def conv_act_layer(from_layer, name, num_filter, kernel=(1,1), pad=(0,0), \
stride=(1,1), act_type="relu", use_batchnorm=False):
"""
wrapper for a small Convolution group
Parameters:
----------
from_layer : mx.symbol
continue on which layer
name : str
base name of the new layers
num_filter : int
how many filters to use in Convolution layer
kernel : tuple (int, int)
kernel size (h, w)
pad : tuple (int, int)
padding size (h, w)
stride : tuple (int, int)
stride size (h, w)
act_type : str
activation type, can be relu...
use_batchnorm : bool
whether to use batch normalization
Returns:
----------
(conv, relu) mx.Symbols
"""
assert not use_batchnorm, "batchnorm not yet supported"
bias = mx.symbol.Variable(name="conv{}_bias".format(name),
init=mx.init.Constant(0.0), attr={'__lr_mult__': '2.0'})
conv = mx.symbol.Convolution(data=from_layer, bias=bias, kernel=kernel, pad=pad, \
stride=stride, num_filter=num_filter, name="conv{}".format(name))
relu = mx.symbol.Activation(data=conv, act_type=act_type, \
name="{}{}".format(act_type, name))
if use_batchnorm:
relu = mx.symbol.BatchNorm(data=relu, name="bn{}".format(name))
return conv, relu
python类symbol()的实例源码
def conv_act_layer(from_layer, name, num_filter, kernel=(1,1), pad=(0,0), \
stride=(1,1), act_type="relu", use_batchnorm=False):
"""
wrapper for a small Convolution group
Parameters:
----------
from_layer : mx.symbol
continue on which layer
name : str
base name of the new layers
num_filter : int
how many filters to use in Convolution layer
kernel : tuple (int, int)
kernel size (h, w)
pad : tuple (int, int)
padding size (h, w)
stride : tuple (int, int)
stride size (h, w)
act_type : str
activation type, can be relu...
use_batchnorm : bool
whether to use batch normalization
Returns:
----------
(conv, relu) mx.Symbols
"""
bias = mx.symbol.Variable(name="{}_conv_bias".format(name),
init=mx.init.Constant(0.0), attr={'__lr_mult__': '2.0'})
conv = mx.symbol.Convolution(data=from_layer, kernel=kernel, pad=pad, \
stride=stride, num_filter=num_filter, name="{}_conv".format(name), bias=bias)
if use_batchnorm:
conv = mx.symbol.BatchNorm(data=conv, name="{}_bn".format(name))
relu = mx.symbol.Activation(data=conv, act_type=act_type, \
name="{}_{}".format(name, act_type))
return relu
def legacy_conv_act_layer(from_layer, name, num_filter, kernel=(1,1), pad=(0,0), \
stride=(1,1), act_type="relu", use_batchnorm=False):
"""
wrapper for a small Convolution group
Parameters:
----------
from_layer : mx.symbol
continue on which layer
name : str
base name of the new layers
num_filter : int
how many filters to use in Convolution layer
kernel : tuple (int, int)
kernel size (h, w)
pad : tuple (int, int)
padding size (h, w)
stride : tuple (int, int)
stride size (h, w)
act_type : str
activation type, can be relu...
use_batchnorm : bool
whether to use batch normalization
Returns:
----------
(conv, relu) mx.Symbols
"""
assert not use_batchnorm, "batchnorm not yet supported"
bias = mx.symbol.Variable(name="conv{}_bias".format(name),
init=mx.init.Constant(0.0), attr={'__lr_mult__': '2.0'})
conv = mx.symbol.Convolution(data=from_layer, bias=bias, kernel=kernel, pad=pad, \
stride=stride, num_filter=num_filter, name="conv{}".format(name))
relu = mx.symbol.Activation(data=conv, act_type=act_type, \
name="{}{}".format(act_type, name))
if use_batchnorm:
relu = mx.symbol.BatchNorm(data=relu, name="bn{}".format(name))
return conv, relu
def conv_act_layer(from_layer, name, num_filter, kernel=(1,1), pad=(0,0), \
stride=(1,1), act_type="relu", use_batchnorm=False):
"""
wrapper for a small Convolution group
Parameters:
----------
from_layer : mx.symbol
continue on which layer
name : str
base name of the new layers
num_filter : int
how many filters to use in Convolution layer
kernel : tuple (int, int)
kernel size (h, w)
pad : tuple (int, int)
padding size (h, w)
stride : tuple (int, int)
stride size (h, w)
act_type : str
activation type, can be relu...
