def forward(self, x):
x = self.fc0(x)
x = F.tanh(x)
x = self.fc1(x)
x = F.tanh(x)
x = self.fc2(x)
return x
def forward(self, x):
x = self.fc0(x)
x = self.bn0(x)
x = F.softmax(x) if self.converter == "tflite" else F.tanh(x)
x = self.fc1(x)
x = self.bn1(x)
x = F.softmax(x) if self.converter == "tflite" else F.tanh(x)
x = self.fc2(x)
return x
def forward(self, x):
y = self.fc0(x)
x = F.tanh(y)
y = self.fc1(x)
x = F.tanh(y)
x = self.fc2(x)
y = (x + x) / 2 # in order to test drop()
y._drop()
return y
def forward(self, x):
x = self.fc0(x)
x = self.bn0(x)
x = F.leaky_relu(x)
x = F.leaky_relu(x)
x = F.tanh(x)
x = self.fc1(x)
x = F.leaky_relu(x)
x = self.bn1(x)
x = F.tanh(x)
x = self.fc2(x)
x = F.leaky_relu(x)
return x
def gelu(x):
"""Implementation of the gelu activation function.
For information: OpenAI GPT's gelu is slightly different (and gives slightly different results):
x * 0.5 * (1.0 + F.tanh((np.sqrt(2 / np.pi) * (x + 0.044715 * (x ** 3)))))
Also see https://arxiv.org/abs/1606.08415
"""
return x * 0.5 * (1.0 + F.tanh(
(np.sqrt(2 / np.pi) * (x + 0.044715 * (x**3)))))
def forward(self, x):
r"""
Feedforwards a batch of noise vectors into a batch of fake images.
Args:
x (Tensor): A batch of noise vectors of shape (N, nz).
Returns:
Tensor: A batch of fake images of shape (N, C, H, W).
"""
h = self.l1(x)
h = h.reshape(x.shape[0], -1, self.bottom_width, self.bottom_width)
h = self.block2(h)
h = self.block3(h)
h = self.block4(h)
h = self.b5(h)
h = self.activation(h)
h = F.tanh(self.c5(h))
return h
def forward(self, input):
"""
Forward pass of the function.
"""
return input * F.tanh(F.softplus(input))
