def ssd_net(inputs,
num_classes=SSDNet.default_params.num_classes,
feat_layers=SSDNet.default_params.feat_layers,
anchor_sizes=SSDNet.default_params.anchor_sizes,
anchor_ratios=SSDNet.default_params.anchor_ratios,
normalizations=SSDNet.default_params.normalizations,
is_training=True,
dropout_keep_prob=0.5,
prediction_fn=slim.softmax,
reuse=None,
scope='ssd_512_vgg'):
"""SSD net definition.
"""
# End_points collect relevant activations for external use.
end_points = {}
with tf.variable_scope(scope, 'ssd_512_vgg', [inputs], reuse=reuse):
# Original VGG-16 blocks.
net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1')
end_points['block1'] = net
net = slim.max_pool2d(net, [2, 2], scope='pool1')
# Block 2.
net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], scope='conv2')
end_points['block2'] = net
net = slim.max_pool2d(net, [2, 2], scope='pool2')
# Block 3.
net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3')
end_points['block3'] = net
net = slim.max_pool2d(net, [2, 2], scope='pool3')
# Block 4.
net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv4')
end_points['block4'] = net
net = slim.max_pool2d(net, [2, 2], scope='pool4')
# Block 5.
net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5')
end_points['block5'] = net
net = slim.max_pool2d(net, [3, 3], 1, scope='pool5')
# Additional SSD blocks.
# Block 6: let's dilate the hell out of it!
net = slim.conv2d(net, 1024, [3, 3], rate=6, scope='conv6')
end_points['block6'] = net
# Block 7: 1x1 conv. Because the f**k.
net = slim.conv2d(net, 1024, [1, 1], scope='conv7')
end_points['block7'] = net
# Block 8/9/10/11: 1x1 and 3x3 convolutions stride 2 (except lasts).
end_point = 'block8'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 256, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net,
512, [3, 3],
stride=2,
scope='conv3x3',
padding='VALID')
end_points[end_point] = net
end_point = 'block9'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net,
256, [3, 3],
stride=2,
scope='conv3x3',
padding='VALID')
end_points[end_point] = net
end_point = 'block10'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net,
256, [3, 3],
stride=2,
scope='conv3x3',
padding='VALID')
end_points[end_point] = net
end_point = 'block11'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net,
256, [3, 3],
stride=2,
scope='conv3x3',
padding='VALID')
end_points[end_point] = net
end_point = 'block12'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net,
256, [4, 4],
scope='conv4x4',
padding='VALID')
# Fix padding to match Caffe version (pad=1).
# pad_shape = [(i-j) for i, j in zip(layer_shape(net), [0, 1, 1, 0])]
# net = tf.slice(net, [0, 0, 0, 0], pad_shape, name='caffe_pad')
end_points[end_point] = net
# Prediction and localisations layers.
predictions = []
logits = []
localisations = []
for i, layer in enumerate(feat_layers):
with tf.variable_scope(layer + '_box'):
p, l = ssd_vgg_300.ssd_multibox_layer(end_points[layer],
num_classes,
anchor_sizes[i],
anchor_ratios[i],
normalizations[i])
predictions.append(prediction_fn(p))
logits.append(p)
localisations.append(l)
return predictions, localisations, logits, end_points
def ssd_net(inputs,
num_classes=SSDNet.default_params.num_classes,
feat_layers=SSDNet.default_params.feat_layers,
anchor_sizes=SSDNet.default_params.anchor_sizes,
anchor_ratios=SSDNet.default_params.anchor_ratios,
normalizations=SSDNet.default_params.normalizations,
is_training=True,
dropout_keep_prob=0.5,
prediction_fn=slim.softmax,
reuse=None,
scope='ssd_512_vgg'):
"""SSD net definition.
