def RfbNet(include_top=True,
pretrained=True,
input_shape=None,
base_filters=16, num_classes=1, num_regressors=4,
**kwargs):
if input_shape is not None and len(input_shape) == 3:
input_shape = tuple(input_shape)
else:
input_shape = (3, 480, 640)
rfbnet = SsdDetectionModel(input_shape=(3, 480, 640), output=RFBnet(base_filters=base_filters, num_classes=num_classes, num_regressors=num_regressors))
rfbnet.detection_threshold=0.7
rfbnet.nms_threshold=0.7
rfbnet.palette[0] = (128, 255, 128)
rfbnet.palette[1] = (128, 255, 128)
rfbnet.preprocess_flow = [
Resize((480, 640), True),
Normalize(127.5, 127.5)
]
if pretrained == True:
download_model_from_google_drive('1T_0VYOHaxoyuG1fAxY-6g0C7pfXiujns', dirname, 'version-RFB-640.pth')
recovery_model =fix_layer( load(os.path.join(dirname, 'version-RFB-640.pth')))
priors=recovery_model.priors.clone()
recovery_model.__delattr__("priors")
recovery_model.register_buffer("priors",priors)
recovery_model.name = 'rfb640'
recovery_model.eval()
recovery_model.to(_device)
rfbnet.model = recovery_model
return rfbnet
def __init__(self, inputs=None, input_shape=None,output=None):
super(YoloDetectionModel, self).__init__(inputs, input_shape,output)
self.preprocess_flow = [Resize((input_shape[-2], input_shape[-1]), True), Normalize(0, 255)]
self.detection_threshold = 0.5
self.nms_threshold = 0.3
self.class_names = None
self.palette = generate_palette(80)
def DenseNetFcn(blocks=(4, 5, 7, 10, 12),
growth_rate=16,
initial_filters=64,
pretrained=False,
input_shape=(224, 224, 3),
num_classes=10,
name='',
**kwargs):
"""
Instantiates the DenseNet FCN architecture.
Optionally loads weights pre-trained on ImageNet.
Args
blocks (tuple/ list of int ): numbers of building blocks for the dense layers.
growth_rate (int):The growth rate regulates how much new information each layer contributes to the global state
initial_filters (int): the channel of the first convolution layer
pretrained (bool): only False is valid for DenseNet FCN
input_shape (tuple or list): the default input image size in CHW order (C, H, W)
num_classes (int): number of classes
name (string): anme of the model
Returns
A trident image segmentation model instance.
"""
model = ImageSegmentationModel(input_shape=input_shape,
output=_DenseNetFcn2(
blocks=blocks,
growth_rate=growth_rate,
initial_filters=initial_filters,
num_classes=num_classes,
name=name,
**kwargs))
model.signature = Signature(name='DenseNetFcn')
if is_tensor(model._input_shape):
model.signature.inputs['input'] = TensorSpec(shape=model._input_shape,
name='input')
if is_tensor(model._output_shape):
model.signature.outputs['output'] = TensorSpec(
shape=model._output_shape, name='output')
model.preprocess_flow = [
Resize((input_shape[2], input_shape[1]), keep_aspect=True),
Normalize(0, 255),
Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]
# model.summary()
return model
def InceptionV3(include_top=True,
pretrained=True,
freeze_features=False,
input_shape=(3, 224, 224),
classes=1000,
**kwargs):
if input_shape is not None and len(input_shape) == 3:
input_shape = tuple(input_shape)
else:
input_shape = (3, 224, 224)
model = ImageClassificationModel(input_shape=input_shape,
output=inception_v3(
input_shape,
model_name='inception_v3',
include_top=include_top,
num_classes=classes))
with open(os.path.join(os.path.dirname(os.path.abspath(__file__)),
'imagenet_labels1.txt'),
'r',
encoding='utf-8-sig') as f:
labels = [l.rstrip() for l in f]
model.class_names = labels
model.preprocess_flow = [
