def parse_conv_params(params):
nonlinearity = 'relu'
if len(params) == 4:
params, nonlinearity = params[:-1], params[-1]
nkernels, stride, num_outputs = [parse_math(p) for p in params]
return nkernels, stride, num_outputs, nonlinearity
def parse_conv_params(params):
nonlinearity = 'relu'
if len(params) == 4:
params, nonlinearity = params[:-1], params[-1]
nkernels, stride, num_outputs = [parse_math(p) for p in params]
return nkernels, stride, num_outputs, nonlinearity
def run_network(inpt,
string,
is_training,
debug=False,
strip_batchnorm_from_last_layer=False):
maybe_fc_batch_norm = layers.batch_norm
maybe_conv_batch_norm = conv_batch_norm
if debug:
print("%s architecture" % (tf.get_variable_scope().name, ))
layer_idx = 0
out = inpt
layer_strs = string.split(",")
for i, layer in enumerate(layer_strs):
if i + 1 == len(layer_strs) and strip_batchnorm_from_last_layer:
maybe_fc_batch_norm = None
maybe_conv_batch_norm = None
if layer.startswith("conv:"):
nkernels, stride, num_outputs, nonlinearity_str = parse_conv_params(
layer[len("conv:"):].split(":"))
nonlinearity = NONLINEARITY_NAME_TO_F[nonlinearity_str]
out = layers.convolution2d(
out,
num_outputs=num_outputs,
kernel_size=nkernels,
stride=stride,
normalizer_params={"is_training": is_training},
normalizer_fn=maybe_conv_batch_norm,
activation_fn=nonlinearity,
scope='layer_%d' % (layer_idx, ))
layer_idx += 1
if debug:
print(
"Convolution with nkernels=%d, stride=%d, num_outputs=%d followed by %s"
% (nkernels, stride, num_outputs, nonlinearity_str))
elif layer.startswith("deconv:"):
nkernels, stride, num_outputs, nonlinearity_str = parse_conv_params(
layer[len("deconv:"):].split(":"))
nonlinearity = NONLINEARITY_NAME_TO_F[nonlinearity_str]
out = layers.convolution2d_transpose(
out,
num_outputs=num_outputs,
kernel_size=nkernels,
stride=stride,
activation_fn=nonlinearity,
normalizer_fn=maybe_conv_batch_norm,
normalizer_params={"is_training": is_training},
scope='layer_%d' % (layer_idx, ))
layer_idx += 1
if debug:
print(
"Deconvolution with nkernels=%d, stride=%d, num_outputs=%d followed by %s"
% (nkernels, stride, num_outputs, nonlinearity_str))
elif layer.startswith("fc:"):
params = layer[len("fc:"):].split(":")
nonlinearity_str = 'relu'
if len(params) == 2:
params, nonlinearity_str = params[:-1], params[-1]
num_outputs = parse_math(params[0])
nonlinearity = NONLINEARITY_NAME_TO_F[nonlinearity_str]
out = layers.fully_connected(out,
num_outputs=num_outputs,
activation_fn=nonlinearity,
normalizer_fn=maybe_fc_batch_norm,
normalizer_params={
"is_training": is_training,
"updates_collections": None
},
scope='layer_%d' % (layer_idx, ))
layer_idx += 1
if debug:
print("Fully connected with num_outputs=%d followed by %s" %
(num_outputs, nonlinearity_str))
elif layer.startswith("reshape:"):
params = layer[len("reshape:"):].split(":")
dims = [parse_math(dim) for dim in params]
out = tf.reshape(out, [-1] + dims)
if debug:
print("Reshape to %r" % (dims, ))
else:
raise ValueError("Could not parse layer description: %r" %
(layer, ))
if debug:
print("")
return out
def run_network(inpt, string, is_training, debug=False, strip_batchnorm_from_last_layer=False):
maybe_fc_batch_norm = layers.batch_norm
maybe_conv_batch_norm = conv_batch_norm
if debug:
print ("%s architecture" % (tf.get_variable_scope().name,))
layer_idx = 0
out = inpt
layer_strs = string.split(",")
for i, layer in enumerate(layer_strs):
if i + 1 == len(layer_strs) and strip_batchnorm_from_last_layer:
maybe_fc_batch_norm = None
maybe_conv_batch_norm = None
if layer.startswith("conv:"):
nkernels, stride, num_outputs, nonlinearity_str = parse_conv_params(layer[len("conv:"):].split(":"))
nonlinearity = NONLINEARITY_NAME_TO_F[nonlinearity_str]
out = layers.convolution2d(
out,
num_outputs=num_outputs,
kernel_size=nkernels,
stride=stride,
normalizer_params={"is_training": is_training},
normalizer_fn=maybe_conv_batch_norm,
activation_fn=nonlinearity,
scope='layer_%d' % (layer_idx,)
)
layer_idx += 1
if debug:
print ("Convolution with nkernels=%d, stride=%d, num_outputs=%d followed by %s" %
(nkernels, stride, num_outputs, nonlinearity_str))
elif layer.startswith("deconv:"):
nkernels, stride, num_outputs, nonlinearity_str = parse_conv_params(layer[len("deconv:"):].split(":"))
nonlinearity = NONLINEARITY_NAME_TO_F[nonlinearity_str]
out = layers.convolution2d_transpose(
out,