"""
# End_points collect relevant activations for external use.
end_points = {}
with tf.variable_scope(scope, 'ssd_512_vgg', [inputs], reuse=reuse):
# Original VGG-16 blocks.
net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1')
end_points['block1'] = net
net = slim.max_pool2d(net, [2, 2], scope='pool1')
# Block 2.
net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], scope='conv2')
end_points['block2'] = net
net = slim.max_pool2d(net, [2, 2], scope='pool2')
# Block 3.
net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3')
end_points['block3'] = net
net = slim.max_pool2d(net, [2, 2], scope='pool3')
# Block 4.
net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv4')
end_points['block4'] = net
net = slim.max_pool2d(net, [2, 2], scope='pool4')
# Block 5.
net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5')
end_points['block5'] = net
net = slim.max_pool2d(net, [3, 3], 1, scope='pool5')
# Additional SSD blocks.
# Block 6: let's dilate the hell out of it!
net = slim.conv2d(net, 1024, [3, 3], rate=6, scope='conv6')
end_points['block6'] = net
# Block 7: 1x1 conv. Because the f**k.
net = slim.conv2d(net, 1024, [1, 1], scope='conv7')
end_points['block7'] = net
# Block 8/9/10/11: 1x1 and 3x3 convolutions stride 2 (except lasts).
end_point = 'block8'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 256, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net, 512, [3, 3], stride=2, scope='conv3x3', padding='VALID')
end_points[end_point] = net
end_point = 'block9'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net, 256, [3, 3], stride=2, scope='conv3x3', padding='VALID')
end_points[end_point] = net
end_point = 'block10'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net, 256, [3, 3], stride=2, scope='conv3x3', padding='VALID')
end_points[end_point] = net
end_point = 'block11'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net, 256, [3, 3], stride=2, scope='conv3x3', padding='VALID')
end_points[end_point] = net
end_point = 'block12'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net, 256, [4, 4], scope='conv4x4', padding='VALID')
# Fix padding to match Caffe version (pad=1).
# pad_shape = [(i-j) for i, j in zip(layer_shape(net), [0, 1, 1, 0])]
# net = tf.slice(net, [0, 0, 0, 0], pad_shape, name='caffe_pad')
end_points[end_point] = net
# Prediction and localisations layers.
predictions = []
logits = []
localisations = []
for i, layer in enumerate(feat_layers):
with tf.variable_scope(layer + '_box'):
p, l = ssd_vgg_300.ssd_multibox_layer(end_points[layer],
num_classes,
anchor_sizes[i],
anchor_ratios[i],
normalizations[i])
predictions.append(prediction_fn(p))
logits.append(p)
localisations.append(l)
return predictions, localisations, logits, end_points
def ssd_net(inputs,
num_classes=SSDNet.default_params.num_classes,
feat_layers=SSDNet.default_params.feat_layers,
anchor_sizes=SSDNet.default_params.anchor_sizes,
anchor_ratios=SSDNet.default_params.anchor_ratios,
normalizations=SSDNet.default_params.normalizations,
is_training=True,
dropout_keep_prob=0.5,
prediction_fn=slim.softmax,
reuse=None,
scope='ssd_512_vgg',
DSSD_FLAG=False):
"""SSD net definition.
"""
# End_points collect relevant activations for external use.
end_points = {}
if inputs.shape[2] == inputs.shape[3]:
mode = 'bnwh'
else:
mode = 'bwhn'
with tf.variable_scope(scope, 'ssd_512_vgg', [inputs], reuse=reuse):
# Original VGG-16 blocks.
net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1')
end_points['block1'] = net
net = slim.max_pool2d(net, [2, 2], scope='pool1')
# Block 2.
net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], scope='conv2')
end_points['block2'] = net
net = slim.max_pool2d(net, [2, 2], scope='pool2')
# Block 3.
net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3')
end_points['block3'] = net
net = slim.max_pool2d(net, [2, 2], scope='pool3')
# Block 4.
net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv4')
end_points['block4'] = net
net = slim.max_pool2d(net, [2, 2], scope='pool4')
# Block 5.
net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5')
end_points['block5'] = net
net = slim.max_pool2d(net, [3, 3], 1, scope='pool5')