use_batchnorm : bool
whether to use batch normalization
Returns:
----------
(conv, relu) mx.Symbols
"""
assert not use_batchnorm, "batchnorm not yet supported"
conv = mx.symbol.Convolution(data=from_layer, kernel=kernel, pad=pad, \
stride=stride, num_filter=num_filter, name="conv{}".format(name))
relu = mx.symbol.Activation(data=conv, act_type=act_type, \
name="{}{}".format(act_type, name))
if use_batchnorm:
relu = mx.symbol.BatchNorm(data=relu, name="bn{}".format(name))
return conv, relu
def sym_factory(node, data):
name = node['name']
params = {}
if 'param' in node:
for k, v in node['param'].items():
try:
params[k] = ast.literal_eval(v)
except ValueError, e:
params[k] = v
return getattr(mx.symbol, node['op'])(data=data, name=name, **params)
def conv_act_layer(from_layer, name, num_filter, kernel=(1,1), pad=(0,0), \
stride=(1,1), act_type="relu", use_batchnorm=False):
"""
wrapper for a small Convolution group
Parameters:
----------
from_layer : mx.symbol
continue on which layer
name : str
base name of the new layers
num_filter : int
how many filters to use in Convolution layer
kernel : tuple (int, int)
kernel size (h, w)
pad : tuple (int, int)
padding size (h, w)
stride : tuple (int, int)
stride size (h, w)
act_type : str
activation type, can be relu...
use_batchnorm : bool
whether to use batch normalization
Returns:
----------
(conv, relu) mx.Symbols
"""
conv = mx.symbol.Convolution(data=from_layer, kernel=kernel, pad=pad, \
stride=stride, num_filter=num_filter, name="{}_conv".format(name))
if use_batchnorm:
conv = mx.symbol.BatchNorm(data=conv, name="{}_bn".format(name))
relu = mx.symbol.Activation(data=conv, act_type=act_type, \
name="{}_{}".format(name, act_type))
return relu
def legacy_conv_act_layer(from_layer, name, num_filter, kernel=(1,1), pad=(0,0), \
stride=(1,1), act_type="relu", use_batchnorm=False):
"""
wrapper for a small Convolution group
Parameters:
----------
from_layer : mx.symbol
continue on which layer
name : str
base name of the new layers
num_filter : int
how many filters to use in Convolution layer
kernel : tuple (int, int)
kernel size (h, w)
pad : tuple (int, int)
padding size (h, w)
stride : tuple (int, int)
stride size (h, w)
act_type : str
activation type, can be relu...
