)].append(v)
else:
# Classical RPN, applied to a single feature level
rpn_blobs = _get_rpn_blobs(
im_height, im_width, [foa], all_anchors, gt_rois
)
for k, v in rpn_blobs.items():
blobs[k].append(v)
for k, v in blobs.items():
if isinstance(v, list) and len(v) > 0:
blobs[k] = np.concatenate(v)
valid_keys = [
'has_visible_keypoints', 'boxes', 'segms', 'seg_areas', 'gt_classes',
'gt_overlaps', 'is_crowd', 'box_to_gt_ind_map', 'gt_keypoints','flipped', 'ignore_UV_body','dp_x','dp_y','dp_I','dp_U','dp_V','dp_masks' ]
minimal_roidb = [{} for _ in range(len(roidb))]
for i, e in enumerate(roidb):
for k in valid_keys:
if k in e:
minimal_roidb[i][k] = e[k]
blobs['roidb'] = blob_utils.serialize(minimal_roidb)
# Always return valid=True, since RPN minibatches are valid by design
return True
def add_mask_rcnn_blobs(blobs, sampled_boxes, roidb, im_scale, batch_idx):
"""Add Mask R-CNN specific blobs to the input blob dictionary."""
# Prepare the mask targets by associating one gt mask to each training roi
# that has a fg (non-bg) class label.
M = cfg.MRCNN.RESOLUTION
# gao 6,29
gt_inds = np.where((roidb['gt_classes'] > 0) & (roidb['is_crowd'] == 0))[0]
boxes_from_polys = roidb['boxes'][gt_inds, :]
gt_classes = roidb['gt_classes'][gt_inds]
im_label = cv2.imread(roidb['ins_seg'], 0)
if roidb['flipped'] == 1: # convert flipped label to original
im_label = im_label[:, ::-1]
dataset_name = cfg.TRAIN.DATASETS[0]
if 'LIP' in dataset_name:
flipped_2_orig_class = {
14: 15,
15: 14,
16: 17,
17: 16,
18: 19,
19: 18
}
if 'ATR' in dataset_name:
flipped_2_orig_class = {
9: 10,
10: 9,
12: 13,
13: 12,
14: 15,
15: 14
}
gt_classes_ = copy.deepcopy(gt_classes)
for i in flipped_2_orig_class.keys():
index_i = np.where(gt_classes_ == i)[0]
if len(index_i) == 0:
continue
gt_classes[index_i] = flipped_2_orig_class[i]
# gt_inds_flip = np.where(gt_classes>13)[0]
# for i in gt_inds_flip:
# gt_classes[i] = flipped_2_orig_class[gt_classes[i]]
fg_inds = np.where(blobs['labels_int32'] > 0)[0]
roi_has_mask = blobs['labels_int32'].copy()
roi_has_mask[roi_has_mask > 0] = 1
if fg_inds.shape[0] > 0:
# Class labels for the foreground rois
mask_class_labels = blobs['labels_int32'][fg_inds]
masks = blob_utils.zeros((fg_inds.shape[0], M**2), int32=True)
# Find overlap between all foreground rois and the bounding boxes
# enclosing each segmentation
rois_fg = sampled_boxes[fg_inds]
overlaps_bbfg_bbpolys = box_utils.bbox_overlaps(
rois_fg.astype(np.float32, copy=False),
boxes_from_polys.astype(np.float32, copy=False))
# Map from each fg rois to the index of the mask with highest overlap
# (measured by bbox overlap)
fg_polys_inds = np.argmax(overlaps_bbfg_bbpolys, axis=1)
# add fg targets
for i in range(rois_fg.shape[0]):
fg_polys_ind = fg_polys_inds[i]
# poly_gt = polys_gt[fg_polys_ind]
roi_fg = rois_fg[i]
# Rasterize the portion of the polygon mask within the given fg roi
# to an M x M binary image
#logger.info('roi_fg, label shape: {},{}'.format(roi_fg,im_label.shape))
x0, y0, x1, y1 = roi_fg
x0 = min(int(x0), im_label.shape[1])
x1 = min(int(x1 + 1), im_label.shape[1])
y0 = min(int(y0), im_label.shape[0])
y1 = min(int(y1 + 1), im_label.shape[0])
#logger.info('x0,y0,x1,y1: {}'.format(x0, y0, x1, y1))
mask_ = im_label[y0:y1, x0:x1]
#logger.info('mask_ shape: {}, gt_classes[fg_polys_ind]:{}'.format(mask_.shape, boxes_from_polys[fg_polys_ind]))
# mask = segm_utils.polys_to_mask_wrt_box(poly_gt, roi_fg, M)
mask = np.array(mask_ == gt_classes[fg_polys_ind],
dtype=np.int32) # Ensure it's binary
mask = cv2.resize(mask, (M, M), interpolation=cv2.INTER_NEAREST)
masks[i, :] = np.reshape(mask, M**2)
im_label = None
else: # If there are no fg masks (it does happen)
# The network cannot handle empty blobs, so we must provide a mask
# We simply take the first bg roi, given it an all -1's mask (ignore
# label), and label it with class zero (bg).
bg_inds = np.where(blobs['labels_int32'] == 0)[0]
