def test_SeparableConv2d_gpu(self):
separ_conv = autograd.SeparableConv2d(8, 16, 3, padding=1)
x = np.random.random((10, 8, 28, 28)).astype(np.float32)
x = tensor.Tensor(device=gpu_dev, data=x)
#y = separ_conv(x)
y1 = separ_conv.spacial_conv(x)
y2 = separ_conv.depth_conv(y1)
dy1, dW_depth, _ = y2.creator.backward(y2.data)
dx, dW_spacial, _ = y1.creator.backward(dy1)
self.check_shape(y2.shape, (10, 16, 28, 28))
self.check_shape(dy1.shape(), (10, 8, 28, 28))
self.check_shape(dW_depth.shape(), (16, 8, 1, 1))
self.check_shape(dx.shape(), (10, 8, 28, 28))
self.check_shape(dW_spacial.shape(), (8, 1, 3, 3))
def __init__(self,
in_filters,
out_filters,
reps,
strides=1,
padding=0,
start_with_relu=True,
grow_first=True):
super(Block, self).__init__()
if out_filters != in_filters or strides != 1:
self.skip = autograd.Conv2d(in_filters,
out_filters,
1,
stride=strides,
padding=padding,
bias=False)
self.skipbn = autograd.BatchNorm2d(out_filters)
else:
self.skip = None
self.layers = []
filters = in_filters
if grow_first:
self.layers.append(autograd.ReLU())
self.layers.append(
autograd.SeparableConv2d(in_filters,
out_filters,
3,
stride=1,
padding=1,
bias=False))
self.layers.append(autograd.BatchNorm2d(out_filters))
filters = out_filters
for i in range(reps - 1):
self.layers.append(autograd.ReLU())
self.layers.append(
autograd.SeparableConv2d(filters,
filters,
3,
stride=1,
padding=1,
bias=False))
self.layers.append(autograd.BatchNorm2d(filters))
if not grow_first:
self.layers.append(autograd.ReLU())
self.layers.append(
autograd.SeparableConv2d(in_filters,
out_filters,
3,
stride=1,
padding=1,
bias=False))
self.layers.append(autograd.BatchNorm2d(out_filters))
if not start_with_relu:
self.layers = self.layers[1:]
else:
self.layers[0] = autograd.ReLU()
if strides != 1:
self.layers.append(autograd.MaxPool2d(3, strides, padding + 1))
def __init__(self, num_classes=1000):
""" Constructor
Args:
num_classes: number of classes
"""
super(Xception, self).__init__()
self.num_classes = num_classes
self.conv1 = autograd.Conv2d(3, 32, 3, 2, 0, bias=False)
self.bn1 = autograd.BatchNorm2d(32)
self.conv2 = autograd.Conv2d(32, 64, 3, 1, 1, bias=False)
self.bn2 = autograd.BatchNorm2d(64)
# do relu here
self.block1 = Block(64,
128,
2,
2,
padding=0,
start_with_relu=False,
grow_first=True)
self.block2 = Block(128,
256,
2,
2,
padding=0,
start_with_relu=True,
grow_first=True)
self.block3 = Block(256,
728,
2,
2,
padding=0,
start_with_relu=True,
grow_first=True)
self.block4 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block5 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block6 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block7 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block8 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block9 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block10 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block11 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block12 = Block(728,
1024,
2,
2,
start_with_relu=True,
grow_first=False)
self.conv3 = autograd.SeparableConv2d(1024, 1536, 3, 1, 1)
self.bn3 = autograd.BatchNorm2d(1536)
# do relu here
self.conv4 = autograd.SeparableConv2d(1536, 2048, 3, 1, 1)
self.bn4 = autograd.BatchNorm2d(2048)
self.globalpooling = autograd.MaxPool2d(10, 1)
self.fc = autograd.Linear(2048, num_classes)