num_outputs=num_outputs,
kernel_size=nkernels,
stride=stride,
activation_fn=nonlinearity,
normalizer_fn=maybe_conv_batch_norm,
normalizer_params={"is_training": is_training},
scope='layer_%d' % (layer_idx,)
)
layer_idx += 1
if debug:
print ("Deconvolution with nkernels=%d, stride=%d, num_outputs=%d followed by %s" %
(nkernels, stride, num_outputs, nonlinearity_str))
elif layer.startswith("fc:"):
params = layer[len("fc:"):].split(":")
nonlinearity_str = 'relu'
if len(params) == 2:
params, nonlinearity_str = params[:-1], params[-1]
num_outputs = parse_math(params[0])
nonlinearity = NONLINEARITY_NAME_TO_F[nonlinearity_str]
out = layers.fully_connected(
out,
num_outputs=num_outputs,
activation_fn=nonlinearity,
normalizer_fn=maybe_fc_batch_norm,
normalizer_params={"is_training": is_training, "updates_collections": None},
scope='layer_%d' % (layer_idx,)
)
layer_idx += 1
if debug:
print ("Fully connected with num_outputs=%d followed by %s" %
(num_outputs, nonlinearity_str))
elif layer.startswith("reshape:"):
params = layer[len("reshape:"):].split(":")
dims = [parse_math(dim) for dim in params]
out = tf.reshape(out, [-1] + dims)
if debug:
print("Reshape to %r" % (dims,))
else:
raise ValueError("Could not parse layer description: %r" % (layer,))
if debug:
print("")
return out
def run_network(inpt,
string,
is_training,
use_batch_norm,
debug=False,
strip_batchnorm_from_last_layer=False):
# 下面两步没有看懂，？？？？？？？？？
# 如果use_batch_norm时，下面的两个都有效
# layers.bacth_norm是对输出的全连接层进行批归一化的
# 而conv_batch_norm是对卷积层进行批归一化的
maybe_fc_batch_norm = layers.batch_norm if use_batch_norm else None
maybe_conv_batch_norm = conv_batch_norm if use_batch_norm else None
if debug:
print("%s architecture" % (tf.get_variable_scope().name, ))
layer_idx = 0
out = inpt
layer_strs = string.split(",")
for i, layer in enumerate(layer_strs):
# 最后一层跳过batch_norm
if i + 1 == len(layer_strs) and strip_batchnorm_from_last_layer:
maybe_fc_batch_norm = None
maybe_conv_batch_norm = None
# 如果为卷积层，进行卷积操作
if layer.startswith("conv:"):
nkernels, stride, num_outputs, nonlinearity_str = parse_conv_params(
layer[len("conv:"):].split(":"))
nonlinearity = NONLINEARITY_NAME_TO_F[nonlinearity_str]
out = layers.convolution2d(
out,
num_outputs=num_outputs,
kernel_size=nkernels,
stride=stride,
normalizer_params={"is_training": is_training},
normalizer_fn=maybe_conv_batch_norm,
activation_fn=nonlinearity,
scope='layer_%d' % (layer_idx, ))
layer_idx += 1
if debug:
print(
"Convolution with nkernels=%d, stride=%d, num_outputs=%d followed by %s"
% (nkernels, stride, num_outputs, nonlinearity_str))
# 如果为反卷积层，进行反卷积操作
#这个操作的具体过程可以查看http://blog.csdn.net/fate_fjh/article/details/52882134说得非常好
#大致的过程就是如果输入为N1*N1，卷积核为N2*N2，步长为K，则输出为（N1-1）*K+N2
elif layer.startswith("deconv:"):
nkernels, stride, num_outputs, nonlinearity_str = parse_conv_params(
layer[len("deconv:"):].split(":"))
nonlinearity = NONLINEARITY_NAME_TO_F[nonlinearity_str]
out = layers.convolution2d_transpose(
out,
num_outputs=num_outputs,
kernel_size=nkernels,
stride=stride,
activation_fn=nonlinearity,
normalizer_fn=maybe_conv_batch_norm,
normalizer_params={"is_training": is_training},
scope='layer_%d' % (layer_idx, ))
layer_idx += 1
if debug:
print(
"Deconvolution with nkernels=%d, stride=%d, num_outputs=%d followed by %s"
% (nkernels, stride, num_outputs, nonlinearity_str))
# 如果为全连接层，进行全连接操作
# 这里的全连接是tensorflow自己集成的，可以看一下内部的说明：大致的意思是
# 如果使用了batch_norm的话，就没有bias，并且默认的激活函数是relu
elif layer.startswith("fc:"):
params = layer[len("fc:"):].split(":")
nonlinearity_str = 'relu'
if len(params) == 2:
params, nonlinearity_str = params[:-1], params[-1]
num_outputs = parse_math(params[0])
nonlinearity = NONLINEARITY_NAME_TO_F[nonlinearity_str]
out = layers.fully_connected(out,
num_outputs=num_outputs,
activation_fn=nonlinearity,
normalizer_fn=maybe_fc_batch_norm,
normalizer_params={
"is_training": is_training,
"updates_collections": None
},
scope='layer_%d' % (layer_idx, ))
layer_idx += 1
if debug:
print("Fully connected with num_outputs=%d followed by %s" %
(num_outputs, nonlinearity_str))
# 如果为重构层，进行重构操作
elif layer.startswith("reshape:"):
params = layer[len("reshape:"):].split(":")
dims = [parse_math(dim) for dim in params]
out = tf.reshape(out, [-1] + dims)
if debug:
print("Reshape to %r" % (dims, ))
else:
raise ValueError("Could not parse layer description: %r" %
(layer, ))
if debug:
print("")
return out