def MobileNetV2(include_top=True,
pretrained=True,
input_shape=(224, 224, 3),
classes=1000,
**kwargs):
if input_shape is not None and len(input_shape) == 3:
input_shape = tuple(input_shape)
else:
input_shape = (224, 224, 3)
mob = MobileNet(input_shape=(224, 224, 3),
classes=classes,
use_bias=False,
width_mult=1.0,
round_nearest=8,
include_top=include_top,
model_name='mobilenet')
if pretrained == True:
download_model_from_google_drive('15LtLJHpvimV6cFGqAwJ4QALNEjeATrKe',
dirname, 'mobilenet_v2_tf.pth')
recovery_model = fix_layer(
load(os.path.join(dirname, 'mobilenet_v2_tf.pth')))
recovery_model.eval()
with tf.device(get_device()):
if include_top == False:
recovery_model.remove_at(-1)
recovery_model.remove_at(-1)
recovery_model.remove_at(-1)
else:
if classes != 1000:
new_fc = Dense(classes, activation=None, name='fc')
new_fc.input_shape = recovery_model.fc.input_shape
recovery_model.fc = new_fc
mob.model = recovery_model
return mob
def DenseNet201(include_top=True,
pretrained=True,
input_shape=(224, 224, 3),
classes=1000,
**kwargs):
"""
Constructor the image classicication model with DenseNet201 as backbond
Args:
include_top ():
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)
classes (int): number of classes
References
Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf
Returns:
the image classicication model with DenseNet201
Examples:
>>> dense201 = DenseNet201(include_top=True,pretrained=True,input_shape=(224,224,3),classes=1000)
>>> 'n02124075' in dense201.infer_single_image(get_image_from_google_drive('1SwablQsZO8mBuB84xnr1IoOisE3pm03l'),1).key_list[0]
True
"""
if input_shape is not None and len(input_shape) == 3:
input_shape = tuple(input_shape)
densenet201 = DenseNet([6, 12, 48, 32],
32,
64,
include_top=include_top,
pretrained=True,
input_shape=input_shape,
num_classes=classes,
name='densenet201')
if pretrained == True:
download_model_from_google_drive('1dJfgus11jXVoCLWfZqTgZ6jKKtrB70om',
dirname, 'densenet201_tf.pth')
recovery_model = load(os.path.join(dirname, 'densenet201_tf.pth'))
recovery_model = fix_layer(recovery_model)
recovery_model._name = 'densenet201'
recovery_model.eval()
if include_top == False:
recovery_model.remove_at(-1)
recovery_model.remove_at(-1)
else:
if classes != 1000:
recovery_model.remove_at(-1)
recovery_model.remove_at(-1)
recovery_model.add_module(
'classifier',
Dense(classes, activation=None, name='classifier'))
recovery_model.add_module('softmax', SoftMax(name='softmax'))
recovery_model.signature = Signature(name='DenseNetFcn')
if is_tensor(recovery_model._input_shape):
recovery_model.signature.inputs['input'] = TensorSpec(
shape=recovery_model._input_shape, name='input')
if is_tensor(recovery_model._output_shape):
recovery_model.signature.outputs['output'] = TensorSpec(
shape=recovery_model._output_shape, name='output')
densenet201.model = recovery_model
return densenet201
def DenseNet201(include_top=True,
pretrained=True,
input_shape=(224, 224, 3),
freeze_features=False,
classes=1000,
**kwargs):
"""
Constructor the image classicication model with DenseNet201 as backbond
Args:
freeze_features ():
include_top ():
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)
classes (int): number of classes
References
Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf
Returns:
the image classicication model with DenseNet201
Examples:
>>> dense201 = DenseNet201(include_top=True,pretrained=True,input_shape=(224,224,3),classes=1000)
>>> 'n02124075' in dense201.infer_single_image(get_image_from_google_drive('1SwablQsZO8mBuB84xnr1IoOisE3pm03l'),1).key_list[0]
True
"""
if input_shape is not None and len(input_shape) == 3:
input_shape = tuple(input_shape)
densenet201 = DenseNet([6, 12, 48, 32],
32,
64,
include_top=include_top,
pretrained=True,
input_shape=input_shape,
num_classes=classes,
name='densenet201')
with tf.device(get_device()):
if pretrained == True:
download_model_from_google_drive(
'1dJfgus11jXVoCLWfZqTgZ6jKKtrB70om', dirname,
'densenet201_tf.pth')
recovery_model = load(os.path.join(dirname, 'densenet201_tf.pth'))
recovery_model = fix_layer(recovery_model)
recovery_model._name = 'densenet201'
recovery_model = _make_recovery_model_include_top(
recovery_model,
include_top=include_top,
classes=classes,
freeze_features=freeze_features)
densenet201.model = recovery_model
else:
densenet201.model = _make_recovery_model_include_top(
densenet201.model,
include_top=include_top,
classes=classes,
freeze_features=False)
densenet201.model.input_shape = input_shape
return densenet201