# Additional SSD blocks.
# Block 6: let's dilate the hell out of it!
net = slim.conv2d(net, 1024, [3, 3], rate=6, scope='conv6')
end_points['block6'] = net
# Block 7: 1x1 conv. Because the f**k.
net = slim.conv2d(net, 1024, [1, 1], scope='conv7')
end_points['block7'] = net
# Block 8/9/10/11: 1x1 and 3x3 convolutions stride 2 (except lasts).
end_point = 'block8'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 256, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net,
512, [3, 3],
stride=2,
scope='conv3x3',
padding='VALID')
end_points[end_point] = net
end_point = 'block9'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net,
256, [3, 3],
stride=2,
scope='conv3x3',
padding='VALID')
end_points[end_point] = net
end_point = 'block10'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net,
256, [3, 3],
stride=2,
scope='conv3x3',
padding='VALID')
end_points[end_point] = net
end_point = 'block11'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net,
256, [3, 3],
stride=2,
scope='conv3x3',
padding='VALID')
end_points[end_point] = net
end_point = 'block12'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net,
256, [4, 4],
scope='conv4x4',
padding='VALID')
# Fix padding to match Caffe version (pad=1).
# pad_shape = [(i-j) for i, j in zip(layer_shape(net), [0, 1, 1, 0])]
# net = tf.slice(net, [0, 0, 0, 0], pad_shape, name='caffe_pad')
end_points[end_point] = net
# Prediction and localisations layers.
# rever_feat_layers = list(reversed(feat_layers))
# for i, l in enumerate(rever_feat_layers):
# if i == 0: continue
# l_ = rever_feat_layers[i - 1]
#
# end_points[l] = tf.concat([upbilinear([end_points[l_], end_points[l]], name=l_), end_points[l]],axis=1)
# with tf.variable_scope("fpn11"):
#
#
# end_points['block11'] = tf.add(upbilinear([end_points['block12'], end_points['block11']],name ="up_11",mode=mode),
# end_points['block11'],name= "fpn_block11")
#
# with tf.variable_scope("fpn10"):
#
# end_points['block10'] = tf.add(upbilinear([end_points['block11'],end_points['block10']],name ="up_10",mode=mode),
# end_points['block10'],
# name="fpn_block10")
# with tf.variable_scope("fpn9"):
# b9 = slim.conv2d(end_points['block10'], 256, [1, 1], scope='9conv1x1')
# b9_ = slim.conv2d(end_points['block9'], 256, [1, 1], scope='9_conv1x1')
# end_points['block9'] = tf.add(upbilinear([end_points['block10'],end_points['block9']],name ="up_9",mode=mode),
# end_points['block9'],
# name="fpn_block9")
# with tf.variable_scope("fpn8"):
# b8 = slim.conv2d(end_points['block9'], 512, [1, 1], scope='8conv1x1')
#
# end_points['block8'] = tf.add(upbilinear([b8, end_points['block8']],name ="up_8",mode=mode), end_points['block8'],
# name="fpn_block8")
# with tf.variable_scope("fpn7"):
# b7 = slim.conv2d(end_points['block8'], 1024, [1, 1], scope='7conv1x1')
#
# end_points['block7'] = tf.add(upbilinear([b7, end_points['block7']],name ="up_7",mode=mode), end_points['block7'],
# name="fpn_block7")
# with tf.variable_scope("fpn4"):
# b4 = slim.conv2d(end_points['block7'], 512, [1, 1], scope='4conv1x1')
#
# end_points['block4'] = tf.add(upbilinear([b4, end_points['block4']],name ="up_4",mode=mode), end_points['block4'],
# name="fpn_block4")
if DSSD_FLAG:
with tf.variable_scope("dssd11"):
de_12 = slim.conv2d_transpose(end_points['block12'],
512, [3, 3],
stride=2,
scope="de_12")
con_12 = slim.conv2d(de_12, 512, [3, 3], scope='conv_12')
bn_12 = slim.batch_norm(con_12, is_training=is_training)
con_11 = slim.conv2d(end_points["block11"],
512, [3, 3],
scope="conv11")
bn_11 = slim.batch_norm(con_11, is_training=is_training)
relu_11 = tf.nn.relu(bn_11)
con_11 = slim.conv2d(relu_11, 512, [3, 3], scope="conv11_2")
bn_11 = slim.batch_norm(con_11, is_training=is_training)
end_points["block11"] = tf.nn.relu(tf.multiply(bn_12, bn_11))
with tf.variable_scope("dssd10"):
de_11 = slim.conv2d_transpose(end_points['block11'],
512, [3, 3],
stride=2,
scope="de_11")
con_11 = slim.conv2d(de_11, 512, [3, 3], scope='conv_11')
bn_11 = slim.batch_norm(con_11, is_training=is_training)
con_10 = slim.conv2d(end_points["block10"],
512, [3, 3],
scope="conv10")
bn_10 = slim.batch_norm(con_10, is_training=is_training)
relu_10 = tf.nn.relu(bn_10)
con_10 = slim.conv2d(relu_10, 512, [3, 3], scope="conv10_2")
bn_10 = slim.batch_norm(con_10, is_training=is_training)
end_points["block10"] = tf.nn.relu(tf.multiply(bn_11, bn_10))
with tf.variable_scope("dssd9"):
de_10 = slim.conv2d_transpose(end_points['block10'],
512, [3, 3],
stride=2,
scope="de_10")
con_10 = slim.conv2d(de_10, 512, [3, 3], scope='conv_10')
bn_10 = slim.batch_norm(con_10, is_training=is_training)
con_9 = slim.conv2d(end_points["block9"],
512, [3, 3],
scope="conv9")
bn_9 = slim.batch_norm(con_9, is_training=is_training)
relu_9 = tf.nn.relu(bn_9)
con_9 = slim.conv2d(relu_9, 512, [3, 3], scope="conv9_2")
bn_9 = slim.batch_norm(con_9, is_training=is_training)
end_points["block9"] = tf.nn.relu(tf.multiply(bn_10, bn_9))
with tf.variable_scope("dssd8"):
de_9 = slim.conv2d_transpose(end_points['block9'],
512, [3, 3],
stride=2,
scope="de_9")
con_9 = slim.conv2d(de_9, 512, [3, 3], scope='conv_9')
bn_9 = slim.batch_norm(con_9, is_training=is_training)
con_8 = slim.conv2d(end_points["block8"],
512, [3, 3],
scope="conv8")
bn_8 = slim.batch_norm(con_8, is_training=is_training)
relu_8 = tf.nn.relu(bn_8)
con_8 = slim.conv2d(relu_8, 512, [3, 3], scope="conv8_2")
bn_8 = slim.batch_norm(con_8, is_training=is_training)
end_points["block8"] = tf.nn.relu(tf.multiply(bn_9, bn_8))
with tf.variable_scope("dssd7"):
de_8 = slim.conv2d_transpose(end_points['block8'],
512, [3, 3],
stride=2,
scope="de_8")
con_8 = slim.conv2d(de_8, 512, [3, 3], scope='conv_8')
bn_8 = slim.batch_norm(con_8, is_training=is_training)
con_7 = slim.conv2d(end_points["block7"],
512, [3, 3],
scope="conv7")
bn_7 = slim.batch_norm(con_7, is_training=is_training)
relu_7 = tf.nn.relu(bn_7)
con_7 = slim.conv2d(relu_7, 512, [3, 3], scope="conv7_2")
bn_7 = slim.batch_norm(con_7, is_training=is_training)
end_points["block7"] = tf.nn.relu(tf.multiply(bn_8, bn_7))
with tf.variable_scope("dssd4"):
de_7 = slim.conv2d_transpose(end_points['block7'],
512, [3, 3],
stride=2,
scope="de_7")
