def model(x, y, batch_size, is_training=True, reuse=None):
with tf.variable_scope('model', reuse=reuse):
x_tensor = tf.reshape(x, [-1, 28, 28, 1])
fc1 = fc(x, 20, is_training, reuse, name='fc1', activation=None)
fc1 = tf.tanh(fc1)
fc1 = dropout(fc1, is_training, drop_p=0.5)
fc2 = fc(fc1, 6, is_training, reuse, use_bias=False, name='fc2')
initial = np.array([[1., 0, 0], [0, 1., 0]])
initial = initial.astype('float32')
initial = initial.flatten()
fc2_b = tf.Variable(initial_value=initial, name='fc2/b')
fc2 = tf.nn.bias_add(fc2, bias=fc2_b)
fc2 = tf.tanh(fc2)
h_trans = spatialtransformer(x_tensor, fc2, batch_size=batch_size)
conv1 = conv2d(h_trans,
16,
is_training,
reuse,
activation=prelu,
name='conv1')
conv2 = conv2d(conv1,
16,
is_training,
reuse,
stride=(2, 2),
activation=prelu,
name='conv2')
fcmain = fc(conv2,
1024,
is_training,
reuse,
name='fc',
activation=prelu)
fcmain = dropout(fcmain, is_training, drop_p=0.5)
logits = fc(fcmain,
10,
is_training,
reuse,
name='logits',
activation=None)
prediction = softmax(logits, 'prediction')
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=y))
opt = tf.train.AdamOptimizer()
optimizer = opt.minimize(loss)
# grads = opt.compute_gradients(loss, [fc2_b])
correct_prediction = tf.equal(tf.argmax(prediction, 1),
tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, 'float'))
return accuracy, loss, optimizer
def discriminator(inputs, is_training, reuse, num_classes=1):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True,
activation=lrelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
conv_args_1st = make_args(batch_norm=None,
activation=lrelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
logits_args = make_args(activation=None,
w_init=initz.he_normal(scale=1),
**common_args)
pool_args = make_args(padding='SAME', **common_args)
end_points = {}
x = inputs
end_points['inputs'] = x
x = dropout(x, drop_p=0.2, name="input_dropout1", **common_args)
x = conv2d(x,
96,
filter_size=(5, 5),
stride=(2, 2),
name="d_conv1_1",
**conv_args_1st)
end_points['d_conv1_1'] = x
x = conv2d(x, 96, name="d_conv1_2", **conv_args)
end_points['d_conv1_2'] = x
x = conv2d(x, 96, stride=(2, 2), name="d_conv1_3", **conv_args)
end_points['d_conv1_3'] = x
x = dropout(x, drop_p=0.2, name="dropout1", **common_args)
x = conv2d(x, 192, name="d_conv2_1", **conv_args)
end_points['d_conv2_1'] = x
x = conv2d(x, 192, name="d_conv2_2", **conv_args)
end_points['d_conv2_2'] = x
# x = conv2d(x, 192, stride=(2, 2), name="d_conv2_3", **conv_args)
# end_points['d_conv2_3'] = x
x = dropout(x, drop_p=0.2, name="dropout2", **common_args)
# x = conv2d(x, 192, stride=(2, 2), name="d_conv3_1", **conv_args)
# end_points['d_conv3_1'] = x
x = conv2d(x, 192, filter_size=(1, 1), name="d_conv4_1", **conv_args)
end_points['d_conv4_1'] = x
x = conv2d(x, 192, filter_size=(1, 1), name="d_conv4_2", **conv_args)
end_points['d_conv4_2'] = x
x = global_avg_pool(x, name="global_pool")
end_points['global_pool'] = x
logits = fully_connected(x, num_classes, name="d_logits", **logits_args)
end_points['logits'] = logits
end_points['predictions'] = softmax(logits,
name='predictions',
**common_args)
return end_points
def encoder(inputs, is_training, reuse, z_dim=512):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True,
activation=lrelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
conv_args_1st = make_args(batch_norm=None,
activation=lrelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
logits_args = make_args(activation=None,
w_init=initz.he_normal(scale=1),
**common_args)
pool_args = make_args(padding='SAME', **common_args)
end_points = {}
x = inputs
end_points['inputs'] = x
x = dropout(x, drop_p=0.2, name="input_dropout1", **common_args)
x = conv2d(x,
96,
filter_size=(5, 5),
stride=(2, 2),
name="e_conv1_1",
**conv_args_1st)
end_points['e_conv1_1'] = x
x = conv2d(x, 96, name="e_conv1_2", **conv_args)
end_points['e_conv1_2'] = x
x = conv2d(x, 96, stride=(2, 2), name="e_conv1_3", **conv_args)
end_points['e_conv1_3'] = x
x = dropout(x, drop_p=0.2, name="dropout1", **common_args)
x = conv2d(x, 192, name="e_conv2_1", **conv_args)
end_points['e_conv2_1'] = x
x = conv2d(x, 192, name="e_conv2_2", **conv_args)
end_points['e_conv2_2'] = x
# x = conv2d(x, 192, stride=(2, 2), name="e_conv2_3", **conv_args)
# end_points['e_conv2_3'] = x
x = dropout(x, drop_p=0.2, name="dropout2", **common_args)
# x = conv2d(x, 192, stride=(2, 2), name="e_conv3_1", **conv_args)
# end_points['e_conv3_1'] = x
x = conv2d(x, 192, filter_size=(1, 1), name="e_conv4_1", **conv_args)
