def setUp(self):
if self.activ == 'relu':
activ = relu
elif self.activ == 'add_one':
activ = _add_one
self.x = np.random.uniform(
-1, 1, (5, self.in_channels, 5, 5)).astype(np.float32)
self.gy = np.random.uniform(
-1, 1, (5, self.out_channels, 5, 5)).astype(np.float32)
# Convolution is the identity function.
initialW = np.array([[0, 0, 0], [0, 1, 0], [0, 0, 0]],
dtype=np.float32).reshape(1, 1, 3, 3)
initial_bias = 0
if self.args_style == 'explicit':
self.l = Conv2DActiv(
self.in_channels, self.out_channels, self.ksize,
self.stride, self.pad,
initialW=initialW, initial_bias=initial_bias,
activ=activ)
elif self.args_style == 'None':
self.l = Conv2DActiv(
None, self.out_channels, self.ksize, self.stride, self.pad,
initialW=initialW, initial_bias=initial_bias,
activ=activ)
elif self.args_style == 'omit':
self.l = Conv2DActiv(
self.out_channels, self.ksize, stride=self.stride,
pad=self.pad, initialW=initialW, initial_bias=initial_bias,
activ=activ)
def __init__(self, n_class, scales):
super(MaskHead, self).__init__()
initialW = HeNormal(1, fan_option='fan_out')
with self.init_scope():
self.conv1 = Conv2DActiv(256, 3, pad=1, initialW=initialW)
self.conv2 = Conv2DActiv(256, 3, pad=1, initialW=initialW)
self.conv3 = Conv2DActiv(256, 3, pad=1, initialW=initialW)
self.conv4 = Conv2DActiv(256, 3, pad=1, initialW=initialW)
self.conv5 = L.Deconvolution2D(
256, 2, pad=0, stride=2, initialW=initialW)
self.seg = L.Convolution2D(n_class, 1, pad=0, initialW=initialW)
self._n_class = n_class
self._scales = scales
def create_fcn(out_chanels, init_options=None):
default_init = {'initialW': initializers.Normal(0.01)}
if init_options is None:
init_options = [None for _ in out_chanels]
fcn = []
for i in range(len(out_chanels)):
oc = out_chanels[i]
init_option = init_options[i]
if i + 1 < len(out_chanels):
activ = F.relu
else:
activ = None
if init_option is None:
init = default_init
else:
init = init_option
fcn.append(Conv2DActiv(None, oc, 3, 1, 1, activ=activ, **init))
return chainer.Sequential(*fcn)
def __init__(self):
super(MaskRefine, self).__init__()
with self.init_scope():
self.v0 = chainer.Sequential(
Conv2DActiv(64, 16, ksize=3, pad=1),
Conv2DActiv(16, 4, ksize=3, pad=1),
)
self.v1 = chainer.Sequential(
Conv2DActiv(256, 64, ksize=3, pad=1),
Conv2DActiv(64, 16, ksize=3, pad=1),
)
self.v2 = chainer.Sequential(
Conv2DActiv(512, 128, ksize=3, pad=1),
Conv2DActiv(128, 32, ksize=3, pad=1),
)
self.h2 = chainer.Sequential(
Conv2DActiv(32, 32, ksize=3, pad=1),
Conv2DActiv(32, 32, ksize=3, pad=1),
)
self.h1 = chainer.Sequential(
Conv2DActiv(16, 16, ksize=3, pad=1),
Conv2DActiv(16, 16, ksize=3, pad=1),
)
self.h0 = chainer.Sequential(
Conv2DActiv(4, 4, ksize=3, pad=1),
Conv2DActiv(4, 4, ksize=3, pad=1),
)
self.deconv = L.Deconvolution2D(256, 32, ksize=15, stride=15)
self.post0 = L.Convolution2D(32, 16, ksize=3, pad=1)
self.post1 = L.Convolution2D(16, 4, ksize=3, pad=1)
self.post2 = L.Convolution2D(4, 1, ksize=3, pad=1)