Resize((input_shape[2], input_shape[1]), keep_aspect=True),
Normalize(0, 255),
Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]
# if pretrained:
# download_model_from_google_drive('1bxnoDerzoNfiZZLft4ocD3DAgx4v6aTN', dirname, 'efficientnet-b0.pth')
# recovery_model = fix_layer(load(os.path.join(dirname, 'efficientnet-b0.pth')))
# recovery_model = _make_recovery_model_include_top(recovery_model,input_shape=input_shape, include_top=include_top, classes=classes, freeze_features=freeze_features)
# effb0.model = recovery_model
# else:
# effb0.model = _make_recovery_model_include_top( effb0.model, include_top=include_top, classes=classes, freeze_features=False)
#
# effb0.model .input_shape = input_shape
# effb0.model .to(get_device())
return model
def SEResNet_IR(include_top=True,num_layers=50,Bottleneck=BottleNeck_IR_SE,drop_ratio=0.4,feature_dim=128,input_shape=(3,112,112)):
blocks=OrderedDict()
blocks['input_layer']=Conv2d_Block((3,3),64,strides=1,auto_pad=True,use_bias=False,activation=PRelu(64),normalization='batch',name='input_layer')
blocks['body']=Sequential(
get_block(Bottleneck, out_channel=64, num_units=3,keep_filter=True)+
get_block(Bottleneck, out_channel=128, num_units=4,keep_filter=False)+
get_block(Bottleneck, out_channel=256, num_units=14,keep_filter=False)+
get_block(Bottleneck, out_channel=512, num_units=3,keep_filter=False)
)
blocks['output_layer']=Sequential(
BatchNorm2d(),
Dropout(drop_ratio),
Flatten(),
Dense(feature_dim),
BatchNorm(),
name='output_layer'
)
facenet=Sequential(blocks).to(_device)
facenet.name=camel2snake('SEResNet_IR')
model=FaceRecognitionModel(input_shape=input_shape,output=facenet)
model.preprocess_flow=[Resize((input_shape[1],input_shape[2]),keep_aspect=True),Normalize(0,255),Normalize([0.485, 0.456, 0.406],[0.229, 0.224, 0.225])]
#model.summary()
return model
def make_vgg_layers(cfg,
num_classes=1000,
input_shape=(224, 224, 3),
include_top=True):
layers = []
in_channels = 3
block = 1
conv = 1
vgg = Sequential()
for v in cfg:
if v == 'M':
vgg.add_module(
'block{0}_pool'.format(block),
MaxPool2d(kernel_size=2,
strides=2,
use_bias=True,
name='block{0}_pool'.format(block)))
block += 1
conv = 1
else:
if len(vgg) == 0:
vgg.add_module(
'block{0}_conv{1}'.format(block, conv),
Conv2d((3, 3),
v,
auto_pad=True,
activation=None,
use_bias=True,
name='block{0}_conv{1}'.format(block, conv)))
else:
vgg.add_module(
'block{0}_conv{1}'.format(block, conv),
Conv2d((3, 3),
v,
auto_pad=True,
activation=None,
use_bias=True,
name='block{0}_conv{1}'.format(block, conv)))
vgg.add_module('block{0}_relu{1}'.format(block, conv),
Relu(name='block{0}_relu{1}'.format(block, conv)))
conv += 1
in_channels = v
if include_top == True:
vgg.add_module('flattened', Flatten())
vgg.add_module('fc1', Dense(4096, use_bias=True, activation='relu'))
vgg.add_module('drop1', Dropout(0.5))
vgg.add_module('fc2', Dense(4096, use_bias=True, activation='relu'))
vgg.add_module('drop2', Dropout(0.5))
vgg.add_module('fc3',
Dense(num_classes, use_bias=True, activation='softmax'))
model = ImageClassificationModel(input_shape=input_shape, output=vgg)
model.signature = get_signature(model.model.forward)
with open(os.path.join(os.path.dirname(os.path.abspath(__file__)),
'imagenet_labels1.txt'),
'r',
encoding='utf-8-sig') as f:
labels = [l.rstrip() for l in f]
model.class_names = labels
model.preprocess_flow = [
Resize((input_shape[0], input_shape[1]), keep_aspect=True),
to_bgr(),
Normalize([103.939, 116.779, 123.68], [1, 1, 1])
]
# model.summary()
return model