end_points['e_conv4_1'] = x
x = conv2d(x, 192, filter_size=(1, 1), name="e_conv4_2", **conv_args)
end_points['e_conv4_2'] = x
x = global_avg_pool(x, name="global_pool")
end_points['global_pool'] = x
logits1 = fully_connected(x, z_dim, name="e_logits1", **logits_args)
logits2 = fully_connected(x, z_dim, name="e_logits2", **logits_args)
logits2 = tf.tanh(logits2, name='e_logits2_tanh')
end_points['e_logits1'] = logits1
end_points['e_logits2'] = logits2
return end_points
def trans_block(inputs, num_filters, drop_p=None, block_name='trans', **kwargs):
x = conv2d(inputs, num_filters, filter_size=(1, 1), name=block_name + "_conv1_1", **kwargs)
if drop_p:
is_training = kwargs.get('is_training')
x = dropout(x, is_training, drop_p=drop_p, name=block_name + "_trans_dropout")
x = rms_pool_2d(x, name=block_name + "rms_pool1", padding='SAME')
return x
def model(is_training, resue, num_classes=5):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(
untie_biases=True, batch_norm=batch_norm, **common_args)
logit_args = make_args(activation=prelu, **common_args)
inputs = input((None, crop_size[1], crop_size[0], 3), **common_args)
net = conv2d(inputs, 32, filter_size=(3, 3), stride=(
2, 2), name='conv1', **conv_params)
net = conv2d(net, 64, name='conv2', **conv_params)
net = bottleneck_v1(net, num_unit=128, name='block_v1_1', **conv_args)
net = bottleneck_v1(net, num_unit=256, name='block_v1_2', **conv_args)
net = bottleneck_v1(net, num_unit=728, name='block_v1_3', **conv_args)
for i in range(8):
prefix = 'block_v2_' + str(i + 5)
net = bottleneck_v2(net, num_unit=728, name=prefix, **kwargs)
net = bottleneck_v1(net, num_unit=1024, name='block_v1_4', **conv_args)
net = separable_conv2d(net, 1536, filter_size=(3, 3), stride=(1, 1),
name='sconv1', **kwargs)
net = separable_conv2d(net, 2048, filter_size=(3, 3), stride=(1, 1),
name='sconv2', **kwargs)
with tf.variable_scope('Logits'):
net = avg_pool_2d(net, net.get_shape()[1:3], name='AvgPool_1a')
net = dropout(
net, is_training, drop_p=1 - dropout_keep_prob, name='Dropout_1b')
logits = fully_connected(net, num_classes,
name='logits', **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(is_training, reuse, dropout_keep_prob=0.5):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True, activation=prelu, w_init=initz.he_normal(
scale=1), untie_biases=False, **common_args)
pool_args = make_args(padding='SAME', **common_args)
inputs = input((None, crop_size[1], crop_size[0], 3), **common_args)
with tf.variable_scope('squeezenet', values=[inputs]):
net = conv2d(inputs, 96, stride=(2, 2), name='conv1', **conv_args)
net = max_pool(net, name='maxpool1', **pool_args)
net = fire_module(net, 16, 64, name='fire2', **conv_args)
net = fire_module(net, 16, 64, name='fire3', **conv_args)
net = fire_module(net, 32, 128, name='fire4', **conv_args)
net = max_pool(net, name='maxpool4', **pool_args)
net = fire_module(net, 32, 128, name='fire5', **conv_args)
net = fire_module(net, 48, 192, name='fire6', **conv_args)
net = fire_module(net, 48, 192, name='fire7', **conv_args)
net = fire_module(net, 64, 256, name='fire8', **conv_args)
net = max_pool(net, name='maxpool8', **pool_args)
net = fire_module(net, 64, 256, name='fire9', **conv_args)
# Reversed avg and conv layers per 'Network in Network'
net = dropout(net, drop_p=1 - dropout_keep_prob,
name='dropout6', **common_args)
net = conv2d(net, 10, filter_size=(1, 1), name='conv10', **conv_args)
logits = global_avg_pool(net, name='logits', **pool_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def conv_block(inputs, num_filters, drop_p=None, block_name='block', **kwargs):
inter_filters = num_filters * 4
x = conv2d(inputs, inter_filters, filter_size=(1, 1), name=block_name + "_conv1_1", **kwargs)
if drop_p:
is_training = kwargs.get('is_training')
x = dropout(x, is_training, drop_p=drop_p, name=block_name + "_conv_dropout")
x = conv2d(x, num_filters, name=block_name + "_conv1_2", **kwargs)
return x
def model(is_training, reuse):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=None, activation=prelu, **common_args)
fc_args = make_args(activation=prelu, **common_args)
logit_args = make_args(activation=None, **common_args)
x = input((None, crop_size[1], crop_size[0], 1), **common_args)
x = conv2d(x, 32, name='conv1_1', **conv_args)
x = conv2d(x, 32, name='conv1_2', **conv_args)
x = max_pool(x, name='pool1', **common_args)
x = dropout(x, drop_p=0.25, name='dropout1', **common_args)
x = fully_connected(x, n_output=128, name='fc1', **fc_args)