# rois_fg is actually one background roi, but that's ok because ...
rois_fg = sampled_boxes[bg_inds[0]].reshape((1, -1))
# We give it an -1's blob (ignore label)
masks = -blob_utils.ones((1, M**2), int32=True)
# We label it with class = 0 (background)
mask_class_labels = blob_utils.zeros((1, ))
# Mark that the first roi has a mask
roi_has_mask[0] = 1
if cfg.MRCNN.CLS_SPECIFIC_MASK:
masks = _expand_to_class_specific_mask_targets(masks,
mask_class_labels)
# Scale rois_fg and format as (batch_idx, x1, y1, x2, y2)
rois_fg *= im_scale
repeated_batch_idx = batch_idx * blob_utils.ones((rois_fg.shape[0], 1))
rois_fg = np.hstack((repeated_batch_idx, rois_fg))
# Update blobs dict with Mask R-CNN blobs
blobs['mask_rois'] = rois_fg
blobs['roi_has_mask_int32'] = roi_has_mask
blobs['masks_int32'] = masks
def add_body_uv_rcnn_blobs(blobs, sampled_boxes, roidb, im_scale, batch_idx):
IsFlipped = roidb['flipped']
M = cfg.BODY_UV_RCNN.HEATMAP_SIZE
#
polys_gt_inds = np.where(roidb['ignore_UV_body'] == 0)[0]
boxes_from_polys = [roidb['boxes'][i, :] for i in polys_gt_inds]
input_w = roidb['input_width']
input_h = roidb['input_height']
if not (boxes_from_polys):
pass
else:
boxes_from_polys = np.vstack(boxes_from_polys)
boxes_from_polys = np.array(boxes_from_polys)
fg_inds = np.where(blobs['labels_int32'] > 0)[0]
roi_has_mask = np.zeros(blobs['labels_int32'].shape)
if (bool(boxes_from_polys.any()) & (fg_inds.shape[0] > 0)):
rois_fg = sampled_boxes[fg_inds]
#
rois_fg.astype(np.float32, copy=False)
boxes_from_polys.astype(np.float32, copy=False)
#
overlaps_bbfg_bbpolys = box_utils.bbox_overlaps(
rois_fg.astype(np.float32, copy=False),
boxes_from_polys.astype(np.float32, copy=False))
fg_polys_value = np.max(overlaps_bbfg_bbpolys, axis=1)
fg_inds = fg_inds[fg_polys_value > 0.7]
all_person_masks = np.zeros((int(input_h), int(input_w)), dtype=np.float32)
if (bool(boxes_from_polys.any()) & (fg_inds.shape[0] > 0)):
# controle the number of roi
if fg_inds.shape[0] > 6:
fg_inds = fg_inds[:6]
for jj in fg_inds:
roi_has_mask[jj] = 1
# Create blobs for densepose supervision.
################################################## The mask
All_labels = blob_utils.zeros((fg_inds.shape[0], M**2), int32=True)
All_Weights = blob_utils.zeros((fg_inds.shape[0], M**2), int32=True)
################################################# The points
X_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
Y_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
Ind_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=True)
I_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=True)
U_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
V_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
Uv_point_weights = blob_utils.zeros((fg_inds.shape[0], 196),
int32=False)
#################################################
rois_fg = sampled_boxes[fg_inds]
overlaps_bbfg_bbpolys = box_utils.bbox_overlaps(
rois_fg.astype(np.float32, copy=False),
boxes_from_polys.astype(np.float32, copy=False))
fg_polys_inds = np.argmax(overlaps_bbfg_bbpolys, axis=1)
rois = np.copy(rois_fg)
for i in range(rois_fg.shape[0]):
#
fg_polys_ind = polys_gt_inds[fg_polys_inds[i]]
#
Ilabel = segm_utils.GetDensePoseMask(
roidb['dp_masks'][fg_polys_ind])
#
GT_I = np.array(roidb['dp_I'][fg_polys_ind])
GT_U = np.array(roidb['dp_U'][fg_polys_ind])
GT_V = np.array(roidb['dp_V'][fg_polys_ind])
GT_x = np.array(roidb['dp_x'][fg_polys_ind])
GT_y = np.array(roidb['dp_y'][fg_polys_ind])
GT_weights = np.ones(GT_I.shape).astype(np.float32)
#
## Do the flipping of the densepose annotation !
if (IsFlipped):
GT_I, GT_U, GT_V, GT_x, GT_y, Ilabel = DP.get_symmetric_densepose(
GT_I, GT_U, GT_V, GT_x, GT_y, Ilabel)
#
roi_fg = rois_fg[i]
roi_gt = boxes_from_polys[fg_polys_inds[i], :]
#
x1 = roi_fg[0]
