在训练过程中，groundtruth 的坐标形式是（y1,x1,y2,x2），而网络输出的坐标形式是（dx,dy,dw,dh），
两者之间的表示形式不同，因此要将 groundtruth 和 anchors 结合，来表示anchor_layers 上每个位置的分类 label 和坐标偏移 loc（即网络的输出），即 encode 过程。
在预测过程中，网络输出的坐标形式是（dx,dy,dw,dh），而真实值的坐标形式是（y1,x1,y2,x2），同样要把网络输出和 anchors 结合，decode成真实值的形式。
一、encode 过程
已知 anchors（坐标形式：x,y,w,h）
已知 gt_labels , gt_bboxes（坐标形式：y1,x1,y2,x2）
目标是将 groundtruth 和 anchors 结合起来，得到每个位置的偏移量，这样才能和网络的输出做 loss。
（注意：anchors 的位置始终不变，因此 groundtruth 和 anchors 的差值就是偏移量了）
1.得到每个anchor的（左上，右下）坐标
因为 groundtruth_bboxes 的坐标表示为（y1,x1,y2,x2），所以这一步将 anchor 的坐标也转换成这种形式。
yref, xref, href, wref = anchors_layer
ymin = yref - href / 2.
xmin = xref - wref / 2.
ymax = yref + href / 2.
xmax = xref + wref / 2.
2.得到每个anchor的分类和偏移
计算 groundtruth_bboxes 与 每个anchors 的 IOU，作为 scores。每个 anchor 取与其IOU最大的groundtruth_bbox作为基准来计算偏移。
vol_anchors = (xmax - xmin) * (ymax - ymin) # 计算每个anchor的面积
# shape = （feat_size,feat_size,num_anchors）
shape = (yref.shape[0], yref.shape[1], href.size)
#全部初始化为0
feat_labels = tf.zeros(shape, dtype=tf.int64)
feat_scores = tf.zeros(shape, dtype=dtype)
feat_ymin = tf.zeros(shape, dtype=dtype)
feat_xmin = tf.zeros(shape, dtype=dtype)
feat_ymax = tf.ones(shape, dtype=dtype)
feat_xmax = tf.ones(shape, dtype=dtype)
# 计算所有 anchors 和某一个 groundtruth_bbox 的IOU
def jaccard_with_anchors(bbox):
"""Compute jaccard score between a box and the anchors.
"""
int_ymin = tf.maximum(ymin, bbox[0])
int_xmin = tf.maximum(xmin, bbox[1])
int_ymax = tf.minimum(ymax, bbox[2])
int_xmax = tf.minimum(xmax, bbox[3])
h = tf.maximum(int_ymax - int_ymin, 0.)
w = tf.maximum(int_xmax - int_xmin, 0.)
# Volumes.
inter_vol = h * w
union_vol = vol_anchors - inter_vol \
+ (bbox[2] - bbox[0]) * (bbox[3] - bbox[1])
jaccard = tf.div(inter_vol, union_vol)
return jaccard
def intersection_with_anchors(bbox):
"""Compute intersection between score a box and the anchors.
"""
int_ymin = tf.maximum(ymin, bbox[0])
int_xmin = tf.maximum(xmin, bbox[1])
int_ymax = tf.minimum(ymax, bbox[2])
int_xmax = tf.minimum(xmax, bbox[3])
h = tf.maximum(int_ymax - int_ymin, 0.)
w = tf.maximum(int_xmax - int_xmin, 0.)
inter_vol = h * w
scores = tf.div(inter_vol, vol_anchors)
return scores
def condition(i, feat_labels, feat_scores,
feat_ymin, feat_xmin, feat_ymax, feat_xmax):
"""Condition: check label index.
"""
r = tf.less(i, tf.shape(labels))
return r[0]
def body(i, feat_labels, feat_scores,
feat_ymin, feat_xmin, feat_ymax, feat_xmax):
"""Body: update feature labels, scores and bboxes.
Follow the original SSD paper for that purpose:
- assign values when jaccard > 0.5;
- only update if beat the score of other bboxes.
"""
# Jaccard score.
label = labels[i]
bbox = bboxes[i]
jaccard = jaccard_with_anchors(bbox)
# Mask: check threshold + scores + no annotations + num_classes.
mask = tf.greater(jaccard, feat_scores)
# mask = tf.logical_and(mask, tf.greater(jaccard, ignore_threshold))
mask = tf.logical_and(mask, feat_scores > -0.5)
mask = tf.logical_and(mask, label < num_classes)
imask = tf.cast(mask, tf.int64)
fmask = tf.cast(mask, dtype)
# Update values using mask.
feat_labels = imask * label + (1 - imask) * feat_labels
feat_scores = tf.where(mask, jaccard, feat_scores)