x = dropout(x, drop_p=0.5, name='dropout2', **common_args)
logits = fully_connected(x, n_output=36, name="logits", **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(inputs, is_training, reuse, num_classes=10, dropout_keep_prob=0.5):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True,
activation=prelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
conv_args_fm = make_args(w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
pool_args = make_args(padding='SAME', **common_args)
with tf.variable_scope('squeezenet', values=[inputs]):
net = separable_conv2d(inputs,
256,
stride=(2, 2),
name='conv1',
**conv_args)
# net = conv2d(inputs, 96, stride=(2, 2), name='conv1', **conv_args)
net = max_pool(net, name='maxpool1', **pool_args)
net = fire_module(net, 16, 64, name='fire2', **conv_args_fm)
net = bottleneck_simple(net, 16, 64, name='fire3', **conv_args_fm)
net = batch_norm(net,
activation_fn=tf.nn.relu,
name='fire3_bn',
is_training=is_training,
reuse=reuse)
net = fire_module(net, 32, 128, name='fire4', **conv_args_fm)
net = max_pool(net, name='maxpool4', **pool_args)
net = bottleneck_simple(net, 32, 128, name='fire5', **conv_args_fm)
net = batch_norm(net,
activation_fn=tf.nn.relu,
name='fire5_bn',
is_training=is_training,
reuse=reuse)
net = fire_module(net, 48, 192, name='fire6', **conv_args_fm)
net = bottleneck_simple(net, 48, 192, name='fire7', **conv_args_fm)
net = batch_norm(net,
activation_fn=tf.nn.relu,
name='fire7_bn',
is_training=is_training,
reuse=reuse)
net = fire_module(net, 64, 256, name='fire8', **conv_args_fm)
net = max_pool(net, name='maxpool8', **pool_args)
net = dropout(net,
drop_p=1 - dropout_keep_prob,
name='dropout6',
**common_args)
net = conv2d(net,
num_classes,
filter_size=(1, 1),
name='conv10',
**conv_args_fm)
logits = global_avg_pool(net, name='logits', **pool_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(is_training, reuse):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(activation=relu, **common_args)
pool_args = make_args(filter_size=(2, 2), **common_args)
fc_args = make_args(activation=relu, **common_args)
logit_args = make_args(activation=None, **common_args)
x = input((None, crop_size[1], crop_size[0], 3), **common_args)
x = conv2d(x, 64, name='conv1_1', **conv_args)
x = conv2d(x, 64, name='conv1_2', **conv_args)
x = max_pool(x, name='maxpool1', **pool_args)
x = conv2d(x, 128, name='conv2_1', **conv_args)
x = conv2d(x, 128, name='conv2_2', **conv_args)
x = max_pool(x, name='maxpool2', **pool_args)
x = conv2d(x, 256, name='conv3_1', **conv_args)
x = conv2d(x, 256, name='conv3_2', **conv_args)
x = conv2d(x, 256, name='conv3_3', **conv_args)
x = max_pool(x, name='maxpool3', **pool_args)
x = conv2d(x, 512, name='conv4_1', **conv_args)
x = conv2d(x, 512, name='conv4_2', **conv_args)
x = conv2d(x, 512, name='conv4_3', **conv_args)
x = max_pool(x, name='maxpool4', **pool_args)
x = conv2d(x, 512, name='conv5_1', **conv_args)
x = conv2d(x, 512, name='conv5_2', **conv_args)
x = conv2d(x, 512, name='conv5_3', **conv_args)
x = max_pool(x, name='maxpool5', **pool_args)
x = fully_connected(x, n_output=4096, name='fc6', **fc_args)
x = dropout(x, drop_p=0.5, name='dropout1', **common_args)
x = fully_connected(x, n_output=4096, name='fc7', **fc_args)
x = dropout(x, drop_p=0.5, name='dropout2', **common_args)
logits = fully_connected(x, n_output=1000, name="logits", **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(is_training, reuse):
common_args = common_layer_args(is_training, reuse)
x = input((None, 7, 7, 512), **common_args)
# x = batch_norm_tf(x, **common_args)
x = fully_connected(x, 512, activation=relu, name='fc1', **common_args)
x = dropout(x, drop_p=0.5, name='dropout1', **common_args)
logits = fully_connected(x,
6,
activation=None,
name='logits',
**common_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(x, is_training, reuse, num_classes=2, **kwargs):
common_args = common_layer_args(is_training, reuse)
fc_args = make_args(activation=relu, **common_args)
logit_args = make_args(activation=None, **common_args)
x = embedding(x, 10000, 128, reuse)
x1 = conv1d(x, 128, name='conv1_1', **common_args)
x2 = conv1d(x, 128, filter_size=4, name='conv1_2', **common_args)
x3 = conv1d(x, 128, filter_size=5, name='conv1_3', **common_args)
x = merge([x1, x2, x3], 'concat', axis=1)
x = lstm(x, 384, reuse, is_training)
x = dropout(x, drop_p=0.3, **common_args)
logits = fc(x, num_classes, name='logits', **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(x, is_training, reuse):
