sipp11
/
SSD_Tensorflow-1.x
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
1 Commit
1 Branch
0 Tags
3.5 MiB
Branch: master
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'master'
${ noResults }
SSD_Tensorflow-1.x/nets/ssd_common.py

411 lines
17 KiB
Raw Permalink Normal View History Unescape

Initial commit Originally from https://github.com/balancap/SSD-Tensorflow
5 years ago
# Copyright 2015 Paul Balanca. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Shared function between different SSD implementations.
"""
import numpy as np
import tensorflow as tf
import tf_extended as tfe
# =========================================================================== #
# TensorFlow implementation of boxes SSD encoding / decoding.
# =========================================================================== #
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 array with 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, matching_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
def tf_ssd_bboxes_encode(labels,
bboxes,
anchors,
num_classes,
no_annotation_label,
ignore_threshold=0.5,
prior_scaling=[0.1, 0.1, 0.2, 0.2],
dtype=tf.float32,
scope='ssd_bboxes_encode'):
"""Encode groundtruth labels and bounding boxes using SSD net anchors.
Encoding boxes for all feature layers.
Arguments:
labels: 1D Tensor(int64) containing groundtruth labels;
bboxes: Nx4 Tensor(float) with bboxes relative coordinates;
anchors: List of Numpy array with layer anchors;
matching_threshold: Threshold for positive match with groundtruth bboxes;
prior_scaling: Scaling of encoded coordinates.
Return:
(target_labels, target_localizations, target_scores):
Each element is a list of target Tensors.
"""
with tf.name_scope(scope):
target_labels = []
target_localizations = []
target_scores = []
for i, anchors_layer in enumerate(anchors):
with tf.name_scope('bboxes_encode_block_%i' % i):
t_labels, t_loc, t_scores = \
tf_ssd_bboxes_encode_layer(labels, bboxes, anchors_layer,
num_classes, no_annotation_label,
ignore_threshold,
prior_scaling, dtype)
target_labels.append(t_labels)
target_localizations.append(t_loc)
target_scores.append(t_scores)
return target_labels, target_localizations, target_scores
def tf_ssd_bboxes_decode_layer(feat_localizations,
anchors_layer,
prior_scaling=[0.1, 0.1, 0.2, 0.2]):
"""Compute the relative bounding boxes from the layer features and
reference anchor bounding boxes.
Arguments:
feat_localizations: Tensor containing localization features.
anchors: List of numpy array containing anchor boxes.
Return:
Tensor Nx4: ymin, xmin, ymax, xmax
"""
yref, xref, href, wref = anchors_layer
# 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 * tf.exp(feat_localizations[:, :, :, :, 2] * prior_scaling[2])
h = href * tf.exp(feat_localizations[:, :, :, :, 3] * prior_scaling[3])
# Boxes coordinates.
ymin = cy - h / 2.
xmin = cx - w / 2.
ymax = cy + h / 2.
xmax = cx + w / 2.
bboxes = tf.stack([ymin, xmin, ymax, xmax], axis=-1)
return bboxes
def tf_ssd_bboxes_decode(feat_localizations,
anchors,
prior_scaling=[0.1, 0.1, 0.2, 0.2],
scope='ssd_bboxes_decode'):
"""Compute the relative bounding boxes from the SSD net features and
reference anchors bounding boxes.
Arguments:
feat_localizations: List of Tensors containing localization features.
anchors: List of numpy array containing anchor boxes.
Return:
List of Tensors Nx4: ymin, xmin, ymax, xmax
"""
with tf.name_scope(scope):
bboxes = []
for i, anchors_layer in enumerate(anchors):
bboxes.append(
tf_ssd_bboxes_decode_layer(feat_localizations[i],
anchors_layer,
prior_scaling))
return bboxes
# =========================================================================== #
# SSD boxes selection.
# =========================================================================== #
def tf_ssd_bboxes_select_layer(predictions_layer, localizations_layer,
select_threshold=None,
num_classes=21,
ignore_class=0,
scope=None):
"""Extract classes, scores and bounding boxes from features in one layer.
Batch-compatible: inputs are supposed to have batch-type shapes.
Args:
predictions_layer: A SSD prediction layer;
localizations_layer: A SSD localization layer;
select_threshold: Classification threshold for selecting a box. All boxes
under the threshold are set to 'zero'. If None, no threshold applied.
Return:
d_scores, d_bboxes: Dictionary of scores and bboxes Tensors of
size Batches X N x 1 | 4. Each key corresponding to a class.
