def _loss_mask(self, proto_output, pred_mask_coef, gt_bbox_norm, gt_masks, positiveness,
max_id_for_anchors, max_masks_for_train):
shape_proto = tf.shape(proto_output)
num_batch = shape_proto[0]
loss_mask = 0.
total_pos = 0
for idx in tf.range(num_batch):
# extract randomly postive sample in pred_mask_coef, gt_cls, gt_offset according to positive_indices
proto = proto_output[idx]
mask_coef = pred_mask_coef[idx]
mask_gt = gt_masks[idx]
bbox_norm = gt_bbox_norm[idx]
pos = positiveness[idx]
max_id = max_id_for_anchors[idx]
pos_indices = tf.squeeze(tf.where(pos == 1))
# tf.print("num_pos", tf.shape(pos_indices))
"""
if tf.size(pos_indices) == 0:
tf.print("detect no positive")
continue
"""
# Todo decrease the number pf positive to be 100
# [num_pos, k]
pos_mask_coef = tf.gather(mask_coef, pos_indices)
pos_max_id = tf.gather(max_id, pos_indices)
if tf.size(pos_indices) == 1:
# tf.print("detect only one dim")
pos_mask_coef = tf.expand_dims(pos_mask_coef, axis=0)
pos_max_id = tf.expand_dims(pos_max_id, axis=0)
total_pos += tf.size(pos_indices)
# proto = [80, 80, num_mask]
# pos_mask_coef = [num_pos, num_mask]
# pred_mask = proto x pos_mask_coef = [80, 80, num_pos]
# pred_mask transpose = [num_pos, 80, 80]
pred_mask = tf.linalg.matmul(proto, pos_mask_coef, transpose_a=False, transpose_b=True)
pred_mask = tf.transpose(pred_mask, perm=(2, 0, 1))
# calculating loss for each mask coef correspond to each postitive anchor
# pos_max_id = [num_pos]
gt = tf.gather(mask_gt, pos_max_id) # [num_pos, 80, 80]
bbox = tf.gather(bbox_norm, pos_max_id) # [num_pos, 4]
bbox_center = utils.map_to_center_form(bbox) # [num_pos, 4]
area = bbox_center[:, -1] * bbox_center[:, -2]
# crop the pred (not real crop, zero out the area outside the gt box)
s = tf.nn.sigmoid_cross_entropy_with_logits(gt, pred_mask) # [num_pos, 80, 80]
s = utils.crop(s, bbox, origin_w=80, origin_h=80) # [num_pos, 80, 80]
loss = tf.reduce_sum(s, axis=[1, 2]) / area # [num_pos]
loss_mask += tf.reduce_sum(loss)
loss_mask /= tf.cast(total_pos, tf.float32)
return loss_mask
def _loss_mask(self, protonet_output, pred_mask_coef, gt_bbox_norm,
gt_masks, positiveness, max_id_for_anchors,
max_masks_for_train):
shape_proto = tf.shape(protonet_output)
batch_size = shape_proto[0]
loss_mask = 0.
total_pos = 0
for idx in tf.range(batch_size):
# extract randomly postive sample in pred_mask_coef, gt_cls, gt_offset according to positive_indices
proto = protonet_output[idx]
mask_coef = pred_mask_coef[idx]
mask_gt = gt_masks[idx]
bbox_norm = gt_bbox_norm[idx]
pos = positiveness[idx]
max_id = max_id_for_anchors[idx]
pos_indices = tf.squeeze(tf.where(pos == 1))
# tf.print("num_pos", tf.shape(pos_indices))
# TODO: Limit number of positive to be less than max_masks_for_train
pos_mask_coef = tf.gather(mask_coef, pos_indices)
pos_max_id = tf.gather(max_id, pos_indices)
if tf.size(pos_indices) == 1:
# tf.print("detect only one dim")
pos_mask_coef = tf.expand_dims(pos_mask_coef, axis=0)
pos_max_id = tf.expand_dims(pos_max_id, axis=0)
total_pos += tf.size(pos_indices)
pred_mask = tf.linalg.matmul(proto,
pos_mask_coef,
transpose_a=False,
transpose_b=True)
pred_mask = tf.transpose(pred_mask, perm=(2, 0, 1))
# calculating loss for each mask coef correspond to each postitive anchor
gt = tf.gather(mask_gt, pos_max_id)
bbox = tf.gather(bbox_norm, pos_max_id)
bbox_center = utils.map_to_center_form(bbox)
area = bbox_center[:, -1] * bbox_center[:, -2]
# crop the pred (not real crop, zero out the area outside the gt box)
s = tf.nn.sigmoid_cross_entropy_with_logits(gt, pred_mask)
s = utils.crop(s, bbox)
loss = tf.reduce_sum(s, axis=[1, 2]) / area
loss_mask += tf.reduce_sum(loss)
loss_mask /= tf.cast(total_pos, tf.float32)
return loss_mask
def _loss_mask(self, proto_output, pred_mask_coef, gt_bbox_norm, gt_masks,
positiveness, max_id_for_anchors, max_masks_for_train):
shape_proto = tf.shape(proto_output)
num_batch = shape_proto[0]
proto_h = shape_proto[1]
proto_w = shape_proto[2]
loss_mask = 0.
total_pos = 0
for idx in tf.range(num_batch):
# extract randomly postive sample in prejd_mask_coef, gt_cls, gt_offset according to positive_indices
proto = proto_output[idx]
mask_coef = pred_mask_coef[idx]
mask_gt = gt_masks[idx]
bbox_norm = gt_bbox_norm[idx] # [100, 4] -> [num_obj, 4]
pos = positiveness[idx]
max_id = max_id_for_anchors[idx]
pos_indices = tf.squeeze(tf.where(pos == 1))
# If exceeds the number of masks for training, select a random subset
old_num_pos = tf.size(pos_indices)
# print("pos indices", pos_indices.shape)
if old_num_pos > max_masks_for_train:
perm = tf.random.shuffle(pos_indices)
pos_indices = perm[:max_masks_for_train]
pos_mask_coef = tf.gather(mask_coef, pos_indices)
pos_max_id = tf.gather(max_id, pos_indices)
# if only 1 positive or no positive
if tf.size(pos_indices) == 1:
pos_mask_coef = tf.expand_dims(pos_mask_coef, axis=0)
pos_max_id = tf.expand_dims(pos_max_id, axis=0)
elif tf.size(pos_indices) == 0:
continue
else:
...
# [num_pos, k]
gt = tf.gather(mask_gt, pos_max_id)
bbox = tf.gather(bbox_norm, pos_max_id)
# print(bbox[:5])
num_pos = tf.size(pos_indices)
# print('gt_me', gt.shape)
total_pos += num_pos
# [138, 138, num_pos]
pred_mask = tf.linalg.matmul(proto,
pos_mask_coef,
transpose_a=False,
transpose_b=True)
pred_mask = tf.transpose(pred_mask, perm=(2, 0, 1))
s = tf.nn.sigmoid_cross_entropy_with_logits(gt, pred_mask)
s = utils.crop(s, bbox)
# calculating loss for each mask coef correspond to each postitive anchor
bbox_center = utils.map_to_center_form(tf.cast(bbox, tf.float32))
area = bbox_center[:, -1] * bbox_center[:, -2]
mask_loss = tf.reduce_sum(s, axis=[1, 2]) / area
if old_num_pos > num_pos:
mask_loss = mask_loss * tf.cast(
(old_num_pos / num_pos), mask_loss.dtype)
loss_mask += tf.reduce_sum(mask_loss)
return loss_mask / tf.cast(total_pos, loss_mask.dtype)