x2 = roi_fg[2]
y1 = roi_fg[1]
y2 = roi_fg[3]
#
x1_source = roi_gt[0]
x2_source = roi_gt[2]
y1_source = roi_gt[1]
y2_source = roi_gt[3]
#
x_targets = (np.arange(x1, x2, (x2 - x1) / M) -
x1_source) * (256. / (x2_source - x1_source))
y_targets = (np.arange(y1, y2, (y2 - y1) / M) -
y1_source) * (256. / (y2_source - y1_source))
#
x_targets = x_targets[
0:
M] ## Strangely sometimes it can be M+1, so make sure size is OK!
y_targets = y_targets[0:M]
#
[X_targets, Y_targets] = np.meshgrid(x_targets, y_targets)
New_Index = cv2.remap(Ilabel,
X_targets.astype(np.float32),
Y_targets.astype(np.float32),
interpolation=cv2.INTER_NEAREST,
borderMode=cv2.BORDER_CONSTANT,
borderValue=(0))
#
All_L = np.zeros(New_Index.shape)
All_W = np.ones(New_Index.shape)
#
All_L = New_Index
#
gt_length_x = x2_source - x1_source
gt_length_y = y2_source - y1_source
#
GT_y = ((GT_y / 256. * gt_length_y) + y1_source - y1) * (M /
(y2 - y1))
GT_x = ((GT_x / 256. * gt_length_x) + x1_source - x1) * (M /
(x2 - x1))
#
GT_I[GT_y < 0] = 0
GT_I[GT_y > (M - 1)] = 0
GT_I[GT_x < 0] = 0
GT_I[GT_x > (M - 1)] = 0
#
points_inside = GT_I > 0
GT_U = GT_U[points_inside]
GT_V = GT_V[points_inside]
GT_x = GT_x[points_inside]
GT_y = GT_y[points_inside]
GT_weights = GT_weights[points_inside]
GT_I = GT_I[points_inside]
#
X_points[i, 0:len(GT_x)] = GT_x
Y_points[i, 0:len(GT_y)] = GT_y
Ind_points[i, 0:len(GT_I)] = i
I_points[i, 0:len(GT_I)] = GT_I
U_points[i, 0:len(GT_U)] = GT_U
V_points[i, 0:len(GT_V)] = GT_V
Uv_point_weights[i, 0:len(GT_weights)] = GT_weights
#
All_labels[i, :] = np.reshape(All_L.astype(np.int32), M**2)
All_Weights[i, :] = np.reshape(All_W.astype(np.int32), M**2)
##
# proposal based segmentation
p_mask = (Ilabel > 0).astype(np.float32)
target_roi = roi_gt * im_scale
p_mask = cv2.resize(p_mask, (int(target_roi[2] - target_roi[0]),
int(target_roi[3] - target_roi[1])))
p_mask = (p_mask > 0.5).astype(np.float32)
start_y, start_x = int(target_roi[1]), int(target_roi[0])
end_y, end_x = start_y + p_mask.shape[0], start_x + p_mask.shape[1]
# if all_person_masks[start_y:end_y, start_x:end_x].shape[0]!=p_mask.shape[0] or all_person_masks[start_y:end_y, start_x:end_x].shape[1]!=p_mask.shape[1]:
# print('shape exception:',all_person_masks[start_y:end_y, start_x:end_x].shape,p_mask.shape)
# print('roi:',target_roi)
# print(start_y,end_y, start_x,end_x)
# print('input image:',all_person_masks.shape)
# assert False
all_person_masks[start_y:end_y, start_x:end_x] = p_mask
else:
bg_inds = np.where(blobs['labels_int32'] == 0)[0]
#
if (len(bg_inds) == 0):
rois_fg = sampled_boxes[0].reshape((1, -1))
else:
rois_fg = sampled_boxes[bg_inds[0]].reshape((1, -1))
roi_has_mask[0] = 1
#
X_points = blob_utils.zeros((1, 196), int32=False)
Y_points = blob_utils.zeros((1, 196), int32=False)
Ind_points = blob_utils.zeros((1, 196), int32=True)
I_points = blob_utils.zeros((1, 196), int32=True)
U_points = blob_utils.zeros((1, 196), int32=False)
V_points = blob_utils.zeros((1, 196), int32=False)
Uv_point_weights = blob_utils.zeros((1, 196), int32=False)
#
All_labels = -blob_utils.ones((1, M**2), int32=True) * 0 ## zeros
All_Weights = -blob_utils.ones((1, M**2), int32=True) * 0 ## zeros
#
rois_fg *= im_scale
repeated_batch_idx = batch_idx * blob_utils.ones((rois_fg.shape[0], 1))
rois_fg = np.hstack((repeated_batch_idx, rois_fg))
#
K = cfg.BODY_UV_RCNN.NUM_PATCHES
#
u_points = np.copy(U_points)
v_points = np.copy(V_points)
U_points = np.tile(U_points, [1, K + 1])
V_points = np.tile(V_points, [1, K + 1])
Uv_Weight_Points = np.zeros(U_points.shape)
#
for jjj in xrange(1, K + 1):
Uv_Weight_Points[:, jjj * I_points.shape[1]:(jjj + 1) *
I_points.shape[1]] = (I_points == jjj).astype(
np.float32)
#
# person masks here
person_mask = (All_labels > 0).astype(np.int32)