con_7 = slim.conv2d(de_7, 512, [3, 3], scope='conv_7')
bn_7 = slim.batch_norm(con_7, is_training=is_training)
con_4 = slim.conv2d(end_points["block4"],
512, [3, 3],
scope="conv4")
bn_4 = slim.batch_norm(con_4, is_training=is_training)
relu_4 = tf.nn.relu(bn_4)
con_4 = slim.conv2d(relu_4, 512, [3, 3], scope="conv4_2")
bn_4 = slim.batch_norm(con_4, is_training=is_training)
end_points["block4"] = tf.nn.relu(tf.multiply(bn_7, bn_4))
#
predictions = []
logits = []
localisations = []
for i, layer in enumerate(feat_layers):
with tf.variable_scope(layer + '_box'):
p, l = ssd_vgg_300.ssd_multibox_layer(end_points[layer],
num_classes,
anchor_sizes[i],
anchor_ratios[i],
normalizations[i])
predictions.append(prediction_fn(p))
logits.append(p)
localisations.append(l)
return predictions, localisations, logits, end_points
def ssd_net(inputs,
num_classes=SSDNet.default_params.num_classes,
feat_layers=SSDNet.default_params.feat_layers,
anchor_sizes=SSDNet.default_params.anchor_sizes,
anchor_ratios=SSDNet.default_params.anchor_ratios,
normalizations=SSDNet.default_params.normalizations,
is_training=True,
dropout_keep_prob=0.5,
prediction_fn=slim.softmax,
reuse=None,
scope='ssd_512_vgg'):
"""SSD net definition.
"""
# End_points collect relevant activations for external use.
end_points = {}
with tf.variable_scope(scope, 'ssd_512_vgg', [inputs], reuse=reuse):
# Original VGG-16 blocks.
print(inputs.shape)
#inputs = tf.transpose(inputs, [0,2,3,1])
with tf.variable_scope("RseNet50"):
with tf.variable_scope("RseNet50"):
net = slim.conv2d(inputs,
64, [3, 3],
activation_fn=tf.nn.selu,
stride=2,
data_format=data_format) # 256
print(net.shape)
end_points['block0'] = net
print('block0')
net = unit_neck(net, [32, 32, 32], 'block1', False)
end_points['block1'] = net
print('block1')
net = block(net, [[96, 96, 48], [144, 144, 48]], 2,
'block1') # 128
end_points['block2'] = net
print('block2')
net = block(net, [[144, 144, 64], [192, 192, 64]], 3,
'block2') # 64
end_points['block3'] = net
print('block3')
net = block(net, [[144, 144, 64], [192, 192, 64]], 3,
'block3') # 32
end_points['block4'] = net
print('block4')
net = block(net, [[192, 192, 128], [384, 384, 128]], 4,
'block4') # 16
end_points['block5'] = net
print('block5')
net = block(net, [[384, 384, 192], [576, 576, 192]],
3,
'block5',
stride=1)
net = block(net, [[576, 576, 320], [960, 960, 320]], 3,
'block6') # 8
end_points['block6'] = net
print('block6')
net = block(net, [[576, 576, 320], [960, 960, 320]], 3,
'block7') # 4
end_points['block7'] = net
end_point = 'Fblock6'
with tf.variable_scope(end_point):
p = slim.conv2d_transpose(net,
256, [3, 3],
stride=2,
activation_fn=tf.nn.selu,
data_format=data_format)
c = slim.conv2d(end_points['block6'],
256, [3, 3],
activation_fn=tf.nn.selu,
data_format=data_format)
print(p.shape, c.shape)
f = tf.concat([p, c], axis=funsion_axis)
net = slim.conv2d(f,
256, [1, 1],
scope='F6conv1x1',
activation_fn=tf.nn.selu,
data_format=data_format)
print(net.shape)
end_points[end_point] = net
end_point = 'Fblock5'
with tf.variable_scope(end_point):
p = slim.conv2d_transpose(net,
256, [3, 3],