def MobileNet(input_shape=(224, 224, 3),
classes=1000,
use_bias=False,
width_mult=1.0,
round_nearest=8,
include_top=True,
model_name='',
**kwargs):
input_filters = 32
last_filters = 1280
mobilenet = Sequential(name='mobilenet')
inverted_residual_setting = [
# t, c, n, s
[1, 16, 1, 1],
[6, 24, 2, 2],
[6, 32, 3, 2],
[6, 64, 4, 2],
[6, 96, 3, 1],
[6, 160, 3, 2],
[6, 320, 1, 1],
]
input_filters = _make_divisible(input_filters * width_mult, round_nearest)
last_filters = _make_divisible(last_filters * max(1.0, width_mult),
round_nearest)
features = []
features.append(
Conv2d_Block((3, 3),
num_filters=input_filters,
strides=2,
auto_pad=True,
padding_mode='zero',
normalization='batch',
activation='relu6',
name='first_layer'))
for t, c, n, s in inverted_residual_setting:
output_filters = _make_divisible(c * width_mult, round_nearest)
for i in range(n):
strides = s if i == 0 else 1
features.append(
inverted_residual(input_filters,
num_filters=output_filters,
strides=strides,
expansion=t,
name='irb_{0}'.format(i)))
input_filters = output_filters
features.append(
Conv2d_Block((1, 1),
last_filters,
auto_pad=True,
padding_mode='zero',
normalization='batch',
activation='relu6',
name='last_layer'))
mobilenet.add_module('features', Sequential(*features, name='features'))
if include_top:
mobilenet.add_module('gap', GlobalAvgPool2d())
mobilenet.add_module('drop', Dropout(0.2))
mobilenet.add_module('fc', Dense((classes), activation=None))
mobilenet.add_module('softmax', SoftMax(name='softmax'))
model = ImageClassificationModel(input_shape=input_shape, output=mobilenet)
with open(os.path.join(os.path.dirname(os.path.abspath(__file__)),
'imagenet_labels1.txt'),
'r',
encoding='utf-8-sig') as f:
labels = [l.rstrip() for l in f]
model.class_names = labels
model.preprocess_flow = [
Resize((224, 224), keep_aspect=True),
Normalize(127.5, 127.5)
]
# model.summary()
return model
def EfficientNet(width_coefficient,
depth_coefficient,
input_shape,
dropout_rate=0.2,
drop_connect_rate=0.2,
depth_divisor=8,
model_name='efficientnet',
include_top=True,
num_classes=1000,
**kwargs):
"""Instantiates the EfficientNet architecture using given scaling coefficients.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.
Args
width_coefficient: float, scaling coefficient for network width.
depth_coefficient: float, scaling coefficient for network depth.
default_size: integer, default input image size.
dropout_rate: float, dropout rate before final classifier layer.
drop_connect_rate: float, dropout rate at skip connections.
depth_divisor: integer, a unit of network width.
activation_fn: activation function.
blocks_args: list of dicts, parameters to construct block modules.
model_name: string, model name.
include_top: whether to include the fully-connected
layer at the top of the network.
input_tensor: optional Keras tensor
(i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False.
It should have exactly 3 inputs channels.
num-classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns
A Efficientnet model instance.
"""
default_block_args = deepcopy(DEFAULT_BLOCKS_ARGS)
def round_filters(filters, divisor=depth_divisor):
"""Round number of filters based on depth multiplier."""
filters *= width_coefficient
new_filters = builtins.max(
divisor,
int(filters + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if new_filters < 0.9 * filters:
new_filters += divisor
return int(new_filters)
def round_repeats(repeats):
"""Round number of repeats based on depth multiplier."""
