def resnet50(images,
cfg,
optimizer,
trainable=True,
need_transpose=False,
model_weight=True,
bn=True):
if need_transpose:
images = flow.transpose(images, name="transpose", perm=[0, 3, 1, 2])
global NAME_NUMBER
NAME_NUMBER = 0
stem = resnet_stem(images, bn, model_weight, optimizer)
body = resnet_conv_x_body(stem, cfg, bn, model_weight, optimizer,
lambda x: x)
pool5 = flow.nn.avg_pool2d(
body,
ksize=7,
strides=1,
padding="VALID",
data_format="NCHW",
name="pool5",
)
pool5 = flow.reshape(pool5, [pool5.shape[0], -1])
dense0 = flow.layers.dense(
inputs=pool5,
units=cfg[4],
use_bias=True,
kernel_initializer=flow.xavier_uniform_initializer(),
bias_initializer=flow.zeros_initializer(),
trainable=trainable,
name="dense0",
)
def getTypeAndShape(inputs, units):
in_shape = inputs.shape
in_num_axes = len(in_shape)
inputs = (flow.reshape(inputs,
(-1,
in_shape[-1])) if in_num_axes > 2 else inputs)
shape = (units, inputs.shape[1])
dtype = inputs.dtype
return shape, dtype
#添加dense层的Model weight
if model_weight == True:
shape_list = []
dtype_list = []
shape_weight, dtype = getTypeAndShape(pool5, cfg[4])
shape_list.append(shape_weight)
dtype_list.append(dtype)
modelWeight.addDense(dtype_old=dtype_list,
shape=shape_list,
optimizer=optimizer,
dense_num=1)
return dense0
def dnn_2(input_tensor, cfg, optimizer, model_weight=True, trainable=True):
input_tensor = flow.reshape(input_tensor, [input_tensor.shape[0], -1])
dense0 = flow.layers.dense(
inputs=input_tensor,
units=cfg[0],
activation=flow.nn.relu,
use_bias=True,
kernel_initializer=flow.random_normal_initializer(mean=0, stddev=0.1),
trainable=trainable,
name="dense0")
dense1 = flow.layers.dense(
inputs=dense0,
units=cfg[1],
activation=None,
use_bias=True,
kernel_initializer=flow.random_normal_initializer(mean=0, stddev=0.1),
trainable=trainable,
name="dense1")
def getTypeAndShape(inputs, units):
in_shape = inputs.shape
in_num_axes = len(in_shape)
inputs = (flow.reshape(inputs,
(-1,
in_shape[-1])) if in_num_axes > 2 else inputs)
shape = (units, inputs.shape[1])
dtype = inputs.dtype
return shape, dtype
if model_weight == True:
shape_list = []
dtype_list = []
shape_weight, dtype = getTypeAndShape(input_tensor, cfg[0])
shape_list.append(shape_weight)
dtype_list.append(dtype)
shape_weight, dtype = getTypeAndShape(dense0, cfg[1])
shape_list.append(shape_weight)
dtype_list.append(dtype)
modelWeight.addDense(dtype_old=dtype_list,
shape=shape_list,
optimizer=optimizer,
dense_num=2)
return dense1
def vgg(images,
cfg,
optimizer,
trainable=True,
need_transpose=False,
training=True,
wd=1.0 / 32768,
model_weight=True,
bn=True):
if need_transpose:
images = flow.transpose(images, name="transpose", perm=[0, 3, 1, 2])
conv1 = _conv_block(images, 0, cfg, 2, optimizer, model_weight, bn=bn)
pool1 = flow.nn.max_pool2d(conv1[-1], 2, 2, "VALID", "NCHW", name="pool1")
conv2 = _conv_block(pool1, 2, cfg, 2, optimizer, model_weight, bn=bn)
pool2 = flow.nn.max_pool2d(conv2[-1], 2, 2, "VALID", "NCHW", name="pool2")
conv3 = _conv_block(pool2, 4, cfg, 3, optimizer, model_weight, bn=bn)
pool3 = flow.nn.max_pool2d(conv3[-1], 2, 2, "VALID", "NCHW", name="pool3")
conv4 = _conv_block(pool3, 7, cfg, 3, optimizer, model_weight, bn=bn)
pool4 = flow.nn.max_pool2d(conv4[-1], 2, 2, "VALID", "NCHW", name="pool4")
conv5 = _conv_block(pool4, 10, cfg, 3, optimizer, model_weight, bn=bn)
pool5 = flow.nn.max_pool2d(conv5[-1], 2, 2, "VALID", "NCHW", name="pool5")
pool5 = flow.reshape(pool5, [pool5.shape[0], -1])
dense0 = flow.layers.dense(
inputs=pool5,
units=cfg[13],
activation=flow.nn.relu,
use_bias=True,
kernel_initializer=flow.random_normal_initializer(mean=0, stddev=0.1),
trainable=trainable,
name="dense0",
)
dense1 = flow.layers.dense(
inputs=dense0,
units=cfg[14],
activation=flow.nn.relu,
use_bias=True,