stride=2,
activation_fn=tf.nn.selu,
data_format=data_format)
c = slim.conv2d(end_points['block5'],
256, [3, 3],
activation_fn=tf.nn.selu,
data_format=data_format)
print(p.shape, c.shape)
f = tf.concat([p, c], axis=funsion_axis)
net = slim.conv2d(f,
256, [1, 1],
scope='F5conv1x1',
activation_fn=tf.nn.selu,
data_format=data_format)
print(net.shape)
end_points[end_point] = net
end_point = 'Fblock4'
with tf.variable_scope(end_point):
p = slim.conv2d_transpose(net,
256, [3, 3],
stride=2,
activation_fn=tf.nn.selu,
data_format=data_format)
c = slim.conv2d(end_points['block4'],
256, [3, 3],
activation_fn=tf.nn.selu,
data_format=data_format)
print(p.shape, c.shape)
f = tf.concat([p, c], axis=funsion_axis)
net = slim.conv2d(f,
256, [1, 1],
scope='F4conv1x1',
activation_fn=tf.nn.selu,
data_format=data_format)
print(net.shape)
end_points[end_point] = net
end_point = 'Fblock3'
with tf.variable_scope(end_point):
p = slim.conv2d_transpose(net,
256, [3, 3],
stride=2,
activation_fn=tf.nn.selu,
data_format=data_format)
c = slim.conv2d(end_points['block3'],
256, [3, 3],
activation_fn=tf.nn.selu,
data_format=data_format)
print(p.shape, c.shape)
f = tf.concat([p, c], axis=funsion_axis)
net = slim.conv2d(f,
256, [1, 1],
scope='F3conv1x1',
activation_fn=tf.nn.selu,
data_format=data_format)
print(net.shape)
end_points[end_point] = net
predictions = []
logits = []
localisations = []
for i, layer in enumerate(feat_layers):
with tf.variable_scope(layer + '_box'):
p, l = ssd_vgg_300.ssd_multibox_layer(end_points[layer],
num_classes,
anchor_sizes[i],
anchor_ratios[i],
normalizations[i])
predictions.append(prediction_fn(p))
logits.append(p)
localisations.append(l)
return predictions, localisations, logits, end_points
def ssd_net(inputs,
num_classes=SSDNet.default_params.num_classes,
feat_layers=SSDNet.default_params.feat_layers,
anchor_sizes=SSDNet.default_params.anchor_sizes,
anchor_ratios=SSDNet.default_params.anchor_ratios,
normalizations=SSDNet.default_params.normalizations,
is_training=True,
dropout_keep_prob=0.5,
prediction_fn=slim.softmax,
reuse=None,
scope='ssd_512_vgg'):
"""SSD net definition.
"""
# End_points collect relevant activations for external use.
end_points = {}
with tf.variable_scope(scope, 'ssd_512_vgg', [inputs], reuse=reuse):
# Original VGG-16 blocks.
net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1')
end_points['block1'] = net
# print("====net.shape = {}".format(net))
net = slim.max_pool2d(net, [2, 2], scope='pool1')
# Block 2.
net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], scope='conv2')
end_points['block2'] = net
net = slim.max_pool2d(net, [2, 2], scope='pool2')
# Block 3.txt.
net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3')
end_points['block3'] = net
net = slim.max_pool2d(net, [2, 2], scope='pool3')
# Block 4.
net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv4')
end_points['block4'] = net
net = slim.max_pool2d(net, [2, 2], scope='pool4')
# Block 5.
net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5')
end_points['block5'] = net
net = slim.max_pool2d(net, [3, 3], 1, scope='pool5')