common_args = common_layer_args(is_training, reuse)
fc_args = make_args(activation=relu, **common_args)
logit_args = make_args(activation=None, **common_args)
x = embedding(x, 10000, 128, reuse)
x1 = conv1d(x, 128, name='conv1_1', **common_args)
x2 = conv1d(x, 128, filter_size=4, name='conv1_2', **common_args)
x3 = conv1d(x, 128, filter_size=5, name='conv1_3', **common_args)
x = merge([x1, x2, x3], 'concat', axis=1)
x = tf.expand_dims(x, 2)
x = global_max_pool(x)
x = dropout(x, drop_p=0.3, **common_args)
logits = fc(x, 2, name='logits', **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(x, is_training, reuse, num_classes=10, **config):
common_args = common_layer_args(is_training, reuse)
logit_args = make_args(activation=None, **common_args)
if config['max_conv_layers']>0:
for i in range(1, config['n_conv_layers']+1):
activation, size, maxpool = layer_config(config, i, layer_type='conv')
conv_args = make_args(batch_norm=bool(config['batch_norm']), activation=prelu, **common_args)
x = conv2d(x, size, name='conv{}'.format(i), **conv_args)
if maxpool:
x = max_pool(x, name='pool{}'.format(i), **common_args)
if config['max_fc_layers']>0:
for i in range(1, config['n_fc_layers']+1):
activation, size, _dropout = layer_config(config, i, layer_type='fc')
fc_args = make_args(activation=prelu, **common_args)
x = fully_connected(x, n_output=size, name='fc{}'.format(i), **fc_args)
x = dropout(x, drop_p=np.round(_dropout, 2), name='dropout{}'.format(i), **common_args)
logits = fully_connected(x, n_output=num_classes, name="logits", **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(is_training, reuse, flexi_inputs=False):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(activation=relu, **common_args)
pool_args = make_args(filter_size=(2, 2), **common_args)
logit_args = make_args(activation=None, **common_args)
if flexi_inputs:
inputs_shape = (None, None, None, 3)
else:
inputs_shape = (None, crop_size[1], crop_size[0], 3)
net_inputs = input(inputs_shape, **common_args)
x = net_inputs
with tf.variable_scope('vgg_16', reuse=reuse):
mean_rgb = tf.get_variable(name='mean_rgb',
initializer=tf.truncated_normal(shape=[3]),
trainable=False)
x = x - mean_rgb
with tf.variable_scope('conv1'):
x = conv2d(x, 64, name='conv1_1', **conv_args)
x = conv2d(x, 64, name='conv1_2', **conv_args)
x = max_pool(x, name='maxpool1', **pool_args)
with tf.variable_scope('conv2'):
x = conv2d(x, 128, name='conv2_1', **conv_args)
x = conv2d(x, 128, name='conv2_2', **conv_args)
x = max_pool(x, name='maxpool2', **pool_args)
with tf.variable_scope('conv3'):
x = conv2d(x, 256, name='conv3_1', **conv_args)
x = conv2d(x, 256, name='conv3_2', **conv_args)
x = conv2d(x, 256, name='conv3_3', **conv_args)
x = max_pool(x, name='maxpool3', **pool_args)
with tf.variable_scope('conv4'):
x = conv2d(x, 512, name='conv4_1', **conv_args)
x = conv2d(x, 512, name='conv4_2', **conv_args)
x = conv2d(x, 512, name='conv4_3', **conv_args)
x = max_pool(x, name='maxpool4', **pool_args)
with tf.variable_scope('conv5'):
x = conv2d(x, 512, name='conv5_1', **conv_args)
x = conv2d(x, 512, name='conv5_2', **conv_args)
x = conv2d(x, 512, name='conv5_3', **conv_args)
x = max_pool(x, name='maxpool5', **pool_args)
x = conv2d(x,
4096,
name='fc6',
filter_size=(7, 7),
padding='VALID',
**conv_args)
x = dropout(x, drop_p=0.5, name='dropout6', **common_args)
x = conv2d(x, 4096, name='fc7', filter_size=(1, 1), **conv_args)
x = dropout(x, drop_p=0.5, name='dropout7', **common_args)
x = conv2d(x, 1000, name='fc8', filter_size=(1, 1), **logit_args)
if flexi_inputs:
logits = alias(x, name='logits', **common_args)
else:
logits = squeeze(x, axis=[1, 2], name='logits', **common_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def vgg_16(is_training, reuse,
num_classes=1000,
dropout_keep_prob=0.5,
spatial_squeeze=True,
name='vgg_16'):
"""Oxford Net VGG 16-Layers version D Example.
Note: All the fully_connected layers have been transformed to conv2d layers.
To use in classification mode, resize input to 224x224.
Args:
inputs: a tensor of size [batch_size, height, width, channels].
num_classes: number of predicted classes.
is_training: whether or not the model is being trained.
dropout_keep_prob: the probability that activations are kept in the dropout
layers during training.
spatial_squeeze: whether or not should squeeze the spatial dimensions of the
outputs. Useful to remove unnecessary dimensions for classification.
name: Optional name for the variables.
Returns:
the last op containing the log predictions and end_points dict.
