def forward(self, z): x = self.upscale0(z) x = self.res0(x) x = self.upscale1(x) x = self.res1(x) x = self.upscale2(x) x = self.res2(x) if 'd' in opts: x = tf.nn.sigmoid( nn.depth_to_space( tf.concat( (self.out_conv(x), self.out_conv1(x), self.out_conv2(x), self.out_conv3(x)), nn.conv2d_ch_axis), 2)) else: x = tf.nn.sigmoid(self.out_conv(x)) m = self.upscalem0(z) m = self.upscalem1(m) m = self.upscalem2(m) if 'd' in opts: m = self.upscalem3(m) m = tf.nn.sigmoid(self.out_convm(m)) if use_fp16: x = tf.cast(x, tf.float32) m = tf.cast(m, tf.float32) return x, m
def forward(self, inp): x = inp for i in range(len(self.convs)): x = self.convs[i](x) x = self.frns[i](x) x = self.tlus[i](x) if self.use_upscale[i]: x = nn.depth_to_space(x, 2) x = self.out_conv(x) x = tf.nn.sigmoid(x) return x
def forward(self, inp): z = inp x = self.upscale0(z) x = self.res0(x) x = self.upscale1(x) x = self.res1(x) x = self.upscale2(x) x = self.res2(x) x = self.upscale3(x) x = self.res3(x) x = tf.nn.sigmoid( nn.depth_to_space(tf.concat( (self.out_conv(x), self.out_conv1(x), self.out_conv2(x), self.out_conv3(x)), nn.conv2d_ch_axis), 2) ) m = self.upscalem0(z) m = self.upscalem1(m) m = self.upscalem2(m) m = self.upscalem3(m) m = self.upscalem4(m) m = tf.nn.sigmoid(self.out_convm(m)) return x, m
def forward(self, x): x = self.conv1(x) x = tf.nn.leaky_relu(x, 0.1) x = nn.depth_to_space(x, 2) return x
def forward(self, x): x = self.conv1(x) x = nn.gelu(x) x = nn.depth_to_space(x, 2) return x
def forward(self, x): x = nn.depth_to_space(tf.nn.leaky_relu(self.conv1(x), 0.1), 2) return x
def forward(self, x): x = self.conv1(x) x = act(x, 0.1) x = nn.depth_to_space(x, 2) return x