# Additional SSD blocks.
# Block 6: let's dilate the hell out of it!
net = slim.conv2d(net, 1024, [3, 3], rate=6, scope='conv6')
end_points['block6'] = net
# Block 7: 1x1 conv. Because the f**k.
net = slim.conv2d(net, 1024, [1, 1], scope='conv7')
end_points['block7'] = net
if IS_FPN:
stride_b8_to_b12 = 1
else:
stride_b8_to_b12 = 2
# Block 8/9/10/11: 1x1 and 3x3 convolutions stride 2 (except lasts).
end_point = 'block8'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 256, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net,
512, [3, 3],
stride=2,
scope='conv3x3',
padding='VALID')
end_points[end_point] = net
end_point = 'block9'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net,
256, [3, 3],
stride=stride_b8_to_b12,
scope='conv3x3',
padding='VALID')
end_points[end_point] = net
end_point = 'block10'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net,
256, [3, 3],
stride=stride_b8_to_b12,
scope='conv3x3',
padding='VALID')
end_points[end_point] = net
end_point = 'block11'
with tf.variable_scope(end_point):
net = slim.conv2d(net, 128, [1, 1], scope='conv1x1')
net = custom_layers.pad2d(net, pad=(1, 1))
net = slim.conv2d(net,
256, [3, 3],
stride=stride_b8_to_b12,
scope='conv3x3',
padding='VALID')
end_points[end_point] = net
end_point = 'concat'
with tf.variable_scope(end_point):
high_feature_list = []
for i in range(9, 12):
high_feature_list.append(end_points['block' + str(i)])
high_feature = tf.concat(high_feature_list, 1)
end_points[end_point] = high_feature
end_point = 'block4_concat'
with tf.variable_scope(end_point):
net_block4 = slim.conv2d(end_points['concat'],
128, [1, 1],
scope='conv1x1')
# print("net_block4 ========{}".format(net_block4))
net_block4 = tf.layers.conv2d_transpose(
net_block4,
512,
kernel_size=3,
strides=(4, 4),
data_format='channels_first')
# print("net_block4 ========{}".format(net_block4))
end_points['block4'] += net_block4
end_point = 'block7_concat'
with tf.variable_scope(end_point):
net_block7 = slim.conv2d(end_points['concat'],
128, [1, 1],
scope='conv1x1')
# print("net_block4 ========{}".format(net_block4))
net_block7 = tf.layers.conv2d_transpose(
net_block7,
1024,
kernel_size=1,
strides=(2, 2),
data_format='channels_first')
# print("net_block4 ========{}".format(net_block4))
end_points['block7'] += net_block7
end_point = 'block8_concat'
with tf.variable_scope(end_point):
net_block8 = slim.conv2d(end_points['concat'],
512, [1, 1],
scope='conv1x1')
end_points['block8'] += net_block8
# with tf.variable_scope(end_point):
# print("=debug===========high_feature = {}".format(high_feature))
# for i in range(1,12):
# print("=debug===== "+str(i)+" = {}".format(end_points['block'+str(i)]))
# Prediction and localisations layers.
predictions_pest = []
logits_pest = []
predictions = []
logits = []
localisations = []
for i, layer in enumerate(feat_layers):
with tf.variable_scope(layer + '_box'):
# print("=debug===== "+str(i)+" = {}".format(end_points[layer]))
# 这里获取每一个anchor的预测值
pest, p, l = ssd_vgg_300.ssd_multibox_layer(
end_points[layer], num_classes, anchor_sizes[i],
anchor_ratios[i], normalizations[i])
predictions_pest.append(prediction_fn(pest))
logits_pest.append(pest)
predictions.append(prediction_fn(p))
logits.append(p)
localisations.append(l)
return predictions_pest, logits_pest, predictions, localisations, logits, end_points