"""
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True, activation=prelu, w_init=initz.he_normal(
scale=1), untie_biases=False, **common_args)
logit_args = make_args(
activation=None, w_init=initz.he_normal(scale=1), **common_args)
pred_args = make_args(
activation=prelu, w_init=initz.he_normal(scale=1), **common_args)
pool_args = make_args(padding='SAME', **common_args)
inputs = input((None, crop_size[1], crop_size[0], 3), **common_args)
with tf.variable_scope(name, 'vgg_16', [inputs]):
net = repeat(inputs, 2, conv2d,
64, filter_size=(3, 3), name='conv1', **conv_args)
net = max_pool(net, name='pool1', **pool_args)
net = repeat(net, 2, conv2d, 128, filter_size=(
3, 3), name='conv2', **conv_args)
net = max_pool(net, name='pool2', **pool_args)
net = repeat(net, 3, conv2d, 256, filter_size=(
3, 3), name='conv3', **conv_args)
net = max_pool(net, name='pool3', **pool_args)
net = repeat(net, 3, conv2d, 512, filter_size=(
3, 3), name='conv4', **conv_args)
net = max_pool(net, name='pool4', **pool_args)
net = repeat(net, 3, conv2d, 512, filter_size=(
3, 3), name='conv5', **conv_args)
net = max_pool(net, name='pool5', **pool_args)
# Use conv2d instead of fully_connected layers.
net = conv2d(net, 4096, filter_size=(7, 7), name='fc6', **conv_args)
net = dropout(net, drop_p=1 - dropout_keep_prob, is_training=is_training,
name='dropout6', **common_args)
net = conv2d(net, 4096, filter_size=(1, 1), name='fc7', **conv_args)
net = dropout(net, drop_p=1 - dropout_keep_prob, is_training=is_training,
name='dropout7', **common_args)
logits = conv2d(net, num_classes, filter_size=(1, 1),
activation=None,
name='logits', **logit_args)
# Convert end_points_collection into a end_point dict.
if spatial_squeeze:
logits = tf.squeeze(logits, [1, 2], name='logits/squeezed')
predictions = softmax(logits, name='predictions', **pred_args)
return end_points(is_training)
def model(inputs,
is_training,
reuse,
num_classes=5,
dropout_keep_prob=0.5,
spatial_squeeze=True,
name='alexnet_v2',
**kwargs):
"""AlexNet version 2.
Described in: http://arxiv.org/pdf/1404.5997v2.pdf
Parameters from:
github.com/akrizhevsky/cuda-convnet2/blob/master/layers/
layers-imagenet-1gpu.cfg
Note: All the fully_connected layers have been transformed to conv2d layers.
To use in classification mode, resize input to 224x224. To use in fully
convolutional mode, set spatial_squeeze to false.
The LRN layers have been removed and change the initializers from
random_normal_initializer to xavier_initializer.
Args:
inputs: a tensor of size [batch_size, height, width, channels].
num_classes: number of predicted classes.
is_training: whether or not the model is being trained.
dropout_keep_prob: the probability that activations are kept in the dropout
layers during training.
spatial_squeeze: whether or not should squeeze the spatial dimensions of the
outputs. Useful to remove unnecessary dimensions for classification.
name: Optional name for the variables.
Returns:
the last op containing the log predictions and end_points dict.
"""
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True,
activation=prelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
logit_args = make_args(activation=None,
w_init=initz.he_normal(scale=1),
**common_args)
pred_args = make_args(activation=prelu,
w_init=initz.he_normal(scale=1),
**common_args)
pool_args = make_args(padding='SAME', **common_args)
# inputs = input((None, crop_size[1], crop_size[0], 3), **common_args)
with tf.variable_scope(name, 'alexnet_v2', [inputs]):
net = conv2d(inputs,
64,
filter_size=(11, 11),
stride=(4, 4),
name='conv1',
**conv_args)
net = max_pool(net, stride=(2, 2), name='pool1', **pool_args)
net = conv2d(net, 192, filter_size=(5, 5), name='conv2', **conv_args)
net = max_pool(net, stride=(2, 2), name='pool2', **pool_args)
net = conv2d(net, 384, name='conv3', **conv_args)
net = conv2d(net, 384, name='conv4', **conv_args)
net = conv2d(net, 256, name='conv5', **conv_args)
net = max_pool(net, stride=(2, 2), name='pool5', **pool_args)
# Use conv2d instead of fully_connected layers.
net = conv2d(net, 4096, filter_size=(5, 5), name='fc6', **conv_args)
net = dropout(net,
drop_p=1 - dropout_keep_prob,
name='dropout6',
**common_args)
net = conv2d(net, 4096, filter_size=(1, 1), name='fc7', **conv_args)
net = dropout(net,
drop_p=1 - dropout_keep_prob,
name='dropout7',
**common_args)
net = global_avg_pool(net)
logits = fc(net, num_classes, name='logits', **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def __call__(self, inputs, state, scope='basiclstm'):
"""Long short-term memory cell (LSTM)."""