kernel_initializer=flow.random_normal_initializer(mean=0, stddev=0.1),
trainable=trainable,
name="dense1",
)
dense2 = flow.layers.dense(
inputs=dense1,
units=cfg[15],
use_bias=True,
kernel_initializer=flow.random_normal_initializer(mean=0, stddev=0.1),
trainable=trainable,
name="dense2",
)
# flow.watch(fc8)
def getTypeAndShape(inputs, units):
in_shape = inputs.shape
in_num_axes = len(in_shape)
inputs = (flow.reshape(inputs,
(-1,
in_shape[-1])) if in_num_axes > 2 else inputs)
shape = (units, inputs.shape[1])
dtype = inputs.dtype
return shape, dtype
if model_weight == True:
shape_list = []
dtype_list = []
shape_weight, dtype = getTypeAndShape(pool5, cfg[13])
shape_list.append(shape_weight)
dtype_list.append(dtype)
shape_weight, dtype = getTypeAndShape(dense0, cfg[14])
shape_list.append(shape_weight)
dtype_list.append(dtype)
shape_weight, dtype = getTypeAndShape(dense1, cfg[15])
shape_list.append(shape_weight)
dtype_list.append(dtype)
modelWeight.addDense(dtype_old=dtype_list,
shape=shape_list,
optimizer=optimizer,
dense_num=3)
# shape_weight,dtype=getTypeAndShape(pool5,4096)
# modelWeight.add('fc1'+'-weight',dtype,shape_weight)
# modelWeight.add('fc1'+'-bias',dtype,(4096,))
# shape_weight,dtype=getTypeAndShape(fc6,4096)
# modelWeight.add('fc2'+'-weight',dtype,shape_weight)
# modelWeight.add('fc2'+'-bias',dtype,(4096,))
# shape_weight,dtype=getTypeAndShape(fc7,1000)
# modelWeight.add('fc_final'+'-weight',dtype,shape_weight)
# modelWeight.add('fc_final'+'-bias',dtype,(1000,))
return dense2
def lenet(images, cfg, optimizer, trainable=True, need_transpose=False,
training=True, wd=1.0/32768, model_weight=True, bn=True):
if need_transpose:
images = flow.transpose(images, name="transpose", perm=[0, 3, 1, 2])
conv0 = conv2d_layer(name="conv0", input=images, filters=cfg[0], kernel_size=5,
padding="VALID", strides=1, bn=bn)
pool0 = flow.nn.max_pool2d(conv0, 2, 2, "VALID", "NCHW", name="pool0")
conv1 = conv2d_layer(name="conv1", input=pool0, filters=cfg[1], kernel_size=5,
padding="VALID", strides=1, bn=bn)
pool1 = flow.nn.max_pool2d(conv1, 2, 2, "VALID", "NCHW", name="pool1")
pool1 = flow.reshape(pool1, [pool1.shape[0], -1])
# pool1 = flow.reshape(images, [images.shape[0], -1])
dense0 = flow.layers.dense(
inputs=pool1,
units=cfg[2],
activation=flow.nn.relu,
use_bias=True,
kernel_initializer=flow.random_normal_initializer(mean=0, stddev=0.1),
trainable=trainable,
name="dense0")
dense1 = flow.layers.dense(
inputs=dense0,
units=cfg[3],
activation=flow.nn.relu,
use_bias=True,
kernel_initializer=flow.random_normal_initializer(mean=0, stddev=0.1),
trainable=trainable,
name="dense1")
dense2 = flow.layers.dense(
inputs=dense1,
units=cfg[4],
use_bias=True,
kernel_initializer=flow.random_normal_initializer(mean=0, stddev=0.1),
trainable=trainable,
name="dense2")
# flow.watch(fc8)
def getTypeAndShape(inputs,units):
in_shape = inputs.shape
in_num_axes = len(in_shape)
inputs = (flow.reshape(inputs, (-1, in_shape[-1])) if in_num_axes > 2 else inputs)
shape=(units, inputs.shape[1])
dtype=inputs.dtype
return shape,dtype
if model_weight == True:
modelWeight.addConv(index=0, dtype=conv0.dtype,
shape1=(cfg[0], images.shape[1], 5, 5), shape2=(cfg[0],),
optimizer=optimizer)
modelWeight.addConv(index=1, dtype=conv1.dtype,
shape1=(cfg[1], conv0.shape[1], 5, 5), shape2=(cfg[1],),
optimizer=optimizer)
shape_list = []
dtype_list = []
shape_weight, dtype = getTypeAndShape(pool1, cfg[2])
shape_list.append(shape_weight)
dtype_list.append(dtype)
shape_weight, dtype = getTypeAndShape(dense0, cfg[3])
shape_list.append(shape_weight)
dtype_list.append(dtype)
shape_weight, dtype = getTypeAndShape(dense1, cfg[4])
shape_list.append(shape_weight)
dtype_list.append(dtype)
modelWeight.addDense(dtype_old=dtype_list, shape=shape_list,
optimizer=optimizer, dense_num=3)
return dense2