def test_gpu_node_tanh(a):
set_cuda_active(True)
g1 = Variable(a)
g3 = rm.sum(rm.tanh(g1))
g = g3.grad()
g_g1 = g.get(g1)
g3.to_cpu()
set_cuda_active(False)
c3 = rm.sum(rm.tanh(g1))
c = c3.grad()
c_g1 = c.get(g1)
close(g3, c3)
close(c_g1, g_g1)
def forward(self, x):
hidden = self.batch(x)
hidden = rm.tanh(hidden)
hidden = self.conv(hidden)
if self.dropout:
hidden = rm.dropout(hidden)
hidden = rm.concat(x, hidden)
if self.depth != 1:
return self.under_model(hidden)
#print(hidden.shape)
return self.output(hidden)
def forward(self, x):
layers = self.hidden._layers
hidden = self.input(x)
i = 0
for _ in range(self.depth):
main_stream = hidden
hidden = layers[i](main_stream)
i += 1
hidden = rm.tanh(hidden)
hidden = layers[i](hidden)
i += 1
if self.dropout:
hidden = rm.dropout(hidden)
hidden = rm.concat(main_stream, hidden)
#print(hidden.shape)
return self.output(hidden)
def forward(self, x):
h = self.transform(x)
#print(h.shape)
h = rm.reshape(h, (len(x), self.channels, self.dim, self.dim))
#print(h.shape)
layers = self.hidden._layers
length = len(layers) if not self.batch_normal else len(layers)//2
for i in range(length):
if self.batch_normal:
h = layers[2*i](h)
h = rm.relu(layers[2*i+1](h))
else:
h = rm.relu(layers[i](h))
#print(h.shape)
h = self.output(h)
#return rm.sigmoid(h)
return rm.tanh(h)
def forward(self, x):
return self.output(rm.tanh(self.hidden(self.input(x))))