feat_ymin = fmask * bbox[0] + (1 - fmask) * feat_ymin
feat_xmin = fmask * bbox[1] + (1 - fmask) * feat_xmin
feat_ymax = fmask * bbox[2] + (1 - fmask) * feat_ymax
feat_xmax = fmask * bbox[3] + (1 - fmask) * feat_xmax
# Check no annotation label: ignore these anchors...
# interscts = intersection_with_anchors(bbox)
# mask = tf.logical_and(interscts > ignore_threshold,
# label == no_annotation_label)
# # Replace scores by -1.
# feat_scores = tf.where(mask, -tf.cast(mask, dtype), feat_scores)
return [i+1, feat_labels, feat_scores,
feat_ymin, feat_xmin, feat_ymax, feat_xmax]
# Main loop definition.
i = 0
[i, feat_labels, feat_scores,
feat_ymin, feat_xmin,
feat_ymax, feat_xmax] = tf.while_loop(condition, body,
[i, feat_labels, feat_scores,
feat_ymin, feat_xmin,
feat_ymax, feat_xmax])
3.将坐标形式转换成偏移量的形式
与网络的输出 pred_locs 计算损失，坐标形式为（dx,dy,dw,dh）。
# Transform to center / size.
feat_cy = (feat_ymax + feat_ymin) / 2.
feat_cx = (feat_xmax + feat_xmin) / 2.
feat_h = feat_ymax - feat_ymin
feat_w = feat_xmax - feat_xmin
# Encode features.
feat_cy = (feat_cy - yref) / href / prior_scaling[0]
feat_cx = (feat_cx - xref) / wref / prior_scaling[1]
feat_h = tf.log(feat_h / href) / prior_scaling[2]
feat_w = tf.log(feat_w / wref) / prior_scaling[3]
# Use SSD ordering: x / y / w / h instead of ours.
feat_localizations = tf.stack([feat_cx, feat_cy, feat_w, feat_h], axis=-1)
encode 过程完整代码
def tf_ssd_bboxes_encode_layer(labels,
bboxes,
anchors_layer,
num_classes,
no_annotation_label,
ignore_threshold=0.5,
prior_scaling=[0.1, 0.1, 0.2, 0.2],
dtype=tf.float32):
"""Encode groundtruth labels and bounding boxes using SSD anchors from
one layer.
Arguments:
labels: 1D Tensor(int64) containing groundtruth labels;
bboxes: Nx4 Tensor(float) with bboxes relative coordinates;
anchors_layer: Numpy arrwiay th layer anchors;
matching_threshold: Threshold for positive match with groundtruth bboxes;
prior_scaling: Scaling of encoded coordinates.
Return:
(target_labels, target_localizations, target_scores): Target Tensors.
"""
# Anchors coordinates and volume.
yref, xref, href, wref = anchors_layer
ymin = yref - href / 2.
xmin = xref - wref / 2.
ymax = yref + href / 2.
xmax = xref + wref / 2.
vol_anchors = (xmax - xmin) * (ymax - ymin)
# Initialize tensors...
shape = (yref.shape[0], yref.shape[1], href.size)
feat_labels = tf.zeros(shape, dtype=tf.int64)
feat_scores = tf.zeros(shape, dtype=dtype)
feat_ymin = tf.zeros(shape, dtype=dtype)
feat_xmin = tf.zeros(shape, dtype=dtype)
feat_ymax = tf.ones(shape, dtype=dtype)
feat_xmax = tf.ones(shape, dtype=dtype)
def jaccard_with_anchors(bbox):
"""Compute jaccard score between a box and the anchors.
"""
int_ymin = tf.maximum(ymin, bbox[0])
int_xmin = tf.maximum(xmin, bbox[1])
int_ymax = tf.minimum(ymax, bbox[2])
int_xmax = tf.minimum(xmax, bbox[3])
h = tf.maximum(int_ymax - int_ymin, 0.)
w = tf.maximum(int_xmax - int_xmin, 0.)
# Volumes.
inter_vol = h * w
union_vol = vol_anchors - inter_vol \
+ (bbox[2] - bbox[0]) * (bbox[3] - bbox[1])
jaccard = tf.div(inter_vol, union_vol)
return jaccard
def intersection_with_anchors(bbox):
"""Compute intersection between score a box and the anchors.
"""
int_ymin = tf.maximum(ymin, bbox[0])
int_xmin = tf.maximum(xmin, bbox[1])
int_ymax = tf.minimum(ymax, bbox[2])
int_xmax = tf.minimum(xmax, bbox[3])
h = tf.maximum(int_ymax - int_ymin, 0.)
w = tf.maximum(int_xmax - int_xmin, 0.)
inter_vol = h * w
scores = tf.div(inter_vol, vol_anchors)
return scores
def condition(i, feat_labels, feat_scores,
feat_ymin, feat_xmin, feat_ymax, feat_xmax):
"""Condition: check label index.
"""
r = tf.less(i, tf.shape(labels))
return r[0]
def body(i, feat_labels, feat_scores,
feat_ymin, feat_xmin, feat_ymax, feat_xmax):
"""Body: update feature labels, scores and bboxes.
Follow the original SSD paper for that purpose:
- assign values when jaccard > 0.5;
- only update if beat the score of other bboxes.
