sigma.size()[-1])
x = self.m_down(x)
# m = torch.ones(sigma.size()[0], sigma.size()[1], x.size()[-2], x.size()[-1]).type_as(x).mul(sigma)
#m = sigma.repeat(1, 1, x.size()[-2], x.size()[-1])
print(sigma.size())
m = sigma
print('coco')
print(x.size())
print(m.size())
print('caca')
x = torch.cat((x, m), 1)
x = self.model(x)
x = self.m_up(x)
x = x[..., :h, :w]
return x
if __name__ == '__main__':
from utils import utils_model
model = FFDNet(in_nc=1, out_nc=1, nc=64, nb=15, act_mode='R')
print(utils_model.describe_model(model))
x = torch.randn((2, 1, 240, 240))
sigma = torch.randn(2, 1, 1, 1)
x = model(x, sigma)
print(x.shape)
# run models/network_ffdnet.py
B.conv(nc, nc, mode='C' + act_mode, bias=bias)
for _ in range(nb - 2)
]
m_tail = B.conv(nc, out_nc, mode='C', bias=bias)
self.model = B.sequential(m_head, *m_body, m_tail)
def forward(self, x):
x = self.model(x)
return x
if __name__ == '__main__':
from utils import utils_model
import torch
model1 = DnCNN(in_nc=1, out_nc=1, nc=64, nb=20, act_mode='BR')
print(utils_model.describe_model(model1))
model2 = FDnCNN(in_nc=2, out_nc=1, nc=64, nb=20, act_mode='R')
print(utils_model.describe_model(model2))
x = torch.randn((1, 1, 240, 240))
x1 = model1(x)
print(x1.shape)
x = torch.randn((1, 2, 240, 240))
x2 = model2(x)
print(x2.shape)
# run models/network_dncnn.py