def buildDualCamClassNetworkV10(x,
keep_prob,
is_training,
num_classes,
num_frames,
name_scope='DualCamClassNet'):
"""
Builds a DualCamNet network for classification using a 3D temporal convolutional layer with 7x1x1 filters.
"""
with tf.variable_scope(name_scope):
# ----------- 1st layer group ---------------
x_reshaped = tf.reshape(x, shape=(-1, num_frames, 36, 48, 512))
conv1 = build3DConvolution(x_reshaped,
512,
512,
1,
1,
7,
name_scope='conv1',
padding='SAME')
relu1 = buildReLU(conv1, 'conv1')
relu1_reshaped = tf.reshape(relu1, shape=(-1, 36, 48, 512))
# ----------- 2nd layer group ---------------
conv2 = build2DConvolution(relu1_reshaped,
512,
32,
5,
5,
name_scope='conv2',
padding='SAME')
relu2 = buildReLU(conv2, 'conv2')
pool2 = buildMaxPooling(relu2, 2, 2, 2, 2, 'conv2')
# ----------- 3rd layer group ---------------
conv3 = build2DConvolution(pool2,
32,
64,
5,
5,
name_scope='conv3',
padding='SAME')
relu3 = buildReLU(conv3, 'conv3')
pool3 = buildMaxPooling(relu3, 2, 2, 2, 2, 'conv3')
# ----------- 4th layer group ---------------
full1 = buildFullyConnected(pool3,
9 * 12 * 64,
1024,
name_scope='full1')
relu4 = buildReLU(full1, 'full1')
drop1 = buildDropout(relu4, keep_prob)
# ----------- 5th layer group ---------------
full2 = buildFullyConnected(drop1, 1024, 1000, name_scope='full2')
relu5 = buildReLU(full2, 'full2')
# ----------- 6th layer group ---------------
full3 = buildFullyConnected(relu5,
1000,
num_classes,
name_scope='full3')
return full3, {
1: conv1,
2: relu1,
3: conv2,
5: relu2,
4: pool2,
6: conv3,
7: relu3,
8: pool3,
9: full1,
10: relu4,
11: drop1,
12: full2,
13: relu5,
14: full3
}
def buildDualCamClassNetworkV11(x,
keep_prob,
is_training,
num_classes,
num_frames,
name_scope='DualCamClassNet'):
"""
Builds a DualCamNet network for classification using a 3D temporal convolutional layer with 3x1x1 filters before
and after the first 2D spatial convolutional layer.
"""
with tf.variable_scope(name_scope):
# ----------- 1st layer group ---------------
x_reshaped = tf.reshape(x, shape=(-1, num_frames, 36, 48, 512))
conv1 = build3DConvolution(x_reshaped,
512,
512,
1,
1,
3,
name_scope='conv1',
padding='SAME')
relu1 = buildReLU(conv1, 'conv1')
relu1_reshaped = tf.reshape(relu1, shape=(-1, 36, 48, 512))
# ----------- 2nd layer group ---------------
conv2 = build2DConvolution(relu1_reshaped,
512,
32,
5,
5,
name_scope='conv2',
padding='SAME')
relu2 = buildReLU(conv2, 'conv2')
pool2 = buildMaxPooling(relu2, 2, 2, 2, 2, 'conv2')
pool2_reshaped = tf.reshape(pool2, shape=(-1, num_frames, 18, 24, 32))
# ----------- 3rd layer group ---------------
conv3 = build3DConvolution(pool2_reshaped,
32,
32,
1,
1,
3,
name_scope='conv3',
padding='SAME')
relu3 = buildReLU(conv3, 'conv3')
relu3_reshaped = tf.reshape(relu3, shape=(-1, 18, 24, 32))
# ----------- 4th layer group ---------------
conv4 = build2DConvolution(relu3_reshaped,
32,
64,
5,
5,
name_scope='conv4',
padding='SAME')
relu4 = buildReLU(conv4, 'conv4')
pool4 = buildMaxPooling(relu4, 2, 2, 2, 2, 'conv4')
# ----------- 5th layer group ---------------
full5 = buildFullyConnected(pool4,
9 * 12 * 64,
1024,
name_scope='full1')
relu5 = buildReLU(full5, 'full1')
drop5 = buildDropout(relu5, keep_prob)
# ----------- 6th layer group ---------------
full6 = buildFullyConnected(drop5, 1024, 1000, name_scope='full2')
relu6 = buildReLU(full6, 'full2')
# ----------- 7th layer group ---------------
full7 = buildFullyConnected(relu6,
1000,
num_classes,
name_scope='full3')
return full7, {
1: conv1,
2: relu1,
3: conv2,
5: relu2,
4: pool2,
6: conv3,
7: relu3,
8: conv4,
9: relu4,
10: pool4,
11: full5,
12: relu5,
13: drop5,
14: full6,
15: relu6,
16: full7
}
def buildDualCamClassNetworkV13(x,
keep_prob,
is_training,
num_classes,
num_frames,
name_scope='DualCamClassNet'):
"""
Builds a DualCamNet network for classification using a set of 3D temporal convolutional layers with 13x1x1 filters
at the beginning to compress the time information followed by two 2D spatial convolutional layers.
"""
with tf.variable_scope(name_scope):
# ----------- 1st layer group ---------------
x_reshaped = tf.reshape(x, shape=(-1, num_frames, 36, 48, 512))
conv1 = build3DConvolution(x_reshaped,
512,
512,
1,
1,
13,
name_scope='conv1',
padding='SAME')
relu1 = buildReLU(conv1, 'conv1')
# ----------- 2nd layer group ---------------
conv2 = build3DConvolution(relu1,
512,
512,
1,
1,
13,
name_scope='conv2',
padding='SAME')
relu2 = buildReLU(conv2, 'conv2')
relu2_reshaped = tf.reshape(relu2, shape=(-1, 36, 48, 512))
# ----------- 3rd layer group ---------------
conv3 = build2DConvolution(relu2_reshaped,
512,
32,
5,
5,
name_scope='conv3',
padding='SAME')
relu3 = buildReLU(conv3, 'conv3')
pool3 = buildMaxPooling(relu3, 2, 2, 2, 2, 'conv3')
# ----------- 4th layer group ---------------
conv4 = build2DConvolution(pool3,
32,
64,
5,
5,
name_scope='conv4',
padding='SAME')
relu4 = buildReLU(conv4, 'conv4')
pool4 = buildMaxPooling(relu4, 2, 2, 2, 2, 'conv4')
# ----------- 5th layer group ---------------
full1 = buildFullyConnected(pool4,
9 * 12 * 64,
1024,
name_scope='full1')
relu5 = buildReLU(full1, 'full1')
drop1 = buildDropout(relu5, keep_prob)
# ----------- 6th layer group ---------------
full2 = buildFullyConnected(drop1, 1024, 1000, name_scope='full2')
relu6 = buildReLU(full2, 'full2')
# ----------- 7th layer group ---------------
full3 = buildFullyConnected(relu6,
1000,
num_classes,
name_scope='full3')
return full3, {
1: conv1,
2: relu1,
3: conv2,
4: relu2,
5: conv3,
6: relu3,
7: pool3,
8: conv4,
9: relu4,
10: pool4,
11: full1,
12: relu5,
13: drop1,
14: full2,
15: relu6,
16: full3
}