def __init__(self, alpha = None, use_gpu=True):
super(Poles,self).__init__()
self.use_gpu = use_gpu
if alpha == None:
self.alpha = nn.Parameter(torch.Tensor([0.25]))
print("Initial alpha set to: {}".format(self.alpha))
else:
self.alpha = torch.Tensor([alpha])
if use_gpu:
self.alpha = self.alpha.cuda()
assert(self.alpha<=1 and self.alpha>=0)
self.ema_loc = 30 # 30 = bottleneck
# Create encoder based on VGG16 architecture
original_vgg16 = vgg16()
# select only convolutional layers
encoder = torch.nn.Sequential(*list(original_vgg16.features)[:30])
# define decoder based on VGG16 (inverse order and Upsampling layers)
decoder_list=[
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor=2, mode='nearest'),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor=2, mode='nearest'),
Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor=2, mode='nearest'),
Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor=2, mode='nearest'),
Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(64, 1, kernel_size=(1, 1), stride=(1, 1), padding=0),
Sigmoid(),
]
decoder = torch.nn.Sequential(*decoder_list)
# assamble the full architecture encoder-decoder
self.salgan = torch.nn.Sequential(*(list(encoder.children())+list(decoder.children())))
print("Model initialized, EMA located at {}".format(self.salgan[self.ema_loc]))
def __init__(self):
super(Decoder,self,pretainer = True).__init__()
decoder_list=[
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor= 4, mode='nearest'),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor= 4, mode='nearest'),
Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor=2, mode='nearest'),
Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor=2, mode='nearest'),
Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(64, 1, kernel_size=(1, 1), stride=(1, 1), padding=0),
Sigmoid(),
]
self.decoder = torch.nn.Sequential(*decoder_list)
self._initialize_weights()
print("decoder initialized")
print("architecture len :",str(len(self.Autoencoder)))
def create_model(input_channels):
# Create encoder based on VGG16 architecture
# original_vgg16 = vgg16()
#
# # select only convolutional layers
# encoder = torch.nn.Sequential(*list(original_vgg16.features)[:30])
# new enconder
encoder = [
Conv2d(input_channels,
64,
kernel_size=(3, 3),
stride=(4, 4),
padding=(1, 1)),
ReLU(),
Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
MaxPool2d(kernel_size=2,
stride=2,
padding=0,
dilation=1,
ceil_mode=False),
Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
MaxPool2d(kernel_size=2,
stride=2,
padding=0,
dilation=1,
ceil_mode=False),
Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
MaxPool2d(kernel_size=2,
stride=2,
padding=0,
dilation=1,
ceil_mode=False),
Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
MaxPool2d(kernel_size=2,
stride=2,
padding=0,
dilation=1,
ceil_mode=False),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU()
]
# define decoder based on VGG16 (inverse order and Upsampling layers)
decoder_list = [
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor=2, mode='nearest'),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor=2, mode='nearest'),
Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor=2, mode='nearest'),
Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor=8, mode='nearest'),
Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(64, 1, kernel_size=(1, 1), stride=(1, 1), padding=(0, 0)),
Sigmoid(),
]
encoder = torch.nn.Sequential(*encoder)
decoder = torch.nn.Sequential(*decoder_list)
# assamble the full architecture encoder-decoder
model = torch.nn.Sequential(*(list(encoder.children()) +
list(decoder.children())))
return model
def __init__(self):
super(Encoder,self,pretainer = True).__init__()
# Create encoder based on VGG16 architecture
# Change just 4,5 th maxpooling layer to 4 scale instead of 2
# select only convolutional layers first 5 conv blocks ,cahnge maxpooling=> enlarge receptive field
# each neuron on bottelneck will see (580,580) all viewports ,
# input (576,288) , features numbers on bottelneck (9*4)*512, exclude last maxpooling
encoder_list[
Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=0),
ReLU(),
Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Downsample(kernel_size = 3)
Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Downsample(kernel_size = 3)
Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Downsample(kernel_size = 3 , stride = 4)
Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Downsample(kernel_size = 3 , stride = 4)
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
]
self.encoder = torch.nn.Sequential(*Global_Attention_Encoder)
print("encoder initialized")
print("architecture len :",str(len(self.Autoencoder)))
def __init__(self, use_gpu=True):
super(Salgan360,self).__init__()
self.use_gpu = use_gpu
# Create encoder based on VGG16 architecture as pointed on salgan architecture
original_vgg16 = vgg16()
# select only convolutional layers first 5 conv blocks , here we keep same receptive field of VGG 212*212
# each neuron on bottelneck will see just (212,212) viewport during sliding ,
# input (576,288) , features numbers on bottelneck 36*18*512, exclude last maxpooling
encoder = torch.nn.Sequential(*list(original_vgg16.features)[:30])
# define decoder based on VGG16 (inverse order and Upsampling layers , chose nearest mode)
decoder_list=[
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor=2, mode='nearest'),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor=2, mode='nearest'),
Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor=2, mode='nearest'),
Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Upsample(scale_factor=2, mode='nearest'),
Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
ReLU(),
Conv2d(64, 1, kernel_size=(1, 1), stride=(1, 1), padding=0),
Sigmoid(),
]
decoder = torch.nn.Sequential(*decoder_list)
# aggreegate the full architecture encoder-decoder of salgan360
self.Salgan360 = torch.nn.Sequential(*(list(encoder.children())+list(decoder.children())))
print("Model initialized, SalGAN360")
print("architecture len :",str(len(self.Salgan360)))