"""
select_threshold = 0.0 if select_threshold is None else select_threshold
with tf.name_scope(scope, 'ssd_bboxes_select_layer',
[predictions_layer, localizations_layer]):
# Reshape features: Batches x N x N_labels | 4
p_shape = tfe.get_shape(predictions_layer)
predictions_layer = tf.reshape(predictions_layer,
tf.stack([p_shape[0], -1, p_shape[-1]]))
l_shape = tfe.get_shape(localizations_layer)
localizations_layer = tf.reshape(localizations_layer,
tf.stack([l_shape[0], -1, l_shape[-1]]))
d_scores = {}
d_bboxes = {}
for c in range(0, num_classes):
if c != ignore_class:
# Remove boxes under the threshold.
scores = predictions_layer[:, :, c]
fmask = tf.cast(tf.greater_equal(scores, select_threshold), scores.dtype)
scores = scores * fmask
bboxes = localizations_layer * tf.expand_dims(fmask, axis=-1)
# Append to dictionary.
d_scores[c] = scores
d_bboxes[c] = bboxes
return d_scores, d_bboxes
def tf_ssd_bboxes_select(predictions_net, localizations_net,
select_threshold=None,
num_classes=21,
ignore_class=0,
scope=None):
"""Extract classes, scores and bounding boxes from network output layers.
Batch-compatible: inputs are supposed to have batch-type shapes.
Args:
predictions_net: List of SSD prediction layers;
localizations_net: List of localization layers;
select_threshold: Classification threshold for selecting a box. All boxes
under the threshold are set to 'zero'. If None, no threshold applied.
Return:
d_scores, d_bboxes: Dictionary of scores and bboxes Tensors of
size Batches X N x 1 | 4. Each key corresponding to a class.
"""
with tf.name_scope(scope, 'ssd_bboxes_select',
[predictions_net, localizations_net]):
l_scores = []
l_bboxes = []
for i in range(len(predictions_net)):
scores, bboxes = tf_ssd_bboxes_select_layer(predictions_net[i],
localizations_net[i],
select_threshold,
num_classes,
ignore_class)
l_scores.append(scores)
l_bboxes.append(bboxes)
# Concat results.
d_scores = {}
d_bboxes = {}
for c in l_scores[0].keys():
ls = [s[c] for s in l_scores]
lb = [b[c] for b in l_bboxes]
d_scores[c] = tf.concat(ls, axis=1)
d_bboxes[c] = tf.concat(lb, axis=1)
return d_scores, d_bboxes
def tf_ssd_bboxes_select_layer_all_classes(predictions_layer, localizations_layer,
select_threshold=None):
"""Extract classes, scores and bounding boxes from features in one layer.
Batch-compatible: inputs are supposed to have batch-type shapes.
Args:
predictions_layer: A SSD prediction layer;
localizations_layer: A SSD localization layer;
select_threshold: Classification threshold for selecting a box. If None,
select boxes whose classification score is higher than 'no class'.
Return:
classes, scores, bboxes: Input Tensors.
"""
# Reshape features: Batches x N x N_labels | 4
p_shape = tfe.get_shape(predictions_layer)
predictions_layer = tf.reshape(predictions_layer,
tf.stack([p_shape[0], -1, p_shape[-1]]))
l_shape = tfe.get_shape(localizations_layer)
localizations_layer = tf.reshape(localizations_layer,
tf.stack([l_shape[0], -1, l_shape[-1]]))
# Boxes selection: use threshold or score > no-label criteria.
if select_threshold is None or select_threshold == 0:
# Class prediction and scores: assign 0. to 0-class
classes = tf.argmax(predictions_layer, axis=2)
scores = tf.reduce_max(predictions_layer, axis=2)
scores = scores * tf.cast(classes > 0, scores.dtype)
else:
sub_predictions = predictions_layer[:, :, 1:]
classes = tf.argmax(sub_predictions, axis=2) + 1
scores = tf.reduce_max(sub_predictions, axis=2)
# Only keep predictions higher than threshold.
mask = tf.greater(scores, select_threshold)
classes = classes * tf.cast(mask, classes.dtype)
scores = scores * tf.cast(mask, scores.dtype)
# Assume localization layer already decoded.
bboxes = localizations_layer
return classes, scores, bboxes
def tf_ssd_bboxes_select_all_classes(predictions_net, localizations_net,
select_threshold=None,
scope=None):
"""Extract classes, scores and bounding boxes from network output layers.
Batch-compatible: inputs are supposed to have batch-type shapes.
Args:
predictions_net: List of SSD prediction layers;
localizations_net: List of localization layers;
select_threshold: Classification threshold for selecting a box. If None,
select boxes whose classification score is higher than 'no class'.
Return:
classes, scores, bboxes: Tensors.
"""
with tf.name_scope(scope, 'ssd_bboxes_select',
[predictions_net, localizations_net]):
l_classes = []
l_scores = []
l_bboxes = []
for i in range(len(predictions_net)):
classes, scores, bboxes = \
tf_ssd_bboxes_select_layer_all_classes(predictions_net[i],
localizations_net[i],
select_threshold)
l_classes.append(classes)
l_scores.append(scores)
l_bboxes.append(bboxes)
classes = tf.concat(l_classes, axis=1)
scores = tf.concat(l_scores, axis=1)
bboxes = tf.concat(l_bboxes, axis=1)
return classes, scores, bboxes