use_batchnorm : bool
whether to use batch normalization
Returns:
----------
(conv, relu) mx.Symbols
"""
assert not use_batchnorm, "batchnorm not yet supported"
bias = mx.symbol.Variable(name="conv{}_bias".format(name),
init=mx.init.Constant(0.0), attr={'__lr_mult__': '2.0'})
conv = mx.symbol.Convolution(data=from_layer, bias=bias, kernel=kernel, pad=pad, \
stride=stride, num_filter=num_filter, name="conv{}".format(name))
relu = mx.symbol.Activation(data=conv, act_type=act_type, \
name="{}{}".format(act_type, name))
if use_batchnorm:
relu = mx.symbol.BatchNorm(data=relu, name="bn{}".format(name))
return conv, relu
def get_symbol(num_classes=20, nms_thresh=0.5, force_nms=False, **kwargs):
body = resnet.get_symbol(num_classes, 50, '3,224,224')
conv1 = body.get_internals()['_plus12_output']
conv2 = body.get_internals()['_plus15_output']
# anchors
anchors = [1.3221, 1.73145, 3.19275, 4.00944, 5.05587, 8.09892, 9.47112, 4.84053, 11.2364, 10.0071]
num_anchor = len(anchors) // 2
# extra layers
conv7_1 = conv_act_layer(conv2, 'conv7_1', 1024, kernel=(3, 3), pad=(1, 1),
act_type='leaky')
conv7_2 = conv_act_layer(conv7_1, 'conv7_2', 1024, kernel=(3, 3), pad=(1, 1),
act_type='leaky')
# re-organize
conv5_6 = mx.sym.stack_neighbor(data=conv1, kernel=(2, 2), name='stack_downsample')
concat = mx.sym.Concat(*[conv5_6, conv7_2], dim=1)
# concat = conv7_2
conv8_1 = conv_act_layer(concat, 'conv8_1', 1024, kernel=(3, 3), pad=(1, 1),
act_type='leaky')
pred = mx.symbol.Convolution(data=conv8_1, name='conv_pred', kernel=(1, 1),
num_filter=num_anchor * (num_classes + 4 + 1))
out = mx.contrib.symbol.YoloOutput(data=pred, num_class=num_classes,
num_anchor=num_anchor, object_grad_scale=5.0, background_grad_scale=1.0,
coord_grad_scale=1.0, class_grad_scale=1.0, anchors=anchors,
nms_topk=400, warmup_samples=12800, name='yolo_output')
return out
def conv_act_layer(from_layer, name, num_filter, kernel=(1,1), pad=(0,0), \
stride=(1,1), act_type="relu", use_batchnorm=False):
"""
wrapper for a small Convolution group
Parameters:
----------
from_layer : mx.symbol
continue on which layer
name : str
base name of the new layers
num_filter : int
how many filters to use in Convolution layer
kernel : tuple (int, int)
kernel size (h, w)
pad : tuple (int, int)
padding size (h, w)
stride : tuple (int, int)
stride size (h, w)
act_type : str
activation type, can be relu...
use_batchnorm : bool
whether to use batch normalization
Returns:
----------
(conv, relu) mx.Symbols
"""
conv = mx.symbol.Convolution(data=from_layer, kernel=kernel, pad=pad, \
stride=stride, num_filter=num_filter, name="conv{}".format(name))
if use_batchnorm:
conv = mx.symbol.BatchNorm(data=conv, name="bn{}".format(name))
relu = mx.symbol.Activation(data=conv, act_type=act_type, \
name="{}{}".format(act_type, name))
return relu
def replace_conv_layer(layer_name, old_model, sym_handle, arg_handle):
conf = json.loads(old_model.symbol.tojson())
sym_dict = {}
nodes = conf['nodes']
nodes = topsort(nodes)
res_sym = None
new_model = old_model
for i,node in enumerate(nodes):
sym = None
if is_input(node):
sym = mx.symbol.Variable(name='data')
elif node['op'] != 'null':
input_nodes = [nodes[int(j[0])] for j in node['inputs']]
datas = [input_node['name'] for input_node in input_nodes\
if not input_node['name'].startswith(node['name'])]
try:
data=sym_dict[datas[0]]
except Exception, e:
print 'can not find symbol %s'%(datas[0])
raise e
if node['name'] == layer_name:
sym = sym_handle(data, node)
else:
sym = sym_factory(node, data)
if sym:
sym_dict[node['name']] = sym
res_sym = sym
arg_params = copy.deepcopy(old_model.arg_params)
if layer_name:
arg_shapes, _, _ = res_sym.infer_shape(data=(1,3,224,224))
arg_names = res_sym.list_arguments()
arg_shape_dic = dict(zip(arg_names, arg_shapes))
try:
arg_handle(arg_shape_dic, arg_params)
except Exception, e:
raise Exception('Exception in arg_handle')
new_model = mx.model.FeedForward(
symbol=res_sym,
ctx=old_model.ctx,
num_epoch=1,
epoch_size=old_model.epoch_size,
optimizer='sgd',
initializer=old_model.initializer,
numpy_batch_size=old_model.numpy_batch_size,
arg_params=arg_params,
aux_params=old_model.aux_params,
allow_extra_params=True,
begin_epoch=old_model.begin_epoch)
return new_model
def conv_act_layer(from_layer, name, num_filter, kernel=(3, 3), pad=(1, 1), \
stride=(1,1), act_type="relu", use_batchnorm=True):
"""
wrapper for a small Convolution group
Parameters:
----------
from_layer : mx.symbol
continue on which layer
name : str
base name of the new layers
num_filter : int
how many filters to use in Convolution layer
kernel : tuple (int, int)
kernel size (h, w)
pad : tuple (int, int)
padding size (h, w)
stride : tuple (int, int)
stride size (h, w)
act_type : str
activation type, can be relu...