# extra
# index_targets = np.zeros_like(person_mask).reshape((-1,M,M)).astype(np.int32)
# index_targets_weights = np.zeros_like(index_targets)
# u_targets = np.zeros((index_targets.shape[0],25,M,M),dtype=np.float32)
# v_targets = np.zeros((index_targets.shape[0], 25, M, M),dtype=np.float32)
# uv_weights = np.zeros((index_targets.shape[0], 25, M, M),dtype=np.float32)
# for ibatch in range(index_targets.shape[0]):
# for i_surface in range(1,K+1):
# points_i = I_points[ibatch] == i_surface
# if len(points_i)>0:
# points_x = np.asarray(X_points[ibatch][points_i], dtype=np.int32).reshape((-1,1))
# points_y = np.asarray(Y_points[ibatch][points_i], dtype=np.int32).reshape((-1,1))
# points_u = u_points[ibatch][points_i].reshape((1, -1))
# points_v = v_points[ibatch][points_i].reshape((1, -1))
# locs = np.hstack([points_x, points_y])
#
# for step in [1]:
# x_plus_locs = np.copy(points_x) + step
# y_plus_locs = np.copy(points_y) + step
# x_minus_locs = np.copy(points_x) - step
# y_minus_locs = np.copy(points_y) - step
#
# locs = np.vstack([locs, np.hstack([x_plus_locs, y_plus_locs])])
# locs = np.vstack([locs, np.hstack([x_plus_locs, y_minus_locs])])
# locs = np.vstack([locs, np.hstack([x_minus_locs, y_plus_locs])])
# locs = np.vstack([locs, np.hstack([x_minus_locs, y_minus_locs])])
#
# locs[locs < 0] = 0.
# locs[locs >= M] = M - 1
#
# points_u = np.repeat(points_u, 5, axis=0).reshape((-1))
# points_v = np.repeat(points_v, 5, axis=0).reshape((-1))
#
#
# index_targets[ibatch][locs[:,1], locs[:, 0]] = i_surface
# index_targets_weights[ibatch][locs[:, 1], locs[:, 0]] = 1
# u_targets[ibatch, i_surface][locs[:, 1], locs[:, 0]] = points_u
# v_targets[ibatch, i_surface][locs[:, 1], locs[:, 0]] = points_v
# uv_weights[ibatch, i_surface][locs[:, 1], locs[:, 0]] = 1.
# if random.random() <= 0.5:
# _,index_targets[ibatch], v_targets[ibatch], v_targets[ibatch], index_targets_weights[ibatch], uv_weights[ibatch] = expand_dp_targets(All_labels[ibatch].reshape((M,M)),
# index_targets[ibatch], v_targets[ibatch],
# v_targets[ibatch],
# index_targets_weights[ibatch],
# uv_weights[ibatch])
# proposal all masks here
if (bool(boxes_from_polys.any()) & (fg_inds.shape[0] > 0)):
proposal_all_mask = blob_utils.zeros((fg_inds.shape[0], M, M),
int32=True)
for i in range(rois_fg.shape[0]):
roi_fg = rois_fg[i][1:]
proposal_mask = all_person_masks[int(roi_fg[1]):int(roi_fg[3]),
int(roi_fg[0]):int(roi_fg[2])]
proposal_mask = cv2.resize(proposal_mask, (M, M))
proposal_mask = (proposal_mask > 0.5).astype(np.int32)
proposal_all_mask[i] = proposal_mask
else:
proposal_all_mask = -blob_utils.ones(
(1, M, M), int32=True) * 0 ## zeros
################
# Update blobs dict with Mask R-CNN blobs
###############
#
blobs['body_mask_labels'] = person_mask.reshape((-1, M, M))
blobs['body_uv_rois'] = np.array(rois_fg)
blobs['roi_has_body_uv_int32'] = np.array(roi_has_mask).astype(np.int32)
##
blobs['body_uv_ann_labels'] = np.array(All_labels).astype(np.int32)
blobs['body_uv_ann_weights'] = np.array(All_Weights).astype(np.float32)
#
##########################
blobs['body_uv_X_points'] = X_points.astype(np.float32)
blobs['body_uv_Y_points'] = Y_points.astype(np.float32)
blobs['body_uv_Ind_points'] = Ind_points.astype(np.float32)
blobs['body_uv_I_points'] = I_points.astype(np.float32)
blobs['body_uv_U_points'] = U_points.astype(
np.float32) #### VERY IMPORTANT : These are switched here :
blobs['body_uv_V_points'] = V_points.astype(np.float32)
blobs['body_uv_point_weights'] = Uv_Weight_Points.astype(np.float32)
###################
# extra
# blobs['body_uv_Index_targets'] = index_targets
# blobs['body_uv_Index_targets_weights'] = index_targets_weights.astype(np.float32)
# blobs['body_uv_U_targets'] = u_targets
# blobs['body_uv_V_targets'] = v_targets
# blobs['body_uv_weights'] = uv_weights
################
# add by wxh
if cfg.BODY_UV_RCNN.USE_CLS_EMBS:
fg_embs, bg_embs, fg_weights, bg_weights = masks_to_embs(
All_labels.reshape((-1, M, M)))
# print('fg',fg_embs.max(), fg_embs.min())
# print('bg',bg_embs.max(), bg_embs.min())
fg_norms = np.sum(fg_embs, axis=(1, 2))
fg_norms[fg_norms != 0] = 56. * 56. / fg_norms[fg_norms != 0]
bg_norms = np.sum(bg_embs, axis=(1, 2))
bg_norms[bg_norms != 0] = 56. * 56. / bg_norms[bg_norms != 0]
blobs['fg_mask'] = np.repeat(np.reshape(fg_embs, (-1, 1, M, M)),
2,
axis=1)
blobs['bg_mask'] = np.repeat(np.reshape(bg_embs, (-1, 1, M, M)),
2,
axis=1)
blobs['fg_norm'] = np.repeat(np.reshape(fg_norms, (-1, 1)), 2, axis=1)
blobs['bg_norm'] = np.repeat(np.reshape(bg_norms, (-1, 1)), 2, axis=1)
blobs['mask_emb_fg_labels'] = np.ones((fg_embs.shape[0], 1),
dtype=np.int32)
blobs['mask_emb_bg_labels'] = np.zeros((bg_embs.shape[0], 1),
dtype=np.int32)
blobs['mask_emb_weights'] = np.vstack([fg_weights,
bg_weights]).reshape(
(-1, 1)).astype(np.float32)
if cfg.BODY_UV_RCNN.USE_BOX_ALL_MASKS:
blobs['body_masks_wrt_box'] = proposal_all_mask
def add_body_uv_rcnn_blobs(blobs, sampled_boxes, roidb, im_scale, batch_idx):
IsFlipped = roidb['flipped']
M = cfg.BODY_UV_RCNN.HEATMAP_SIZE
#
polys_gt_inds = np.where(roidb['ignore_UV_body'] == 0)[0]
boxes_from_polys = [roidb['boxes'][i,:] for i in polys_gt_inds]
if not(boxes_from_polys):
pass
else:
boxes_from_polys = np.vstack(boxes_from_polys)
boxes_from_polys = np.array(boxes_from_polys)
fg_inds = np.where(blobs['labels_int32'] > 0)[0]
roi_has_mask = np.zeros( blobs['labels_int32'].shape )
if (bool(boxes_from_polys.any()) & (fg_inds.shape[0] > 0) ):
rois_fg = sampled_boxes[fg_inds]
#
rois_fg.astype(np.float32, copy=False)
boxes_from_polys.astype(np.float32, copy=False)
#
overlaps_bbfg_bbpolys = box_utils.bbox_overlaps(
rois_fg.astype(np.float32, copy=False),
boxes_from_polys.astype(np.float32, copy=False))
fg_polys_value = np.max(overlaps_bbfg_bbpolys, axis=1)
fg_inds = fg_inds[fg_polys_value>0.7]
if (bool(boxes_from_polys.any()) & (fg_inds.shape[0] > 0) ):
for jj in fg_inds:
roi_has_mask[jj] = 1
# Create blobs for densepose supervision.
################################################## The mask
All_labels = blob_utils.zeros((fg_inds.shape[0], M ** 2), int32=True)
All_Weights = blob_utils.zeros((fg_inds.shape[0], M ** 2), int32=True)
################################################# The points
X_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
Y_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
Ind_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=True)
I_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=True)
U_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
V_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
Uv_point_weights = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
#################################################
rois_fg = sampled_boxes[fg_inds]
overlaps_bbfg_bbpolys = box_utils.bbox_overlaps(
rois_fg.astype(np.float32, copy=False),
boxes_from_polys.astype(np.float32, copy=False))
fg_polys_inds = np.argmax(overlaps_bbfg_bbpolys, axis=1)
for i in range(rois_fg.shape[0]):
#
fg_polys_ind = polys_gt_inds[ fg_polys_inds[i] ]
#
Ilabel = segm_utils.GetDensePoseMask( roidb['dp_masks'][ fg_polys_ind ] )
#
GT_I = np.array(roidb['dp_I'][ fg_polys_ind ])
GT_U = np.array(roidb['dp_U'][ fg_polys_ind ])
GT_V = np.array(roidb['dp_V'][ fg_polys_ind ])
GT_x = np.array(roidb['dp_x'][ fg_polys_ind ])
GT_y = np.array(roidb['dp_y'][ fg_polys_ind ])
GT_weights = np.ones(GT_I.shape).astype(np.float32)