with tf.variable_scope(scope):
c, h = state
concat = _linear([inputs, h],
4 * self._num_units,
self.reuse,
trainable=self.trainable,
use_bias=False,
name=scope)
# i = input_gate, j = new_input, f = forget_gate, o = output_gate
try:
i, j, f, o = tf.split(1, 4, concat)
except Exception as e:
print('Upgrade to recent version >= r.12 %s' % str(e.message))
i, j, f, o = tf.split(concat, 4, 1)
# apply batch normalization to inner state and gates
if self.layer_norm is not None:
i = self.layer_norm(i,
self.reuse,
trainable=self.trainable,
**self.layer_norm_args)
j = self.layer_norm(j,
self.reuse,
trainable=self.trainable,
**self.layer_norm_args)
f = self.layer_norm(f,
self.reuse,
trainable=self.trainable,
**self.layer_norm_args)
o = self.layer_norm(o,
self.reuse,
trainable=self.trainable,
**self.layer_norm_args)
j = self._activation(j)
if (not isinstance(self._keep_prob, float)) or self._keep_prob < 1:
j = dropout(j, self._keep_prob, seed=self._dropout_seed)
new_c = (c * self._inner_activation(f + self._forget_bias) +
self._inner_activation(i) * self._activation(j))
if self._cell_clip is not None:
new_c = tf.clip_by_value(new_c, -self._cell_clip,
self._cell_clip)
if self.layer_norm is not None:
layer_norm_new_c = self.layer_norm(new_c,
self.reuse,
trainable=self.trainable,
**self.layer_norm_args)
new_h = self._activation(
layer_norm_new_c) * self._inner_activation(o)
else:
new_h = self._activation(new_c) * self._inner_activation(o)
new_state = core_rnn_cell.LSTMStateTuple(new_c, new_h)
new_h = _collect_named_outputs(self.outputs_collections,
scope + '_h', new_h)
new_state = _collect_named_outputs(self.outputs_collections,
scope + '_state', new_state)
return new_h, new_state
def discriminator(inputs, is_training, reuse, num_classes=11, batch_size=32):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True,
activation=lrelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
conv_args_1st = make_args(batch_norm=None,
activation=lrelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
logits_args = make_args(activation=None,
w_init=initz.he_normal(scale=1),
**common_args)
pool_args = make_args(padding='SAME', **common_args)
end_points = {}
x = inputs
end_points['inputs'] = x
x = dropout(x, drop_p=0.2, name="input_dropout1", **common_args)
x = conv2d(x,
96,
filter_size=(5, 5),
stride=(2, 2),
name="d_conv1_1",
**conv_args_1st)
end_points['d_conv1_1'] = x
x = conv2d(x, 96, name="d_conv1_2", **conv_args)
end_points['d_conv1_2'] = x
x = conv2d(x, 96, stride=(2, 2), name="d_conv1_3", **conv_args)
end_points['d_conv1_3'] = x
x = dropout(x, drop_p=0.2, name="dropout1", **common_args)
x = conv2d(x, 192, name="d_conv2_1", **conv_args)
end_points['d_conv2_1'] = x
x = conv2d(x, 192, name="d_conv2_2", **conv_args)
end_points['d_conv2_2'] = x
x = conv2d(x, 192, stride=(2, 2), name="d_conv2_3", **conv_args)
end_points['d_conv2_3'] = x
x = dropout(x, drop_p=0.2, name="dropout2", **common_args)
x = conv2d(x, 192, stride=(2, 2), name="d_conv3_1", **conv_args)
end_points['d_conv3_1'] = x
x = conv2d(x, 192, filter_size=(1, 1), name="d_conv4_1", **conv_args)
end_points['d_conv4_1'] = x
x = conv2d(x, 192, filter_size=(1, 1), name="d_conv4_2", **conv_args)
end_points['d_conv4_2'] = x
x = global_avg_pool(x, name="global_pool")
end_points['global_pool'] = x
logits = fully_connected(x, num_classes, name="d_logits", **logits_args)
end_points['logits'] = logits
end_points['predictions'] = softmax(logits,
name='predictions',
**common_args)
if is_training:
batch_size = 2 * batch_size
generated_class_logits = tf.squeeze(
tf.slice(logits, [0, num_classes - 1], [batch_size, 1]))
end_points['generated_class_logits'] = generated_class_logits
positive_class_logits = tf.slice(logits, [0, 0],
[batch_size, num_classes - 1])
end_points['positive_class_logits'] = positive_class_logits
max_ = tf.reduce_max(positive_class_logits, 1, keep_dims=True)
safe_pos_class_logits = positive_class_logits - max_
end_points['safe_pos_class_logits'] = safe_pos_class_logits
gan_logits = tf.log(
tf.reduce_sum(tf.exp(safe_pos_class_logits),
1)) + tf.squeeze(max_) - generated_class_logits
end_points['gan_logits'] = gan_logits
assert len(gan_logits.get_shape()) == 1
probs = tf.nn.sigmoid(gan_logits)
end_points['probs'] = probs
class_logits = tf.slice(logits, [0, 0], [batch_size / 2, num_classes])
end_points['class_logits'] = class_logits
D_on_data = tf.slice(probs, [0], [batch_size / 2])