"""
# Jaccard score.
label = labels[i]
bbox = bboxes[i]
jaccard = jaccard_with_anchors(bbox)
# Mask: check threshold + scores + no annotations + num_classes.
mask = tf.greater(jaccard, feat_scores)
# mask = tf.logical_and(mask, tf.greater(jaccard, ignore_threshold))
mask = tf.logical_and(mask, feat_scores > -0.5)
mask = tf.logical_and(mask, label < num_classes)
imask = tf.cast(mask, tf.int64)
fmask = tf.cast(mask, dtype)
# Update values using mask.
feat_labels = imask * label + (1 - imask) * feat_labels
feat_scores = tf.where(mask, jaccard, feat_scores)
feat_ymin = fmask * bbox[0] + (1 - fmask) * feat_ymin
feat_xmin = fmask * bbox[1] + (1 - fmask) * feat_xmin
feat_ymax = fmask * bbox[2] + (1 - fmask) * feat_ymax
feat_xmax = fmask * bbox[3] + (1 - fmask) * feat_xmax
# Check no annotation label: ignore these anchors...
# interscts = intersection_with_anchors(bbox)
# mask = tf.logical_and(interscts > ignore_threshold,
# label == no_annotation_label)
# # Replace scores by -1.
# feat_scores = tf.where(mask, -tf.cast(mask, dtype), feat_scores)
return [i+1, feat_labels, feat_scores,
feat_ymin, feat_xmin, feat_ymax, feat_xmax]
# Main loop definition.
i = 0
[i, feat_labels, feat_scores,
feat_ymin, feat_xmin,
feat_ymax, feat_xmax] = tf.while_loop(condition, body,
[i, feat_labels, feat_scores,
feat_ymin, feat_xmin,
feat_ymax, feat_xmax])
# Transform to center / size.
feat_cy = (feat_ymax + feat_ymin) / 2.
feat_cx = (feat_xmax + feat_xmin) / 2.
feat_h = feat_ymax - feat_ymin
feat_w = feat_xmax - feat_xmin
# Encode features.
feat_cy = (feat_cy - yref) / href / prior_scaling[0]
feat_cx = (feat_cx - xref) / wref / prior_scaling[1]
feat_h = tf.log(feat_h / href) / prior_scaling[2]
feat_w = tf.log(feat_w / wref) / prior_scaling[3]
# Use SSD ordering: x / y / w / h instead of ours.
feat_localizations = tf.stack([feat_cx, feat_cy, feat_w, feat_h], axis=-1)
return feat_labels, feat_localizations, feat_scores
一、decode 过程
已知 anchors （坐标形式：x,y,w,h）
已知 网络输出 pred_locs （坐标形式：dx,dy,dw,dh）
目标是将 网络输出 pred_locs 和 anchors 结合起来，得到真实值。
（同样注意：anchors 的位置始终不变，因此网络输出 pred_locs 和 anchors 的结合就是真实值了）
1.得到每个anchor的坐标
yref, xref, href, wref = anchor_bboxes
2.计算每个anchor的中心点和宽高
# Compute center, height and width
cx = feat_localizations[:, :, 0] * wref * prior_scaling[0] + xref
cy = feat_localizations[:, :, 1] * href * prior_scaling[1] + yref
w = wref * np.exp(feat_localizations[:, :, 2] * prior_scaling[2])
h = href * np.exp(feat_localizations[:, :, 3] * prior_scaling[3])
3.转换成真实值的坐标形式
# bboxes: ymin, xmin, xmax, ymax.
bboxes = np.zeros_like(feat_localizations)
bboxes[:, :, 0] = cy - h / 2.
bboxes[:, :, 1] = cx - w / 2.
bboxes[:, :, 2] = cy + h / 2.
bboxes[:, :, 3] = cx + w / 2.
decode 过程完整代码
def ssd_bboxes_decode(feat_localizations,
anchor_bboxes,
prior_scaling=[0.1, 0.1, 0.2, 0.2]):
"""Compute the relative bounding boxes from the layer features and
reference anchor bounding boxes.
Return:
numpy array Nx4: ymin, xmin, ymax, xmax
"""
# Reshape for easier broadcasting.
l_shape = feat_localizations.shape
feat_localizations = np.reshape(feat_localizations,
(-1, l_shape[-2], l_shape[-1]))
yref, xref, href, wref = anchor_bboxes
xref = np.reshape(xref, [-1, 1])
yref = np.reshape(yref, [-1, 1])
# Compute center, height and width
cx = feat_localizations[:, :, 0] * wref * prior_scaling[0] + xref
cy = feat_localizations[:, :, 1] * href * prior_scaling[1] + yref
w = wref * np.exp(feat_localizations[:, :, 2] * prior_scaling[2])
h = href * np.exp(feat_localizations[:, :, 3] * prior_scaling[3])
# bboxes: ymin, xmin, xmax, ymax.
bboxes = np.zeros_like(feat_localizations)
bboxes[:, :, 0] = cy - h / 2.
bboxes[:, :, 1] = cx - w / 2.
bboxes[:, :, 2] = cy + h / 2.
bboxes[:, :, 3] = cx + w / 2.
# Back to original shape.
bboxes = np.reshape(bboxes, l_shape)
return bboxes
