def _conv_layers(self,x):
conv_layers = Layers(x)
# Convolutional layers
res_blocks = [1,3,4,23,3]
output_channels = [64,256,512,1024,2048]
with tf.variable_scope('scale0'):
conv_layers.conv2d(filter_size=7,output_channels=output_channels[0],stride=2,padding='SAME',b_value=None)
conv_layers.maxpool(k=3)
with tf.variable_scope('scale1'):
conv_layers.res_layer(filter_size=3, output_channels=output_channels[1], stride=2)
for block in range(res_blocks[1]-1):
conv_layers.conv_layers.res_layer(filter_size=3, output_channels=output_channels[1], stride=1)
with tf.variable_scope('scale2'):
conv_layers.res_layer(filter_size=3, output_channels=output_channels[2], stride=2)
for block in range(res_blocks[2]-1):
conv_layers.conv_layers.res_layer(filter_size=3, output_channels=output_channels[2], stride=1)
with tf.variable_scope('scale3'):
conv_layers.res_layer(filter_size=3, output_channels=output_channels[3], stride=2)
for block in range(res_blocks[3]-1):
conv_layers.conv_layers.res_layer(filter_size=3, output_channels=output_channels[3], stride=1)
with tf.variable_scope('scale4'):
conv_layers.res_layer(filter_size=3, output_channels=output_channels[4], stride=2)
for block in range(res_blocks[4]-1):
conv_layers.conv_layers.res_layer(filter_size=3, output_channels=output_channels[4], stride=1)
conv_layers.avgpool(globe=True)
# Fully Connected Layer
conv_layers.fc(output_nodes=10)
return conv_layers.get_output()
def _conv_layers(self, x):
conv_layers = Layers(x)
# Convolutional layers
res_blocks = [1, 3, 4, 23, 3]
output_channels = [64, 256, 512, 1024, 2048]
with tf.variable_scope('scale0'):
conv_layers.conv2d(filter_size=7,
output_channels=output_channels[0],
stride=2,
padding='SAME',
b_value=None)
conv_layers.maxpool(k=3)
with tf.variable_scope('scale1'):
conv_layers.res_layer(filter_size=3,
output_channels=output_channels[1],
stride=2)
for block in range(res_blocks[1] - 1):
conv_layers.conv_layers.res_layer(
filter_size=3,
output_channels=output_channels[1],
stride=1)
with tf.variable_scope('scale2'):
conv_layers.res_layer(filter_size=3,
output_channels=output_channels[2],
stride=2)
for block in range(res_blocks[2] - 1):
conv_layers.conv_layers.res_layer(
filter_size=3,
output_channels=output_channels[2],
stride=1)
with tf.variable_scope('scale3'):
conv_layers.res_layer(filter_size=3,
output_channels=output_channels[3],
stride=2)
for block in range(res_blocks[3] - 1):
conv_layers.conv_layers.res_layer(
filter_size=3,
output_channels=output_channels[3],
stride=1)
with tf.variable_scope('scale4'):
conv_layers.res_layer(filter_size=3,
output_channels=output_channels[4],
stride=2)
for block in range(res_blocks[4] - 1):
conv_layers.conv_layers.res_layer(
filter_size=3,
output_channels=output_channels[4],
stride=1)
conv_layers.avgpool(globe=True)
# Fully Connected Layer
conv_layers.fc(output_nodes=10)
return conv_layers.get_output()
class fast_rcnn:
'''
Crop and resize areas from the feature-extracting CNN's feature maps
according to the ROIs generated from the ROI proposal layer
'''
def __init__(self, featureMaps, roi_proposal_net, eval_mode):
self.featureMaps = featureMaps
self.roi_proposal_net = roi_proposal_net