use_batchnorm : bool
whether to use batch normalization
Returns:
----------
(conv, relu) mx.Symbols
"""
conv = mx.symbol.Convolution(data=from_layer, kernel=kernel, pad=pad, \
stride=stride, num_filter=num_filter, name="{}".format(name))
if use_batchnorm:
conv = mx.symbol.BatchNorm(data=conv, name="bn_{}".format(name))
if act_type in ['elu', 'leaky', 'prelu', 'rrelu']:
relu = mx.symbol.LeakyReLU(data=conv, act_type=act_type,
name="{}_{}".format(act_type, name), slope=0.1)
elif act_type in ['relu', 'sigmoid', 'softrelu', 'tanh']:
relu = mx.symbol.Activation(data=conv, act_type=act_type, \
name="{}_{}".format(act_type, name))
else:
assert isinstance(act_type, str)
raise ValueError("Invalid activation type: " + str(act_type))
return relu
def conv_act_layer(from_layer, name, num_filter, kernel=(3, 3), pad=(1, 1), \
stride=(1,1), act_type="relu", use_batchnorm=True):
"""
wrapper for a small Convolution group
Parameters:
----------
from_layer : mx.symbol
continue on which layer
name : str
base name of the new layers
num_filter : int
how many filters to use in Convolution layer
kernel : tuple (int, int)
kernel size (h, w)
pad : tuple (int, int)
padding size (h, w)
stride : tuple (int, int)
stride size (h, w)
act_type : str
activation type, can be relu...
use_batchnorm : bool
whether to use batch normalization
Returns:
----------
(conv, relu) mx.Symbols
"""
conv = mx.symbol.Convolution(data=from_layer, kernel=kernel, pad=pad, \
stride=stride, num_filter=num_filter, name="{}".format(name))
if use_batchnorm:
conv = mx.symbol.BatchNorm(data=conv, name="bn_{}".format(name))
if act_type in ['elu', 'leaky', 'prelu', 'rrelu']:
relu = mx.symbol.LeakyReLU(data=conv, act_type=act_type,
name="{}_{}".format(act_type, name), slope=0.1)
elif act_type in ['relu', 'sigmoid', 'softrelu', 'tanh']:
relu = mx.symbol.Activation(data=conv, act_type=act_type, \
name="{}_{}".format(act_type, name))
else:
assert isinstance(act_type, str)
raise ValueError("Invalid activation type: " + str(act_type))
return relu
def get_symbol(num_classes=20, nms_thresh=0.5, force_suppress=False, nms_topk=400):
"""
Single-shot multi-box detection with VGG 16 layers ConvNet
This is a modified version, with fc6/fc7 layers replaced by conv layers
And the network is slightly smaller than original VGG 16 network
This is the detection network
Parameters:
----------
num_classes: int
number of object classes not including background
nms_thresh : float
threshold of overlap for non-maximum suppression
force_suppress : boolean
whether suppress different class objects
nms_topk : int
apply NMS to top K detections
Returns:
----------
mx.Symbol
"""
net = get_symbol_train(num_classes)
cls_preds = net.get_internals()["multibox_cls_pred_output"]
loc_preds = net.get_internals()["multibox_loc_pred_output"]
anchor_boxes = net.get_internals()["multibox_anchors_output"]
cls_prob = mx.symbol.SoftmaxActivation(data=cls_preds, mode='channel', \
name='cls_prob')
out = mx.contrib.symbol.MultiBoxDetection(*[cls_prob, loc_preds, anchor_boxes], \
name="detection", nms_threshold=nms_thresh, force_suppress=force_suppress,
variances=(0.1, 0.1, 0.2, 0.2), nms_topk=nms_topk)
return out
def get_symbol(num_classes=20, nms_thresh=0.5, force_suppress=False, nms_topk=400):
"""
Single-shot multi-box detection with VGG 16 layers ConvNet