return int(math.ceil(depth_coefficient * repeats))
flow_list = []
efficientnet = Sequential(name=model_name)
efficientnet.add_module(
'stem',
Conv2d_Block((3, 3),
round_filters(32),
strides=2,
use_bias=False,
auto_pad=True,
padding_mode='zero',
normalization='batch',
activation='swish',
name='stem'))
b = 0
blocks = float(builtins.sum(args['repeats']
for args in default_block_args))
for (i, args) in enumerate(default_block_args):
assert args['repeats'] > 0
# Update block input and output filters based on depth multiplier.
# args['filters_in'] = round_filters(args['filters_in'])
# args['filters_out'] = round_filters(args['filters_out'])
for j in range(round_repeats(args.pop('repeats'))):
# The first block needs to take care of stride and filter size increase.
if j > 0:
args['strides'] = 1
args['filters_in'] = args['filters_out']
efficientnet.add_module(
'block{}{}'.format(i + 1, chr(j + 97)),
efficient_block(expand_ratio=args['expand_ratio'],
filters_in=round_filters(args['filters_in']),
filters_out=round_filters(args['filters_out']),
kernel_size=args['kernel_size'],
strides=args['strides'],
zero_pad=0,
se_ratio=args['se_ratio'],
drop_connect_rate=drop_connect_rate * b /
blocks,
name='block{}{}_'.format(i + 1, chr(j + 97)))),
b += 1
efficientnet.add_module(
'top_conv',
Conv2d_Block((1, 1),
round_filters(1280),
strides=1,
use_bias=False,
auto_pad=True,
padding_mode='zero',
normalization='batch',
activation='swish',
name='top_conv'))
efficientnet.add_module('avg_pool', GlobalAvgPool2d(name='avg_pool'))
if include_top:
if dropout_rate > 0:
efficientnet.add_module('top_dropout',
Dropout(dropout_rate, name='top_dropout'))
efficientnet.add_module('fc',
Dense(num_classes, activation=None, name='fc'))
efficientnet.add_module('softmax', SoftMax(name='softmax'))
model = ImageClassificationModel(input_shape=input_shape,
output=efficientnet)
with open(os.path.join(os.path.dirname(os.path.abspath(__file__)),
'imagenet_labels1.txt'),
'r',
encoding='utf-8-sig') as f:
labels = [l.rstrip() for l in f]
model.class_names = labels
model.preprocess_flow = [
Resize((input_shape[2], input_shape[1]), keep_aspect=True),
Normalize(0, 255),
Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]
# model.summary()
return model
def forward(self, x, scale):
inp = x.exand_dims(0)
boxes = self.pnet(inp)
boxes_list = []
if boxes is not None and len(boxes) > 0:
box = boxes[:, :4] / scale
score = boxes[:, 4:]
boxes = concate([box.round_(), score], axis=1)
if len(boxes) > 0:
boxes_list.append(boxes)
#######################################
#########pnet finish
#######################################
if len(boxes_list) > 0:
boxes = to_tensor(concate(boxes_list, axis=0))
# print('total {0} boxes in pnet in all scale '.format(len(boxes)))
boxes = clip_boxes_to_image(boxes, (x.shape[0], x.shape[1]))
boxes = nms(boxes, threshold=self.detection_threshold[0])
print('pnet:{0} boxes '.format(len(boxes)))
# print('total {0} boxes after nms '.format(len(boxes)))
# score = to_numpy(boxes[:, 4]).reshape(-1)
if boxes is not None:
# prepare rnet input
boxes = self.rerec(boxes, x.shape)
