def forward(self, x):
# Normalize x
x = (x + 1.) / 2.0
x = (x - self.mean) / self.std
# Upsample if necessary
if x.shape[2] != 299 or x.shape[3] != 299:
x = F.interpolate(x,
size=(299, 299),
mode='bilinear',
align_corners=True)
# 299 x 299 x 3
x = self.net.Conv2d_1a_3x3(x)
# 149 x 149 x 32
x = self.net.Conv2d_2a_3x3(x)
# 147 x 147 x 32
x = self.net.Conv2d_2b_3x3(x)
# 147 x 147 x 64
x = F.max_pool2d(x, kernel_size=3, stride=2)
# 73 x 73 x 64
x = self.net.Conv2d_3b_1x1(x)
# 73 x 73 x 80
x = self.net.Conv2d_4a_3x3(x)
# 71 x 71 x 192
x = F.max_pool2d(x, kernel_size=3, stride=2)
# 35 x 35 x 192
x = self.net.Mixed_5b(x)
# 35 x 35 x 256
x = self.net.Mixed_5c(x)
# 35 x 35 x 288
x = self.net.Mixed_5d(x)
# 35 x 35 x 288
x = self.net.Mixed_6a(x)
# 17 x 17 x 768
x = self.net.Mixed_6b(x)
# 17 x 17 x 768
x = self.net.Mixed_6c(x)
# 17 x 17 x 768
x = self.net.Mixed_6d(x)
# 17 x 17 x 768
x = self.net.Mixed_6e(x)
# 17 x 17 x 768
# 17 x 17 x 768
x = self.net.Mixed_7a(x)
# 8 x 8 x 1280
x = self.net.Mixed_7b(x)
# 8 x 8 x 2048
x = self.net.Mixed_7c(x)
# 8 x 8 x 2048
pool = torch.mean(x.view(x.size(0), x.size(1), -1), 2)
# 1 x 1 x 2048
logits = self.net.fc(
F.dropout(pool, training=False).view(pool.size(0), -1))
# 1000 (num_classes)
return pool, logits
def _forward(self, x):
# N x 3 x 299 x 299
x = self.Conv2d_1a_3x3(x)
# N x 32 x 149 x 149
x = self.Conv2d_2a_3x3(x)
# N x 32 x 147 x 147
x = self.Conv2d_2b_3x3(x)
# N x 64 x 147 x 147
x = F.max_pool2d(x, kernel_size=3, stride=2)
# N x 64 x 73 x 73
x = self.Conv2d_3b_1x1(x)
# N x 80 x 73 x 73
x = self.Conv2d_4a_3x3(x)
# N x 192 x 71 x 71
x = F.max_pool2d(x, kernel_size=3, stride=2)
# N x 192 x 35 x 35
x = self.Mixed_5b(x)
# N x 256 x 35 x 35
x = self.Mixed_5c(x)
# N x 288 x 35 x 35
x = self.Mixed_5d(x)
# N x 288 x 35 x 35
x = self.Mixed_6a(x)
# N x 768 x 17 x 17
x = self.Mixed_6b(x)
# N x 768 x 17 x 17
x = self.Mixed_6c(x)
# N x 768 x 17 x 17
x = self.Mixed_6d(x)
# N x 768 x 17 x 17
x = self.Mixed_6e(x)
# N x 768 x 17 x 17
aux_defined = self.training and self.aux_logits
if aux_defined:
aux = self.AuxLogits(x)
else:
aux = None
# N x 768 x 17 x 17
x = self.Mixed_7a(x)
# N x 1280 x 8 x 8
x = self.Mixed_7b(x)
# N x 2048 x 8 x 8
x = self.Mixed_7c(x)
# N x 2048 x 8 x 8
# Adaptive average pooling
x = F.adaptive_avg_pool2d(x, (1, 1))
# N x 2048 x 1 x 1
x = F.dropout(x, training=self.training)
# N x 2048 x 1 x 1
x = torch.flatten(x, 1)
# N x 2048
x = self.fc(x)
# N x 1000 (num_classes)
return x, aux
def forward(self, x, y=None):
# Apply convs
theta = self.theta(x)
phi = F.max_pool2d(self.phi(x), [2, 2])
g = F.max_pool2d(self.g(x), [2, 2])
# Perform reshapes
theta = theta.view(-1, self.ch // 8, x.shape[2] * x.shape[3])
phi = phi.view(-1, self.ch // 8, x.shape[2] * x.shape[3] // 4)
g = g.view(-1, self.ch // 2, x.shape[2] * x.shape[3] // 4)
# Matmul and softmax to get attention maps
beta = F.softmax(torch.bmm(theta.transpose(1, 2), phi), -1)
# Attention map times g path
o = self.o(
torch.bmm(g, beta.transpose(1, 2)).view(-1, self.ch // 2,
x.shape[2], x.shape[3]))
return self.gamma * o + x
def _forward(self, x):
branch3x3 = self.branch3x3(x)
branch3x3dbl = self.branch3x3dbl_1(x)
branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)
branch_pool = F.max_pool2d(x, kernel_size=3, stride=2)
outputs = [branch3x3, branch3x3dbl, branch_pool]
return outputs
def _forward(self, x):
branch3x3 = self.branch3x3_1(x)
branch3x3 = self.branch3x3_2(branch3x3)
branch7x7x3 = self.branch7x7x3_1(x)
branch7x7x3 = self.branch7x7x3_2(branch7x7x3)
branch7x7x3 = self.branch7x7x3_3(branch7x7x3)
branch7x7x3 = self.branch7x7x3_4(branch7x7x3)
branch_pool = F.max_pool2d(x, kernel_size=3, stride=2)
outputs = [branch3x3, branch7x7x3, branch_pool]
return outputs