def __init__(self,
num_classes,
aux_logits=True,
transform_input=False,
num_channels=4):
super(SEInception3, self).__init__()
model = Inception3(num_classes=num_classes,
aux_logits=aux_logits,
transform_input=transform_input)
model.Mixed_5b.add_module("SELayer", SELayer(192))
model.Mixed_5c.add_module("SELayer", SELayer(256))
model.Mixed_5d.add_module("SELayer", SELayer(288))
model.Mixed_6a.add_module("SELayer", SELayer(288))
model.Mixed_6b.add_module("SELayer", SELayer(768))
model.Mixed_6c.add_module("SELayer", SELayer(768))
model.Mixed_6d.add_module("SELayer", SELayer(768))
model.Mixed_6e.add_module("SELayer", SELayer(768))
if aux_logits:
model.AuxLogits.add_module("SELayer", SELayer(768))
model.Mixed_7a.add_module("SELayer", SELayer(768))
model.Mixed_7b.add_module("SELayer", SELayer(1280))
model.Mixed_7c.add_module("SELayer", SELayer(2048))
if num_channels == 4:
model.Conv2d_1a_3x3.conv = nn.Conv2d(4,
32,
kernel_size=(3, 3),
stride=(2, 2),
bias=False)
self.model = model
def __init__(self,
pretrained=True,
num_classes=1000,
aux_logits=True,
transform_input=False):
Inception3.__init__(self,
num_classes=num_classes,
aux_logits=aux_logits,
transform_input=transform_input)
if pretrained:
self.load_state_dict(
model_zoo.load_url(inception_urls['inception_v3_google']))
self.aux_logit = False
self.filter = USM(in_channels=3,
kernel_size=5,
fixed_coeff=True,
sigma=1.667,
cuda=True,
requires_grad=True)
def __init__(self, num_class=2, freeze=False, pretrain=True):
super(inception_v3_pretrain, self).__init__()
self.num_class = num_class
self.model = Inception3(aux_logits=True, transform_input=False)
if pretrain:
self.model.load_state_dict(model_zoo.load_url(URL))
self.sigmoid = nn.Sigmoid()
# freeze the model
if freeze:
for param in self.model.parameters():
param.requires_grad = False
in_features = self.model.fc.in_features
in_features_aux = self.model.AuxLogits.fc.in_features
self.model.fc = nn.Linear(in_features, 1)
self.model.AuxLogits.fc = nn.Linear(in_features_aux, 1)
def __init__(self, num_classes, aux_logits=True, transform_input=False):
super(SEInception3, self).__init__()
model = Inception3(num_classes=num_classes, aux_logits=aux_logits,
transform_input=transform_input)
model.Mixed_5b.add_module("SELayer", SELayer(192))
model.Mixed_5c.add_module("SELayer", SELayer(256))
model.Mixed_5d.add_module("SELayer", SELayer(288))
model.Mixed_6a.add_module("SELayer", SELayer(288))
model.Mixed_6b.add_module("SELayer", SELayer(768))
model.Mixed_6c.add_module("SELayer", SELayer(768))
model.Mixed_6d.add_module("SELayer", SELayer(768))
model.Mixed_6e.add_module("SELayer", SELayer(768))
if aux_logits:
model.AuxLogits.add_module("SELayer", SELayer(768))
model.Mixed_7a.add_module("SELayer", SELayer(768))
model.Mixed_7b.add_module("SELayer", SELayer(1280))
model.Mixed_7c.add_module("SELayer", SELayer(2048))
self.model = model
def load_inception(
resize: bool = True,
normalizer: Optional[Callable] = None
) -> Tuple[nn.Module, torch.device]:
file_ = os.path.join(INFO_PATH, INCEPTION_V3)
if not os.path.exists(file_):
print(">>> Inception model is not found. Download from url ...")
inception_model = inception_v3(pretrained=True, transform_input=False)
device = gpu(inception_model)
torch.save(inception_model.state_dict(), file_)
else:
print(f">>> Inception model is found: {file_} ...")
inception_model = Inception3(transform_input=False)
device = gpu(inception_model)
load(model=inception_model,
path=INFO_PATH,
filename=INCEPTION_V3,
device=device)
model = _Net(arch=inception_model, resize=resize, normalizer=normalizer)
return model, device
def se_inception_v3(**kwargs):
return Inception3(**kwargs)
def Inceptionv3_Net(n_classes, **kwargs):
if Params.isTrue('UseSqueezeExcitation'):
return Inception3(n_classes, inception_blocks=WrappedBlocks, **kwargs)
else:
return Inception3(n_classes, **kwargs)