#
## Do the flipping of the densepose annotation !
if(IsFlipped):
GT_I,GT_U,GT_V,GT_x,GT_y,Ilabel = DP.get_symmetric_densepose(GT_I,GT_U,GT_V,GT_x,GT_y,Ilabel)
#
roi_fg = rois_fg[i]
roi_gt = boxes_from_polys[fg_polys_inds[i],:]
#
x1 = roi_fg[0] ; x2 = roi_fg[2]
y1 = roi_fg[1] ; y2 = roi_fg[3]
#
x1_source = roi_gt[0]; x2_source = roi_gt[2]
y1_source = roi_gt[1]; y2_source = roi_gt[3]
#
x_targets = ( np.arange(x1,x2, (x2 - x1)/M ) - x1_source ) * ( 256. / (x2_source-x1_source) )
y_targets = ( np.arange(y1,y2, (y2 - y1)/M ) - y1_source ) * ( 256. / (y2_source-y1_source) )
#
x_targets = x_targets[0:M] ## Strangely sometimes it can be M+1, so make sure size is OK!
y_targets = y_targets[0:M]
#
[X_targets,Y_targets] = np.meshgrid( x_targets, y_targets )
New_Index = cv2.remap(Ilabel,X_targets.astype(np.float32), Y_targets.astype(np.float32), interpolation=cv2.INTER_NEAREST, borderMode= cv2.BORDER_CONSTANT, borderValue=(0))
#
All_L = np.zeros(New_Index.shape)
All_W = np.ones(New_Index.shape)
#
All_L = New_Index
#
gt_length_x = x2_source - x1_source
gt_length_y = y2_source - y1_source
#
GT_y = (( GT_y / 256. * gt_length_y ) + y1_source - y1 ) * ( M / ( y2 - y1 ) )
GT_x = (( GT_x / 256. * gt_length_x ) + x1_source - x1 ) * ( M / ( x2 - x1 ) )
#
GT_I[GT_y<0] = 0
GT_I[GT_y>(M-1)] = 0
GT_I[GT_x<0] = 0
GT_I[GT_x>(M-1)] = 0
#
points_inside = GT_I>0
GT_U = GT_U[points_inside]
GT_V = GT_V[points_inside]
GT_x = GT_x[points_inside]
GT_y = GT_y[points_inside]
GT_weights = GT_weights[points_inside]
GT_I = GT_I[points_inside]
#
X_points[i, 0:len(GT_x)] = GT_x
Y_points[i, 0:len(GT_y)] = GT_y
Ind_points[i, 0:len(GT_I)] = i
I_points[i, 0:len(GT_I)] = GT_I
U_points[i, 0:len(GT_U)] = GT_U
V_points[i, 0:len(GT_V)] = GT_V
Uv_point_weights[i, 0:len(GT_weights)] = GT_weights
#
All_labels[i, :] = np.reshape(All_L.astype(np.int32), M ** 2)
All_Weights[i, :] = np.reshape(All_W.astype(np.int32), M ** 2)
##
else:
bg_inds = np.where(blobs['labels_int32'] == 0)[0]
#
if(len(bg_inds)==0):
rois_fg = sampled_boxes[0].reshape((1, -1))
else:
rois_fg = sampled_boxes[bg_inds[0]].reshape((1, -1))
roi_has_mask[0] = 1
#
X_points = blob_utils.zeros((1, 196), int32=False)
Y_points = blob_utils.zeros((1, 196), int32=False)
Ind_points = blob_utils.zeros((1, 196), int32=True)
I_points = blob_utils.zeros((1,196), int32=True)
U_points = blob_utils.zeros((1, 196), int32=False)
V_points = blob_utils.zeros((1, 196), int32=False)
Uv_point_weights = blob_utils.zeros((1, 196), int32=False)
#
All_labels = -blob_utils.ones((1, M ** 2), int32=True) * 0 ## zeros
All_Weights = -blob_utils.ones((1, M ** 2), int32=True) * 0 ## zeros
#
rois_fg *= im_scale
repeated_batch_idx = batch_idx * blob_utils.ones((rois_fg.shape[0], 1))
rois_fg = np.hstack((repeated_batch_idx, rois_fg))
#
K = cfg.BODY_UV_RCNN.NUM_PATCHES
#
U_points = np.tile( U_points , [1,K+1] )
V_points = np.tile( V_points , [1,K+1] )
Uv_Weight_Points = np.zeros(U_points.shape)
#
for jjj in xrange(1,K+1):
Uv_Weight_Points[ : , jjj * I_points.shape[1] : (jjj+1) * I_points.shape[1] ] = ( I_points == jjj ).astype(np.float32)
#
################
# Update blobs dict with Mask R-CNN blobs
###############
#
blobs['body_uv_rois'] = np.array(rois_fg)
blobs['roi_has_body_uv_int32'] = np.array(roi_has_mask).astype(np.int32)
##
blobs['body_uv_ann_labels'] = np.array(All_labels).astype(np.int32)
blobs['body_uv_ann_weights'] = np.array(All_Weights).astype(np.float32)
#
##########################
blobs['body_uv_X_points'] = X_points.astype(np.float32)
blobs['body_uv_Y_points'] = Y_points.astype(np.float32)
blobs['body_uv_Ind_points'] = Ind_points.astype(np.float32)
blobs['body_uv_I_points'] = I_points.astype(np.float32)
blobs['body_uv_U_points'] = U_points.astype(np.float32) #### VERY IMPORTANT : These are switched here :
blobs['body_uv_V_points'] = V_points.astype(np.float32)
blobs['body_uv_point_weights'] = Uv_Weight_Points.astype(np.float32)
def add_body_uv_rcnn_blobs(blobs, sampled_boxes, roidb, im_scale, batch_idx):
IsFlipped = roidb['flipped']
M = cfg.BODY_UV_RCNN.HEATMAP_SIZE
#
polys_gt_inds = np.where(roidb['ignore_UV_body'] == 0)[0]
boxes_from_polys = [roidb['boxes'][i, :] for i in polys_gt_inds]
if not (boxes_from_polys):
pass
else:
boxes_from_polys = np.vstack(boxes_from_polys)
boxes_from_polys = np.array(boxes_from_polys)
fg_inds = np.where(blobs['labels_int32'] > 0)[0]
roi_has_mask = np.zeros(blobs['labels_int32'].shape)
if (bool(boxes_from_polys.any()) & (fg_inds.shape[0] > 0)):
rois_fg = sampled_boxes[fg_inds]
#
rois_fg.astype(np.float32, copy=False)
boxes_from_polys.astype(np.float32, copy=False)
#
overlaps_bbfg_bbpolys = box_utils.bbox_overlaps(
rois_fg.astype(np.float32, copy=False),
boxes_from_polys.astype(np.float32, copy=False))
fg_polys_value = np.max(overlaps_bbfg_bbpolys, axis=1)
fg_inds = fg_inds[fg_polys_value > 0.7]
if (bool(boxes_from_polys.any()) & (fg_inds.shape[0] > 0)):
for jj in fg_inds:
roi_has_mask[jj] = 1
# Create blobs for densepose supervision.
################################################## The mask
All_labels = blob_utils.zeros((fg_inds.shape[0], M**2), int32=True)
All_Weights = blob_utils.zeros((fg_inds.shape[0], M**2), int32=True)
################################################# The points
X_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
Y_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
Ind_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=True)
I_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=True)
U_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
V_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
Uv_point_weights = blob_utils.zeros((fg_inds.shape[0], 196),
int32=False)
#################################################
rois_fg = sampled_boxes[fg_inds]
overlaps_bbfg_bbpolys = box_utils.bbox_overlaps(
rois_fg.astype(np.float32, copy=False),
boxes_from_polys.astype(np.float32, copy=False))
fg_polys_inds = np.argmax(overlaps_bbfg_bbpolys, axis=1)
for i in range(rois_fg.shape[0]):
#
fg_polys_ind = polys_gt_inds[fg_polys_inds[i]]
#
Ilabel = segm_utils.GetDensePoseMask(
roidb['dp_masks'][fg_polys_ind])
#
GT_I = np.array(roidb['dp_I'][fg_polys_ind])
GT_U = np.array(roidb['dp_U'][fg_polys_ind])
GT_V = np.array(roidb['dp_V'][fg_polys_ind])
GT_x = np.array(roidb['dp_x'][fg_polys_ind])
GT_y = np.array(roidb['dp_y'][fg_polys_ind])
GT_weights = np.ones(GT_I.shape).astype(np.float32)
#
## Do the flipping of the densepose annotation !
if (IsFlipped):
GT_I, GT_U, GT_V, GT_x, GT_y, Ilabel = DP.get_symmetric_densepose(
GT_I, GT_U, GT_V, GT_x, GT_y, Ilabel)
#
roi_fg = rois_fg[i]
roi_gt = boxes_from_polys[fg_polys_inds[i], :]
#
x1 = roi_fg[0]
x2 = roi_fg[2]
y1 = roi_fg[1]
y2 = roi_fg[3]
#
x1_source = roi_gt[0]
x2_source = roi_gt[2]
y1_source = roi_gt[1]
y2_source = roi_gt[3]
#
x_targets = (np.arange(x1, x2, (x2 - x1) / M) -
x1_source) * (256. / (x2_source - x1_source))
y_targets = (np.arange(y1, y2, (y2 - y1) / M) -
y1_source) * (256. / (y2_source - y1_source))
#
x_targets = x_targets[
0:
M] ## Strangely sometimes it can be M+1, so make sure size is OK!
y_targets = y_targets[0:M]
#
[X_targets, Y_targets] = np.meshgrid(x_targets, y_targets)
New_Index = cv2.remap(Ilabel,
X_targets.astype(np.float32),
Y_targets.astype(np.float32),
interpolation=cv2.INTER_NEAREST,
borderMode=cv2.BORDER_CONSTANT,
borderValue=(0))
#
All_L = np.zeros(New_Index.shape)
All_W = np.ones(New_Index.shape)
#
All_L = New_Index
#
gt_length_x = x2_source - x1_source
gt_length_y = y2_source - y1_source
#
GT_y = ((GT_y / 256. * gt_length_y) + y1_source - y1) * (M /
(y2 - y1))
GT_x = ((GT_x / 256. * gt_length_x) + x1_source - x1) * (M /
(x2 - x1))
#
GT_I[GT_y < 0] = 0
GT_I[GT_y > (M - 1)] = 0
GT_I[GT_x < 0] = 0
GT_I[GT_x > (M - 1)] = 0
#
points_inside = GT_I > 0
GT_U = GT_U[points_inside]
GT_V = GT_V[points_inside]
GT_x = GT_x[points_inside]
GT_y = GT_y[points_inside]
GT_weights = GT_weights[points_inside]
GT_I = GT_I[points_inside]
#
X_points[i, 0:len(GT_x)] = GT_x
Y_points[i, 0:len(GT_y)] = GT_y
Ind_points[i, 0:len(GT_I)] = i
I_points[i, 0:len(GT_I)] = GT_I
U_points[i, 0:len(GT_U)] = GT_U
V_points[i, 0:len(GT_V)] = GT_V
Uv_point_weights[i, 0:len(GT_weights)] = GT_weights
#
All_labels[i, :] = np.reshape(All_L.astype(np.int32), M**2)
All_Weights[i, :] = np.reshape(All_W.astype(np.int32), M**2)
##
else:
bg_inds = np.where(blobs['labels_int32'] == 0)[0]
#
if (len(bg_inds) == 0):
rois_fg = sampled_boxes[0].reshape((1, -1))
else:
rois_fg = sampled_boxes[bg_inds[0]].reshape((1, -1))
roi_has_mask[0] = 1
#
X_points = blob_utils.zeros((1, 196), int32=False)
Y_points = blob_utils.zeros((1, 196), int32=False)
Ind_points = blob_utils.zeros((1, 196), int32=True)
I_points = blob_utils.zeros((1, 196), int32=True)
U_points = blob_utils.zeros((1, 196), int32=False)
V_points = blob_utils.zeros((1, 196), int32=False)
Uv_point_weights = blob_utils.zeros((1, 196), int32=False)
#
All_labels = -blob_utils.ones((1, M**2), int32=True) * 0 ## zeros
All_Weights = -blob_utils.ones((1, M**2), int32=True) * 0 ## zeros
#
rois_fg *= im_scale