end_points['D_on_data'] = D_on_data
D_on_data_logits = tf.slice(gan_logits, [0], [batch_size / 2])
end_points['D_on_data_logits'] = D_on_data_logits
D_on_G = tf.slice(probs, [batch_size / 2], [batch_size / 2])
end_points['D_on_G'] = D_on_G
D_on_G_logits = tf.slice(gan_logits, [batch_size / 2],
[batch_size / 2])
end_points['D_on_G_logits'] = D_on_G_logits
return end_points
else:
return end_points
def model(inputs, is_training, reuse, num_classes=21, batch_size=1):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True, activation=lrelu, w_init=initz.he_normal(
scale=1), untie_biases=False, **common_args)
upsample_args = make_args(
batch_norm=False, activation=lrelu, use_bias=False, **common_args)
logits_args = make_args(
activation=None, **common_args)
pool_args = make_args(padding='SAME', **common_args)
conv1_1 = conv2d(inputs, 64, name="vgg_19/conv1/conv1_1", **conv_args)
conv1_2 = conv2d(conv1_1, 64, name="vgg_19/conv1/conv1_2", **conv_args)
pool1 = max_pool(conv1_2, stride=2, name='pool1', **pool_args)
conv2_1 = conv2d(pool1, 128, name="vgg_19/conv2/conv2_1", **conv_args)
conv2_2 = conv2d(conv2_1, 128, name="vgg_19/conv2/conv2_2", **conv_args)
pool2 = max_pool(conv2_2, stride=2, name='pool2', **pool_args)
conv3_1 = conv2d(pool2, 256, name="vgg_19/conv3/conv3_1", **conv_args)
conv3_2 = conv2d(conv3_1, 256, name="vgg_19/conv3/conv3_2", **conv_args)
conv3_3 = conv2d(conv3_2, 256, name="vgg_19/conv3/conv3_3", **conv_args)
conv3_4 = conv2d(conv3_3, 256, name="vgg_19/conv3/conv3_4", **conv_args)
pool3 = max_pool(conv3_4, stride=2, name='pool3', **pool_args)
conv4_1 = conv2d(pool3, 512, name="vgg_19/conv4/conv4_1", **conv_args)
conv4_2 = conv2d(conv4_1, 512, name="vgg_19/conv4/conv4_2", **conv_args)
conv4_3 = conv2d(conv4_2, 512, name="vgg_19/conv4/conv4_3", **conv_args)
conv4_4 = conv2d(conv4_3, 512, name="vgg_19/conv4/conv4_4", **conv_args)
pool4 = max_pool(conv4_4, stride=2, name='pool4', **pool_args)
conv5_1 = conv2d(pool4, 512, name="vgg_19/conv5/conv5_1", **conv_args)
conv5_2 = conv2d(conv5_1, 512, name="vgg_19/conv5/conv5_2", **conv_args)
conv5_3 = conv2d(conv5_2, 512, name="vgg_19/conv5/conv5_3", **conv_args)
conv5_4 = conv2d(conv5_3, 512, name="vgg_19/conv5/conv5_4", **conv_args)
pool5 = max_pool(conv5_4, stride=2, name='pool5', **pool_args)
fc6 = conv2d(pool5, 4096, filter_size=(7, 7),
name="vgg_19/fc6", **conv_args)
fc6 = dropout(fc6, **common_args)
fc7 = conv2d(fc6, 4096, filter_size=(1, 1), name="vgg_19/fc7", **conv_args)
fc7 = dropout(fc7, **common_args)
score_fr = conv2d(fc7, num_classes, filter_size=(1, 1),
name="score_fr", **conv_args)
pred = tf.argmax(score_fr, axis=3)
pool4_shape = pool4.get_shape().as_list()
upscore2 = upsample2d(score_fr, [batch_size, pool4_shape[1], pool4_shape[2], num_classes], filter_size=(4, 4), stride=(2, 2),
name="deconv2d_1", w_init=initz.bilinear((4, 4, num_classes, num_classes)), **upsample_args)
score_pool4 = conv2d(pool4, num_classes, filter_size=(1, 1),
name="score_pool4", **conv_args)
fuse_pool4 = tf.add(upscore2, score_pool4)
pool3_shape = pool3.get_shape().as_list()
upscore4 = upsample2d(fuse_pool4, [batch_size, pool3_shape[1], pool3_shape[2], num_classes], filter_size=(4, 4), stride=(2, 2),
name="deconv2d_2", w_init=initz.bilinear((4, 4, num_classes, num_classes)), **upsample_args)
score_pool3 = conv2d(pool3, num_classes, filter_size=(1, 1),
name="score_pool3", **conv_args)
fuse_pool3 = tf.add(upscore4, score_pool3)
input_shape = inputs.get_shape().as_list()
upscore32 = upsample2d(fuse_pool3, [batch_size, input_shape[1], input_shape[2], num_classes], filter_size=(16, 16), stride=(8, 8),
name="deconv2d_3", w_init=initz.bilinear((16, 16, num_classes, num_classes)), **logits_args)
logits = register_to_collections(tf.reshape(
upscore32, shape=(-1, num_classes)), name='logits', **common_args)
pred_up = tf.argmax(upscore32, axis=3)
pred_up = register_to_collections(
pred_up, name='final_prediction_map', **common_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(inputs,
is_training,
reuse,
num_classes=5,
drop_prob=0.2,
name='InceptionResnetV2'):
common_args = common_layer_args(is_training, reuse)
rest_conv_params = make_args(use_bias=False,
batch_norm=batch_norm,
activation=relu,
**common_args)
conv_params_no_bias = make_args(use_bias=False,
batch_norm=batch_norm,
activation=relu,
**common_args)
conv_params = make_args(use_bias=True,
batch_norm=batch_norm,
activation=None,