self.rois = roi_proposal_net.get_rois()
self.im_dims = roi_proposal_net.im_dims
self.num_classes = cfg.NUM_CLASSES
self.eval_mode = eval_mode
self._network()
def _network(self):
with tf.variable_scope('fast_rcnn'):
# No dropout in evaluation mode
keep_prob = cfg.FRCNN_DROPOUT_KEEP_RATE if self.eval_mode is False else 1.0
# ROI pooling
pooledFeatures = roi_pool(self.featureMaps, self.rois,
self.im_dims)
# Fully Connect layers (with dropout)
with tf.variable_scope('fc'):
self.rcnn_fc_layers = Layers(pooledFeatures)
self.rcnn_fc_layers.flatten()
for i in range(len(cfg.FRCNN_FC_HIDDEN)):
self.rcnn_fc_layers.fc(output_nodes=cfg.FRCNN_FC_HIDDEN[i],
keep_prob=keep_prob)
hidden = self.rcnn_fc_layers.get_output()
# Classifier score
with tf.variable_scope('cls'):
self.rcnn_cls_layers = Layers(hidden)
self.rcnn_cls_layers.fc(output_nodes=self.num_classes,
activation_fn=None)
# Bounding Box refinement
with tf.variable_scope('bbox'):
self.rcnn_bbox_layers = Layers(hidden)
self.rcnn_bbox_layers.fc(output_nodes=self.num_classes * 4,
activation_fn=None)
# Get functions
def get_cls_score(self):
return self.rcnn_cls_layers.get_output()
def get_cls_prob(self):
logits = self.get_cls_score()
return tf.nn.softmax(logits)
def get_bbox_refinement(self):
return self.rcnn_bbox_layers.get_output()
# Loss functions
def get_fast_rcnn_cls_loss(self):
assert self.eval_mode is False, 'No Fast RCNN cls loss without ground truth boxes'
fast_rcnn_cls_score = self.get_cls_score()
labels = self.roi_proposal_net.get_labels()
return fast_rcnn_cls_loss(fast_rcnn_cls_score, labels)
def get_fast_rcnn_bbox_loss(self):
assert self.eval_mode is False, 'No Fast RCNN bbox loss without ground truth boxes'
fast_rcnn_bbox_pred = self.get_bbox_refinement()
bbox_targets = self.roi_proposal_net.get_bbox_targets()
roi_inside_weights = self.roi_proposal_net.get_bbox_inside_weights()
roi_outside_weights = self.roi_proposal_net.get_bbox_outside_weights()
return fast_rcnn_bbox_loss(fast_rcnn_bbox_pred, bbox_targets,
roi_inside_weights, roi_outside_weights)
class fast_rcnn:
'''
Crop and resize areas from the feature-extracting CNN's feature maps
according to the ROIs generated from the ROI proposal layer
'''
def __init__(self,featureMaps, roi_proposal_net):
self.featureMaps = featureMaps
self.roi_proposal_net = roi_proposal_net
self.rois = roi_proposal_net.get_rois()
self.im_dims = roi_proposal_net.im_dims
self.flags = roi_proposal_net.flags
self._network()
def _network(self):
with tf.variable_scope('fast_rcnn'):
# ROI pooling
pooledFeatures = roi_pool(self.featureMaps,self.rois,self.im_dims)
# Fully Connect layers (with dropout)
with tf.variable_scope('fc'):
self.rcnn_fc_layers = Layers(pooledFeatures)
self.rcnn_fc_layers.flatten()
self.rcnn_fc_layers.fc(output_nodes=4096, keep_prob=0.5)
self.rcnn_fc_layers.fc(output_nodes=4096, keep_prob=0.5)
hidden = self.rcnn_fc_layers.get_output()
# Classifier score
with tf.variable_scope('cls'):
self.rcnn_cls_layers = Layers(hidden)
self.rcnn_cls_layers.fc(output_nodes=self.flags['num_classes'],activation_fn=None)
# Bounding Box refinement
with tf.variable_scope('bbox'):
self.rcnn_bbox_layers = Layers(hidden)
self.rcnn_bbox_layers.fc(output_nodes=4*self.flags['num_classes'],activation_fn=None)