repeated_batch_idx = batch_idx * blob_utils.ones((rois_fg.shape[0], 1))
rois_fg = np.hstack((repeated_batch_idx, rois_fg))
#
K = cfg.BODY_UV_RCNN.NUM_PATCHES
#
U_points = np.tile(U_points, [1, K + 1])
V_points = np.tile(V_points, [1, K + 1])
Uv_Weight_Points = np.zeros(U_points.shape)
#
for jjj in xrange(1, K + 1):
Uv_Weight_Points[:, jjj * I_points.shape[1]:(jjj + 1) *
I_points.shape[1]] = (I_points == jjj).astype(
np.float32)
#
################
# Update blobs dict with Mask R-CNN blobs
###############
#
blobs['body_uv_rois'] = np.array(rois_fg)
blobs['roi_has_body_uv_int32'] = np.array(roi_has_mask).astype(np.int32)
##
blobs['body_uv_ann_labels'] = np.array(All_labels).astype(np.int32)
blobs['body_uv_ann_weights'] = np.array(All_Weights).astype(np.float32)
#
##########################
blobs['body_uv_X_points'] = X_points.astype(np.float32)
blobs['body_uv_Y_points'] = Y_points.astype(np.float32)
blobs['body_uv_Ind_points'] = Ind_points.astype(np.float32)
blobs['body_uv_I_points'] = I_points.astype(np.float32)
blobs['body_uv_U_points'] = U_points.astype(
np.float32) #### VERY IMPORTANT : These are switched here :
blobs['body_uv_V_points'] = V_points.astype(np.float32)
blobs['body_uv_point_weights'] = Uv_Weight_Points.astype(np.float32)
def add_body_uv_rcnn_blobs(blobs, sampled_boxes, roidb, im_scale, batch_idx):
"""Add DensePose specific blobs to the given inputs blobs dictionary."""
M = cfg.BODY_UV_RCNN.HEATMAP_SIZE
# Prepare the body UV targets by associating one gt box which contains
# body UV annotations to each training roi that has a fg class label.
polys_gt_inds = np.where(roidb['ignore_UV_body'] == 0)[0]
boxes_from_polys = roidb['boxes'][polys_gt_inds]
# Select foreground RoIs
fg_inds = np.where(blobs['labels_int32'] > 0)[0]
roi_has_body_uv = np.zeros_like(blobs['labels_int32'], dtype=np.int32)
if ((boxes_from_polys.shape[0] > 0) & (fg_inds.shape[0] > 0)):
# Find overlap between all foreground RoIs and the gt bounding boxes
# containing each body UV annotaion.
rois_fg = sampled_boxes[fg_inds]
overlaps_bbfg_bbpolys = box_utils.bbox_overlaps(
rois_fg.astype(np.float32, copy=False),
boxes_from_polys.astype(np.float32, copy=False))
# Select foreground RoIs as those with > 0.7 overlap
fg_polys_value = np.max(overlaps_bbfg_bbpolys, axis=1)
fg_inds = fg_inds[fg_polys_value > 0.7]
if ((boxes_from_polys.shape[0] > 0) & (fg_inds.shape[0] > 0)):
roi_has_body_uv[fg_inds] = 1
# Create body UV blobs
# Dense masks, each mask for a given fg roi is of size M x M.
part_inds = blob_utils.zeros((fg_inds.shape[0], M, M), int32=True)
# Weights assigned to each target in `part_inds`. By default, all 1's.
# part_inds_weights = blob_utils.zeros((fg_inds.shape[0], M, M), int32=True)
part_inds_weights = blob_utils.ones((fg_inds.shape[0], M, M),
int32=False)
# 2D spatial coordinates (on the image). Shape is (#fg_rois, 2) in format
# (x, y).
coords_xy = blob_utils.zeros((fg_inds.shape[0], 196, 2), int32=False)
# 24 patch indices plus a background class
I_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=True)
# UV coordinates in each patch
U_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
V_points = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
# Uv_point_weights = blob_utils.zeros((fg_inds.shape[0], 196), int32=False)
rois_fg = sampled_boxes[fg_inds]
overlaps_bbfg_bbpolys = overlaps_bbfg_bbpolys[fg_inds]
# Map from each fg roi to the index of the gt box with highest overlap
fg_polys_inds = np.argmax(overlaps_bbfg_bbpolys, axis=1)
# Add body UV targets for each fg roi
for i in range(rois_fg.shape[0]):
fg_polys_ind = fg_polys_inds[i]
polys_gt_ind = polys_gt_inds[fg_polys_ind]
# RLE encoded dense masks which are of size 256 x 256.
# Map all part masks to 14 labels (i.e., indices of semantic body parts).
dp_masks = dp_utils.GetDensePoseMask(
roidb['dp_masks'][polys_gt_ind],
cfg.BODY_UV_RCNN.NUM_SEMANTIC_PARTS)
# Surface patch indices of collected points
dp_I = np.array(roidb['dp_I'][polys_gt_ind], dtype=np.int32)
# UV coordinates of collected points
dp_U = np.array(roidb['dp_U'][polys_gt_ind], dtype=np.float32)
dp_V = np.array(roidb['dp_V'][polys_gt_ind], dtype=np.float32)