**common_args)
rest_logit_params = make_args(activation=None, **common_args)
rest_pool_params = make_args(padding='SAME', **common_args)
rest_dropout_params = make_args(drop_p=drop_prob, **common_args)
# inputs = input((None, crop_size[1], crop_size[0], 3), **common_args)
with tf.variable_scope(name, 'InceptionResnetV2'):
net = conv2d(inputs,
32,
stride=(2, 2),
name='Conv2d_1a_3x3',
**conv_params_no_bias)
net = conv2d(net, 32, name='Conv2d_2a_3x3', **conv_params_no_bias)
# 112 x 112
net = conv2d(net, 64, name='Conv2d_2b_3x3', **rest_conv_params)
# 112 x 112
net = max_pool(net, name='MaxPool_3a_3x3', **rest_pool_params)
# 64 x 64
net = conv2d(net,
80,
filter_size=(1, 1),
name='Conv2d_3b_1x1',
**rest_conv_params)
# 64 x 64
net = conv2d(net, 192, name='Conv2d_4a_3x3', **rest_conv_params)
# 64 x 64
net = max_pool(net,
stride=(2, 2),
name='maxpool_5a_3x3',
**rest_pool_params)
# 32 x 32
with tf.variable_scope('Mixed_5b'):
with tf.variable_scope('Branch_0'):
tower_conv = conv2d(net,
96,
filter_size=(1, 1),
name='Conv2d_1x1',
**rest_conv_params)
with tf.variable_scope('Branch_1'):
tower_conv1_0 = conv2d(net,
48,
filter_size=(1, 1),
name='Conv2d_0a_1x1',
**rest_conv_params)
tower_conv1_1 = conv2d(tower_conv1_0,
64,
filter_size=(5, 5),
name='Conv2d_0b_5x5',
**rest_conv_params)
with tf.variable_scope('Branch_2'):
tower_conv2_0 = conv2d(net,
64,
filter_size=(1, 1),
name='Conv2d_0a_1x1',
**rest_conv_params)
tower_conv2_1 = conv2d(tower_conv2_0,
96,
name='Conv2d_0b_3x3',
**rest_conv_params)
tower_conv2_2 = conv2d(tower_conv2_1,
96,
name='Conv2d_0c_3x3',
**rest_conv_params)
with tf.variable_scope('Branch_3'):
tower_pool = avg_pool_2d(net,
stride=(1, 1),
name='avgpool_0a_3x3',
**rest_pool_params)
tower_pool_1 = conv2d(tower_pool,
64,
filter_size=(1, 1),
name='Conv2d_0b_1x1',
**rest_conv_params)
net = tf.concat(
[tower_conv, tower_conv1_1, tower_conv2_2, tower_pool_1], 3)
with tf.variable_scope('Repeat'):
for i in range(1, 11):
net = block35(net,
name='block35_' + str(i),
scale=0.17,
**conv_params_no_bias)
# 32 x 32
with tf.variable_scope('Mixed_6a'):
with tf.variable_scope('Branch_0'):
tower_conv = conv2d(net,
384,
stride=(2, 2),
name='Conv2d_1a_3x3',
**rest_conv_params)
with tf.variable_scope('Branch_1'):
tower_conv1_0 = conv2d(net,
256,
filter_size=(1, 1),
name='Conv2d_0a_1x1',
**rest_conv_params)
tower_conv1_1 = conv2d(tower_conv1_0,
256,
name='Conv2d_0b_3x3',
**rest_conv_params)
tower_conv1_2 = conv2d(tower_conv1_1,
384,
stride=(2, 2),
name='Conv2d_1a_3x3',
**rest_conv_params)
with tf.variable_scope('Branch_2'):
tower_pool = max_pool(net,
name='maxpool_1a_3x3',
**rest_pool_params)
net = tf.concat([tower_conv, tower_conv1_2, tower_pool], 3)
with tf.variable_scope('Repeat_1'):
for i in range(1, 21):
net = block17(net,
name='block17_' + str(i),
scale=0.10,
**conv_params_no_bias)
with tf.variable_scope('Mixed_7a'):
with tf.variable_scope('Branch_0'):
tower_conv = conv2d(net,
256,
filter_size=(1, 1),
name='Conv2d_0a_1x1',
**rest_conv_params)
tower_conv_1 = conv2d(tower_conv,
384,
stride=(2, 2),
name='Conv2d_1a_3x3',
**rest_conv_params)
with tf.variable_scope('Branch_1'):
tower_conv1 = conv2d(net,
256,
filter_size=(1, 1),
name='Conv2d_0a_1x1',
**rest_conv_params)
tower_conv1_1 = conv2d(tower_conv1,
288,
stride=(2, 2),
name='Conv2d_1a_3x3',
**rest_conv_params)
with tf.variable_scope('Branch_2'):
tower_conv2 = conv2d(net,
256,
filter_size=(1, 1),
name='Conv2d_0a_1x1',
**rest_conv_params)
tower_conv2_1 = conv2d(tower_conv2,
288,
name='Conv2d_0b_3x3',
**rest_conv_params)
tower_conv2_2 = conv2d(tower_conv2_1,
320,
stride=(2, 2),
name='Conv2d_1a_3x3',
**rest_conv_params)
with tf.variable_scope('Branch_3'):
tower_pool = max_pool(net,
name='maxpool_1a_3x3',
**rest_pool_params)
net = tf.concat(
[tower_conv_1, tower_conv1_1, tower_conv2_2, tower_pool], 3)
# 8 x 8
with tf.variable_scope('Repeat_2'):
for i in range(1, 10):
net = block8(net,
name='block8_' + str(i),
scale=0.20,
**conv_params_no_bias)
net = block8(net, name='Block8', **conv_params_no_bias)
net = conv2d(net,
1536,
filter_size=(1, 1),
name='Conv2d_7b_1x1',
**rest_conv_params)
with tf.variable_scope('Logits'):
net = global_avg_pool(net, name='avgpool_1a_8x8')
net = dropout(net, name='dropout', **rest_dropout_params)
logits = fully_connected(net,
num_classes,
name='Logits',
**rest_logit_params)
predictions = softmax(logits, name='Predictions', **common_args)
return end_points(is_training)
