def test_gpu_node_leaky_relu(a):
set_cuda_active(True)
g1 = Variable(a)
g3 = sum(rm.leaky_relu(g1))
g = g3.grad()
g_g1 = g.get(g1)
g3.to_cpu()
set_cuda_active(False)
c3 = sum(rm.leaky_relu(g1))
c = c3.grad()
c_g1 = c.get(g1)
close(g3, c3)
close(c_g1, g_g1)
def forward(self, x, print_parameter=False):
hidden = self.input(x)
if print_parameter:
print('{}'.format('-' * 20))
print('check network')
print(x.shape)
print('{}'.format('-' * 20))
if self.dropout:
hidden = rm.dropout(hidden)
hidden = rm.max_pool2d(hidden, stride=1, padding=1)
if print_parameter:
print(hidden.shape)
print('{}'.format('-' * 20))
layers = self.hidden._layers
blocks = self.blocks if isinstance(self.blocks, int) else len(
self.blocks)
for i in range(blocks):
offset = i * (self.depth * 2 + 1)
for j in range(self.depth):
sub = rm.leaky_relu(layers[offset + 2 * j](hidden))
if print_parameter:
print('{}.{} b {}'.format(i, j, sub.shape))
sub = layers[offset + 2 * j + 1](sub)
if print_parameter:
print('{}.{} + {}'.format(i, j, sub.shape))
if self.dropout:
sub = rm.dropout(sub)
hidden = rm.concat(hidden, sub)
if print_parameter:
print('{}.{} = {}'.format(i, j, hidden.shape))
offset = (i + 1) * (self.depth * 2 + 1) - 1
hidden = layers[offset](hidden)
if print_parameter:
print('{}.{} * {}'.format(i, j, hidden.shape))
if self.dropout:
if print_parameter:
print('dropout')
hidden = rm.dropout(hidden)
hidden = rm.average_pool2d(hidden,
padding=1,
stride=(1, 2) if self.keep_v else 2)
if print_parameter:
print('{}.{} @ {}'.format(i, j, hidden.shape))
print('{}'.format('-' * 20))
x = rm.flatten(hidden)
if print_parameter:
print(' >>> {} prameters'.format(x.shape))
return x
def forward(self, x):
return rm.leaky_relu(self._bn(self._conv(x)), 0.1)
def forward(self, x):
h = self.pool1(rm.leaky_relu(self.bn1(self.conv1(x)), slope=0.1))
h = self.pool2(rm.leaky_relu(self.bn2(self.conv2(h)), slope=0.1))
h = rm.leaky_relu(self.bn3(self.conv3(h)), slope=0.1)
h = rm.leaky_relu(self.bn4(self.conv4(h)), slope=0.1)
h = self.pool3(rm.leaky_relu(self.bn5(self.conv5(h)), slope=0.1))
h = rm.leaky_relu(self.bn6(self.conv6(h)), slope=0.1)
h = rm.leaky_relu(self.bn7(self.conv7(h)), slope=0.1)
h = self.pool4(rm.leaky_relu(self.bn8(self.conv8(h)), slope=0.1))
h = rm.leaky_relu(self.bn9(self.conv9(h)), slope=0.1)
h = rm.leaky_relu(self.bn10(self.conv10(h)), slope=0.1)
h = rm.leaky_relu(self.bn11(self.conv11(h)), slope=0.1)
h = rm.leaky_relu(self.bn12(self.conv12(h)), slope=0.1)
h = rm.leaky_relu(self.bn13(self.conv13(h)), slope=0.1)
high_resolution_feature = reorg(h) # 高解像度特徴量をreorgでサイズ落として保存しておく
h = self.pool5(h)
h = rm.leaky_relu(self.bn14(self.conv14(h)), slope=0.1)
h = rm.leaky_relu(self.bn15(self.conv15(h)), slope=0.1)
h = rm.leaky_relu(self.bn16(self.conv16(h)), slope=0.1)
h = rm.leaky_relu(self.bn17(self.conv17(h)), slope=0.1)
h = rm.leaky_relu(self.bn18(self.conv18(h)), slope=0.1)
##### detection layer
h = rm.leaky_relu(self.bn19(self.conv19(h)), slope=0.1)
h = rm.leaky_relu(self.bn20(self.conv20(h)), slope=0.1)
h = rm.concat(high_resolution_feature, h)
h = rm.leaky_relu(self.bn21(self.conv21(h)), slope=0.1)
h = self.conv22(h)
return h
def func(node):
return sum(rm.leaky_relu(node))
def forward(self, x):
h = self.pool1(rm.leaky_relu(self.bn1(self.conv1(x)), slope=0.1))
h = self.pool2(rm.leaky_relu(self.bn2(self.conv2(h)), slope=0.1))
h = rm.leaky_relu(self.bn3(self.conv3(h)), slope=0.1)
h = rm.leaky_relu(self.bn4(self.conv4(h)), slope=0.1)
h = self.pool3(rm.leaky_relu(self.bn5(self.conv5(h)), slope=0.1))
h = rm.leaky_relu(self.bn6(self.conv6(h)), slope=0.1)
h = rm.leaky_relu(self.bn7(self.conv7(h)), slope=0.1)
h = self.pool4(rm.leaky_relu(self.bn8(self.conv8(h)), slope=0.1))
h = rm.leaky_relu(self.bn9(self.conv9(h)), slope=0.1)
h = rm.leaky_relu(self.bn10(self.conv10(h)), slope=0.1)
h = rm.leaky_relu(self.bn11(self.conv11(h)), slope=0.1)
h = rm.leaky_relu(self.bn12(self.conv12(h)), slope=0.1)
h = rm.leaky_relu(self.bn13(self.conv13(h)), slope=0.1)
h = self.pool5(h)
h = rm.leaky_relu(self.bn14(self.conv14(h)), slope=0.1)
h = rm.leaky_relu(self.bn15(self.conv15(h)), slope=0.1)
h = rm.leaky_relu(self.bn16(self.conv16(h)), slope=0.1)
h = rm.leaky_relu(self.bn17(self.conv17(h)), slope=0.1)
h = rm.leaky_relu(self.bn18(self.conv18(h)), slope=0.1)
##### pretraining layer
h = self.conv23(h)
h = rm.average_pool2d(h,
filter=(h.shape[-1], h.shape[-1]),
stride=(1, 1),
padding=(0, 0))
y = rm.reshape(h, (x.shape[0], -1))
return y
def forward(self, inputs):
self.inputs = inputs
h1 = rm.leaky_relu(self.l_1(self.inputs))
h2 = rm.leaky_relu(self.l_2(h1))
h3 = self.l_3(h2)
return h3