# dp_UV_weights = np.ones_like(dp_I).astype(np.float32)
# Spatial coordinates on the image which are scaled such that the bbox
# size is 256 x 256.
dp_x = np.array(roidb['dp_x'][polys_gt_ind], dtype=np.float32)
dp_y = np.array(roidb['dp_y'][polys_gt_ind], dtype=np.float32)
# Do the flipping of the densepose annotation
if roidb['flipped']:
dp_I, dp_U, dp_V, dp_x, dp_y, dp_masks = DP.get_symmetric_densepose(
dp_I, dp_U, dp_V, dp_x, dp_y, dp_masks)
roi_fg = rois_fg[i]
gt_box = boxes_from_polys[fg_polys_ind]
fg_x1, fg_y1, fg_x2, fg_y2 = roi_fg[0:4]
gt_x1, gt_y1, gt_x2, gt_y2 = gt_box[0:4]
fg_width = fg_x2 - fg_x1
fg_height = fg_y2 - fg_y1
gt_width = gt_x2 - gt_x1
gt_height = gt_y2 - gt_y1
fg_scale_w = float(M) / fg_width
fg_scale_h = float(M) / fg_height
gt_scale_w = 256. / gt_width
gt_scale_h = 256. / gt_height
# Sample M points evenly within the fg roi and scale the relative coordinates
# (to associated gt box) such that the bounding box size is 256 x 256.
x_targets = (np.arange(fg_x1, fg_x2, fg_width / M) -
gt_x1) * gt_scale_w
y_targets = (np.arange(fg_y1, fg_y2, fg_height / M) -
gt_y1) * gt_scale_h
# Construct 2D coordiante matrices
x_targets, y_targets = np.meshgrid(x_targets[:M], y_targets[:M])
## Another implementation option (which results in similar performance)
# x_targets = (np.linspace(fg_x1, fg_x2, M, endpoint=True, dtype=np.float32) - gt_x1) * gt_scale_w
# y_targets = (np.linspace(fg_y1, fg_y2, M, endpoint=True, dtype=np.float32) - gt_y1) * gt_scale_h
# x_targets = (np.linspace(fg_x1, fg_x2, M, endpoint=False) - gt_x1) * gt_scale_w
# y_targets = (np.linspace(fg_y1, fg_y2, M, endpoint=False) - gt_y1) * gt_scale_h
# x_targets, y_targets = np.meshgrid(x_targets, y_targets)
# Map dense masks of size 256 x 256 to target heatmap of size M x M.
part_inds[i] = cv2.remap(dp_masks,
x_targets.astype(np.float32),
y_targets.astype(np.float32),
interpolation=cv2.INTER_NEAREST,
borderMode=cv2.BORDER_CONSTANT,
borderValue=(0))
# Scale annotated spatial coordinates from bbox of size 256 x 256 to target
# heatmap of size M x M.
dp_x = (dp_x / gt_scale_w + gt_x1 - fg_x1) * fg_scale_w
dp_y = (dp_y / gt_scale_h + gt_y1 - fg_y1) * fg_scale_h
# Set patch index of points outside the heatmap as 0 (background).
dp_I[dp_x < 0] = 0
dp_I[dp_x > (M - 1)] = 0
dp_I[dp_y < 0] = 0
dp_I[dp_y > (M - 1)] = 0
# Get body UV annotations of points inside the heatmap.
points_inside = dp_I > 0
dp_x = dp_x[points_inside]
dp_y = dp_y[points_inside]
dp_I = dp_I[points_inside]
dp_U = dp_U[points_inside]
dp_V = dp_V[points_inside]
# dp_UV_weights = dp_UV_weights[points_inside]
# Update body UV blobs
num_dp_points = len(dp_I)
# coords_xy[i, 0:num_dp_points, 0] = i # fg_roi index
coords_xy[i, 0:num_dp_points, 0] = dp_x
coords_xy[i, 0:num_dp_points, 1] = dp_y
I_points[i, 0:num_dp_points] = dp_I.astype(np.int32)
U_points[i, 0:num_dp_points] = dp_U
V_points[i, 0:num_dp_points] = dp_V
# Uv_point_weights[i, 0:len(dp_UV_weights)] = dp_UV_weights
else: # If there are no fg rois
# The network cannot handle empty blobs, so we must provide a blob.
# We simply take the first bg roi, give it an all 0's body UV annotations
# and label it with class zero (bg).
bg_inds = np.where(blobs['labels_int32'] == 0)[0]
# `rois_fg` is actually one background roi, but that's ok because ...
if len(bg_inds) == 0:
rois_fg = sampled_boxes[0].reshape((1, -1))
else:
rois_fg = sampled_boxes[bg_inds[0]].reshape((1, -1))
# Mark that the first roi has body UV annotation
roi_has_body_uv[0] = 1
# We give it all 0's blobs
part_inds = blob_utils.zeros((1, M, M), int32=True)
part_inds_weights = blob_utils.zeros((1, M, M), int32=False)
coords_xy = blob_utils.zeros((1, 196, 2), int32=False)
I_points = blob_utils.zeros((1, 196), int32=True)
U_points = blob_utils.zeros((1, 196), int32=False)
V_points = blob_utils.zeros((1, 196), int32=False)
# Uv_point_weights = blob_utils.zeros((1, 196), int32=False)
# Scale rois_fg and format as (batch_idx, x1, y1, x2, y2)
rois_fg *= im_scale
repeated_batch_idx = batch_idx * blob_utils.ones((rois_fg.shape[0], 1))
rois_fg = np.hstack((repeated_batch_idx, rois_fg))
# Create body UV blobs for all patches (including background)
K = cfg.BODY_UV_RCNN.NUM_PATCHES + 1
# Construct U/V_points blobs for all patches by repeating it #num_patches times.
# Shape: (#rois, 196, K)
U_points = np.repeat(U_points[:, :, np.newaxis], K, axis=-1)
V_points = np.repeat(V_points[:, :, np.newaxis], K, axis=-1)
uv_point_weights = np.zeros_like(U_points)
# Set binary weights for UV targets in each patch
for i in np.arange(1, K):
uv_point_weights[:, :, i] = (I_points == i).astype(np.float32)
# Update blobs dict with body UV blobs
blobs['body_uv_rois'] = rois_fg
blobs['roi_has_body_uv_int32'] = roi_has_body_uv # shape: (#rois,)
blobs['body_uv_parts'] = part_inds # shape: (#rois, M, M)
blobs['body_uv_parts_weights'] = part_inds_weights
blobs['body_uv_coords_xy'] = coords_xy.reshape(
-1, 2) # shape: (#rois * 196, 2)
blobs['body_uv_I_points'] = I_points.reshape(-1,
1) # shape: (#rois * 196, 1)
blobs['body_uv_U_points'] = U_points # shape: (#rois, 196, K)
blobs['body_uv_V_points'] = V_points
blobs['body_uv_point_weights'] = uv_point_weights