This is a modified version, with fc6/fc7 layers replaced by conv layers
And the network is slightly smaller than original VGG 16 network
This is the detection network
Parameters:
----------
num_classes: int
number of object classes not including background
nms_thresh : float
threshold of overlap for non-maximum suppression
force_suppress : boolean
whether suppress different class objects
nms_topk : int
apply NMS to top K detections
Returns:
----------
mx.Symbol
"""
net = get_symbol_train(num_classes)
cls_preds = net.get_internals()["multibox_cls_pred_output"]
loc_preds = net.get_internals()["multibox_loc_pred_output"]
anchor_boxes = net.get_internals()["multibox_anchors_output"]
cls_prob = mx.symbol.SoftmaxActivation(data=cls_preds, mode='channel', \
name='cls_prob')
out = mx.contrib.symbol.MultiBoxDetection(*[cls_prob, loc_preds, anchor_boxes], \
name="detection", nms_threshold=nms_thresh, force_suppress=force_suppress,
variances=(0.1, 0.1, 0.2, 0.2), nms_topk=nms_topk)
return out
def get_symbol(num_classes=20, nms_thresh=0.5, force_suppress=False,
nms_topk=400, **kwargs):
"""
Single-shot multi-box detection with VGG 16 layers ConvNet
This is a modified version, with fc6/fc7 layers replaced by conv layers
And the network is slightly smaller than original VGG 16 network
This is the detection network
Parameters:
----------
num_classes: int
number of object classes not including background
nms_thresh : float
threshold of overlap for non-maximum suppression
force_suppress : boolean
whether suppress different class objects
nms_topk : int
apply NMS to top K detections
Returns:
----------
mx.Symbol
"""
net = get_symbol_train(num_classes)
cls_preds = net.get_internals()["multibox_cls_pred_output"]
loc_preds = net.get_internals()["multibox_loc_pred_output"]
anchor_boxes = net.get_internals()["multibox_anchors_output"]
cls_prob = mx.symbol.SoftmaxActivation(data=cls_preds, mode='channel', \
name='cls_prob')
out = mx.contrib.symbol.MultiBoxDetection(*[cls_prob, loc_preds, anchor_boxes], \
name="detection", nms_threshold=nms_thresh, force_suppress=force_suppress,
variances=(0.1, 0.1, 0.2, 0.2), nms_topk=nms_topk)
return out
def get_symbol(num_classes=20, nms_thresh=0.5, force_suppress=False, nms_topk=400):
"""
Single-shot multi-box detection with VGG 16 layers ConvNet
This is a modified version, with fc6/fc7 layers replaced by conv layers
And the network is slightly smaller than original VGG 16 network
This is the detection network
Parameters:
----------
num_classes: int
number of object classes not including background
nms_thresh : float
threshold of overlap for non-maximum suppression
force_suppress : boolean
whether suppress different class objects
nms_topk : int
apply NMS to top K detections
Returns:
----------
mx.Symbol
"""
net = get_symbol_train(num_classes)
cls_preds = net.get_internals()["multibox_cls_pred_output"]
loc_preds = net.get_internals()["multibox_loc_pred_output"]
anchor_boxes = net.get_internals()["multibox_anchors_output"]
cls_prob = mx.symbol.SoftmaxActivation(data=cls_preds, mode='channel', \
name='cls_prob')
out = mx.contrib.symbol.MultiBoxDetection(*[cls_prob, loc_preds, anchor_boxes], \
name="detection", nms_threshold=nms_thresh, force_suppress=force_suppress,
variances=(0.1, 0.1, 0.2, 0.2), nms_topk=nms_topk)
return out
def get_symbol(num_classes=20, nms_thresh=0.5, force_suppress=True):
"""