# Get functions
def get_cls_score(self):
return self.rcnn_cls_layers.get_output()
def get_cls_prob(self):
logits = self.get_cls_score()
return tf.nn.softmax(logits)
def get_bbox_refinement(self):
return self.rcnn_bbox_layers.get_output()
# Loss functions
def get_fast_rcnn_cls_loss(self):
fast_rcnn_cls_score = self.get_cls_score()
labels = self.roi_proposal_net.get_labels()
return fast_rcnn_cls_loss(fast_rcnn_cls_score, labels)
def get_fast_rcnn_bbox_loss(self):
fast_rcnn_bbox_pred = self.get_bbox_refinement()
bbox_targets = self.roi_proposal_net.get_bbox_targets()
roi_inside_weights = self.roi_proposal_net.get_bbox_inside_weights()
roi_outside_weights = self.roi_proposal_net.get_bbox_outside_weights()
return fast_rcnn_bbox_loss(fast_rcnn_bbox_pred, bbox_targets, roi_inside_weights, roi_outside_weights)
class fast_rcnn:
'''
Crop and resize areas from the feature-extracting CNN's feature maps
according to the ROIs generated from the ROI proposal layer
'''
def __init__(self, featureMaps, roi_proposal_net, eval_mode):
self.featureMaps = featureMaps
self.roi_proposal_net = roi_proposal_net
self.rois = roi_proposal_net.get_rois()
self.im_dims = roi_proposal_net.im_dims
self.num_classes = cfg.NUM_CLASSES
self.eval_mode = eval_mode
self._network()
def _network(self):
with tf.variable_scope('fast_rcnn'):
# No dropout in evaluation mode
keep_prob = cfg.FRCNN_DROPOUT_KEEP_RATE if self.eval_mode is False else 1.0
# ROI pooling
pooledFeatures = roi_pool(self.featureMaps, self.rois, self.im_dims)
# Fully Connect layers (with dropout)
with tf.variable_scope('fc'):
self.rcnn_fc_layers = Layers(pooledFeatures)
self.rcnn_fc_layers.flatten()
for i in range(len(cfg.FRCNN_FC_HIDDEN)):
self.rcnn_fc_layers.fc(output_nodes=cfg.FRCNN_FC_HIDDEN[i], keep_prob=keep_prob)
hidden = self.rcnn_fc_layers.get_output()
# Classifier score
with tf.variable_scope('cls'):
self.rcnn_cls_layers = Layers(hidden)
self.rcnn_cls_layers.fc(output_nodes=self.num_classes, activation_fn=None)
# Bounding Box refinement
with tf.variable_scope('bbox'):
self.rcnn_bbox_layers = Layers(hidden)
self.rcnn_bbox_layers.fc(output_nodes=self.num_classes*4, activation_fn=None)
# Get functions
def get_cls_score(self):
return self.rcnn_cls_layers.get_output()
def get_cls_prob(self):
logits = self.get_cls_score()
return tf.nn.softmax(logits)
def get_bbox_refinement(self):
return self.rcnn_bbox_layers.get_output()
# Loss functions
def get_fast_rcnn_cls_loss(self):
assert self.eval_mode is False, 'No Fast RCNN cls loss without ground truth boxes'
fast_rcnn_cls_score = self.get_cls_score()
labels = self.roi_proposal_net.get_labels()
return fast_rcnn_cls_loss(fast_rcnn_cls_score, labels)
def get_fast_rcnn_bbox_loss(self):
assert self.eval_mode is False, 'No Fast RCNN bbox loss without ground truth boxes'
fast_rcnn_bbox_pred = self.get_bbox_refinement()
bbox_targets = self.roi_proposal_net.get_bbox_targets()
roi_inside_weights = self.roi_proposal_net.get_bbox_inside_weights()
roi_outside_weights = self.roi_proposal_net.get_bbox_outside_weights()
return fast_rcnn_bbox_loss(fast_rcnn_bbox_pred, bbox_targets, roi_inside_weights, roi_outside_weights)