new_arr = np.zeros((boxes.shape[0], 3, 24, 24))
for k in range(boxes.shape[0]):
box = boxes[k]
crop_img = x.copy()[int(box[1]):int(box[3]),
int(box[0]):int(box[2]), :]
if crop_img.shape[0] > 0 and crop_img.shape[1] > 0:
new_arr[k] = Resize(
(24, 24))(crop_img / 255.0).transpose([2, 0, 1])
# else:
# print(box)
new_arr = to_tensor(new_arr)
r_output1_list = []
r_output2_list = []
r_output3_list = []
if len(new_arr) > 16:
for i in range(len(new_arr) // 16 + 1):
if i * 16 < len(new_arr):
r_out1, r_out2, r_out3 = self.rnet(
new_arr[i * 16:(i + 1) * 16, :, :, :])
r_output1_list.append(r_out1)
r_output2_list.append(r_out2)
r_output3_list.append(r_out3)
r_out1 = concate(r_output1_list, axis=0)
r_out2 = concate(r_output2_list, axis=0)
r_out3 = concate(r_output3_list, axis=0)
else:
r_out1, r_out2, r_out3 = self.rnet(new_arr)
probs = to_numpy(r_out1)
keep = np.where(probs[:, 0] > self.detection_threshold[1])[0]
r_out1 = r_out1[keep]
boxes = boxes[keep]
boxes[:, 4] = r_out1[:, 0]
r_out2 = r_out2[keep]
boxes = calibrate_box(boxes, r_out2)
#######################################
#########rnet finish
#######################################
boxes = nms(boxes,
threshold=self.detection_threshold[1],
image_size=(x.shape[0], x.shape[1]),
min_size=self.min_size)
print('rnet:{0} boxes '.format(len(boxes)))
# print('total {0} boxes after nms '.format(len(boxes)))
boxes = clip_boxes_to_image(boxes, (x.shape[0], x.shape[1]))
boxes = self.rerec(boxes, x.shape)
new_arr = np.zeros((boxes.shape[0], 3, 48, 48))
for k in range(boxes.shape[0]):
box = boxes[k]
crop_img = x.copy()[int(box[1]):int(box[3]),
int(box[0]):int(box[2]), :]
if crop_img.shape[0] > 0 and crop_img.shape[1] > 0:
new_arr[k] = Resize(
(48, 48))(crop_img / 255.0).transpose([2, 0, 1])
# else:
# print(box)
new_arr = to_tensor(new_arr)
o_out1, o_out2, o_out3 = self.onet(new_arr)
probs = to_numpy(o_out1)
keep = np.where(probs[:, 0] > self.detection_threshold[2])[0]
o_out1 = o_out1[keep]
boxes = boxes[keep]
boxes[:, 4] = o_out1[:, 0]
o_out2 = o_out2[keep]
o_out3 = o_out3[keep]
boxes = calibrate_box(boxes, o_out2)
landmarks_x = boxes[:, 0:1] + o_out3[:, 0::2] * (
boxes[:, 2:3] - boxes[:, 0:1] + 1)
landmarks_y = boxes[:, 1:2] + o_out3[:, 1::2] * (
boxes[:, 3:4] - boxes[:, 1:2] + 1)
boxes = concate([boxes, landmarks_x, landmarks_y], axis=-1)
def ResNet(block, layers, input_shape=(224, 224,3), num_classes=1000, use_bias=False, include_top=True, model_name='',
**kwargs):
"""Instantiates the ResNet, ResNetV2, and ResNeXt architecture.
Args
block: a function that returns output tensor for the stacked residual blocks.
layers: list of integer, the number of repeat units in each blocks.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)`
It should have exactly 3 inputs channels.
num_classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
use_bias: whether to use biases for convolutional layers or not
(True for ResNet and ResNetV2, False for ResNeXt).
include_top: whether to include the fully-connected layer at the top of the network.
model_name: string, model name.
Returns
A Keras model instance.
Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
def _make_layer(block, num_filters, blocklayers, strides=1, dilate=False,use_bias=use_bias,layer_name=''):
layers = OrderedDict()
layers['0']=block(num_filters=num_filters, strides=strides, expansion = 4, conv_shortcut=True,use_bias=use_bias, name=layer_name+'1')
for k in range(1, blocklayers):
layers['{0}'.format(k)]=block(num_filters=num_filters, strides=1, expansion = 4, conv_shortcut=False, use_bias=use_bias,name=layer_name+'{0}'.format(k+1))
laters_block=Sequential(layers)
laters_block._name=layer_name
return laters_block
flow_list=[]
resnet = Sequential()
resnet.add_module('conv1',Conv2d_Block((7,7),64,strides=2,use_bias=use_bias,auto_pad=True,padding_mode='zero',normalization='batch',activation='relu',name='first_block'))
resnet.add_module('maxpool',(MaxPool2d((3,3),strides=2,auto_pad=True,padding_mode='zero')))
resnet.add_module('layer1',(_make_layer(block, 64, layers[0],strides=1, dilate=None,use_bias=use_bias,layer_name='layer1' )))
resnet.add_module('layer2',(_make_layer(block, 128, layers[1], strides=2, dilate=None,use_bias=use_bias,layer_name='layer2' )))
resnet.add_module('layer3',(_make_layer(block, 256, layers[2], strides=2, dilate=None,use_bias=use_bias,layer_name='layer3' )))
resnet.add_module('layer4' ,(_make_layer(block, 512, layers[3], strides=2, dilate=None,use_bias=use_bias,layer_name='layer4' )))
resnet.add_module('avg_pool',GlobalAvgPool2d(name='avg_pool'))
if include_top:
resnet.add_module('fc',Dense(num_classes,activation=None,name='fc'))
resnet.add_module('softmax', SoftMax(name='softmax'))
resnet._name=model_name
model=ImageClassificationModel(input_shape=input_shape,output=resnet)
with open(os.path.join(os.path.dirname(os.path.abspath(__file__)) ,'imagenet_labels1.txt'), 'r', encoding='utf-8-sig') as f:
labels = [l.rstrip() for l in f]
model.class_names=labels
input_np_shape=to_numpy(input_shape)
model.preprocess_flow=[Resize((input_np_shape[0],input_np_shape[1]),keep_aspect=True), to_bgr(), Normalize([103.939, 116.779, 123.68], [1, 1, 1])]
#model.summary()
return model
def DenseNet(blocks,
growth_rate=32,
initial_filters=64,
include_top=True,
pretrained=True,
input_shape=(224, 224, 3),
num_classes=1000,
name='',
**kwargs):
"""'
Instantiates the DenseNet architecture.
Optionally loads weights pre-trained on ImageNet.
Args
blocks (tuple/ list of int ): numbers of building blocks for the dense layers.
growth_rate (int):The growth rate regulates how much new information each layer contributes to the global state
initial_filters (int): the channel of the first convolution layer
pretrained (bool): If True, returns a model pre-trained on ImageNet.
input_shape (tuple or list): the default input image size in CHW order (C, H, W)
num_classes (int): number of classes
name (string): anme of the model
Returns
A trident image classification model instance.
"""
densenet = Sequential()
densenet.add_module(
'conv1/conv',
Conv2d_Block((7, 7),
num_filters=initial_filters,
strides=2,
use_bias=False,
auto_pad=True,
padding_mode='zero',
activation='relu',
normalization='batch',
name='conv1/conv'))
densenet.add_module('maxpool', (MaxPool2d(
(3, 3), strides=2, auto_pad=True, padding_mode='zero')))
densenet.add_module('denseblock1',
DenseBlock(blocks[0], growth_rate=growth_rate))
densenet.add_module('transitiondown1', Transition(0.5))
densenet.add_module('denseblock2',
DenseBlock(blocks[1], growth_rate=growth_rate))
densenet.add_module('transitiondown2', Transition(0.5))
densenet.add_module('denseblock3',
DenseBlock(blocks[2], growth_rate=growth_rate))
densenet.add_module('transitiondown3', Transition(0.5))
densenet.add_module('denseblock4',
DenseBlock(blocks[3], growth_rate=growth_rate))
densenet.add_module('classifier_norm', BatchNorm2d(name='classifier_norm'))
densenet.add_module('classifier_relu', Relu(name='classifier_relu'))
densenet.add_module('avg_pool', GlobalAvgPool2d(name='avg_pool'))
if include_top:
densenet.add_module(
'classifier', Dense(num_classes,
activation=None,
name='classifier'))
densenet.add_module('softmax', SoftMax(name='softmax'))
densenet.name = name
model = ImageClassificationModel(input_shape=input_shape, output=densenet)
with open(os.path.join(os.path.dirname(os.path.abspath(__file__)),
'imagenet_labels1.txt'),
'r',
encoding='utf-8-sig') as f:
labels = [l.rstrip() for l in f]
model.class_names = labels
model.preprocess_flow = [
Resize((input_shape[0], input_shape[1]), keep_aspect=True),
Normalize(0, 255),
Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]
# model.summary()
return model