Single-shot multi-box detection with VGG 16 layers ConvNet
This is a modified version, with fc6/fc7 layers replaced by conv layers
And the network is slightly smaller than original VGG 16 network
This is the detection network
Parameters:
----------
num_classes: int
number of object classes not including background
nms_thresh : float
threshold of overlap for non-maximum suppression
Returns:
----------
mx.Symbol
"""
net = get_symbol_train(num_classes)
# print net.get_internals().list_outputs()
cls_preds = net.get_internals()["multibox_cls_pred_output"]
loc_preds = net.get_internals()["multibox_loc_pred_output"]
anchor_boxes = net.get_internals()["multibox_anchors_output"]
cls_prob = mx.symbol.SoftmaxActivation(data=cls_preds, mode='channel', \
name='cls_prob')
# group output
# out = mx.symbol.Group([loc_preds, cls_preds, anchor_boxes])
out = mx.symbol.MultiBoxDetection(*[cls_prob, loc_preds, anchor_boxes], \
name="detection", nms_threshold=nms_thresh, force_suppress=force_suppress,
variances=(0.1, 0.1, 0.2, 0.2))
return out
def get_symbol(num_classes=20, nms_thresh=0.5, force_suppress=False,
nms_topk=400, **kwargs):
"""
Single-shot multi-box detection with VGG 16 layers ConvNet
This is a modified version, with fc6/fc7 layers replaced by conv layers
And the network is slightly smaller than original VGG 16 network
This is the detection network
Parameters:
----------
num_classes: int
number of object classes not including background
nms_thresh : float
threshold of overlap for non-maximum suppression
force_suppress : boolean
whether suppress different class objects
nms_topk : int
apply NMS to top K detections
Returns:
----------
mx.Symbol
"""
net = get_symbol_train(num_classes)
cls_preds = net.get_internals()["multibox_cls_pred_output"]
loc_preds = net.get_internals()["multibox_loc_pred_output"]
anchor_boxes = net.get_internals()["multibox_anchors_output"]
cls_prob = mx.symbol.SoftmaxActivation(data=cls_preds, mode='channel', \
name='cls_prob')
out = mx.contrib.symbol.MultiBoxDetection(*[cls_prob, loc_preds, anchor_boxes], \
name="detection", nms_threshold=nms_thresh, force_suppress=force_suppress,
variances=(0.1, 0.1, 0.2, 0.2), nms_topk=nms_topk)
return out
def get_symbol(num_classes=20, nms_thresh=0.5, force_suppress=False, nms_topk=400):
"""
Single-shot multi-box detection with VGG 16 layers ConvNet
This is a modified version, with fc6/fc7 layers replaced by conv layers
And the network is slightly smaller than original VGG 16 network
This is the detection network
Parameters:
----------
num_classes: int
number of object classes not including background
nms_thresh : float
threshold of overlap for non-maximum suppression
force_suppress : boolean
whether suppress different class objects
nms_topk : int
apply NMS to top K detections
Returns:
----------
mx.Symbol
"""
net = get_symbol_train(num_classes)
cls_preds = net.get_internals()["multibox_cls_pred_output"]
loc_preds = net.get_internals()["multibox_loc_pred_output"]
anchor_boxes = net.get_internals()["multibox_anchors_output"]
cls_prob = mx.symbol.SoftmaxActivation(data=cls_preds, mode='channel', \
name='cls_prob')
out = mx.contrib.symbol.MultiBoxDetection(*[cls_prob, loc_preds, anchor_boxes], \
name="detection", nms_threshold=nms_thresh, force_suppress=force_suppress,
variances=(0.1, 0.1, 0.2, 0.2), nms_topk=nms_topk)
return out
