def __init__(self, num_class):
init_deconv = DeconvInitializer()
self.block1 = layer_factory(channel=64, conv_layer_num=2, first=True)
self.block2 = layer_factory(channel=128, conv_layer_num=2)
self.block3 = layer_factory(channel=256, conv_layer_num=3)
self.block4 = layer_factory(channel=512, conv_layer_num=3)
self.block5 = layer_factory(channel=512, conv_layer_num=3)
self.fc6 = rm.Conv2d(4096, filter=7, stride=1, padding=0)
self.dr1 = rm.Dropout(dropout_ratio=0.5)
self.fc7 = rm.Conv2d(4096, filter=1, stride=1, padding=0)
self.dr2 = rm.Dropout(dropout_ratio=0.5)
self.score_fr = rm.Conv2d(num_class, filter=1, stride=1,
padding=0) # n_classes
self.score_pool4 = rm.Conv2d(num_class, filter=1, padding=0)
self.upscore2 = rm.Deconv2d(num_class,
filter=4,
stride=2,
padding=0,
ignore_bias=True,
initializer=init_deconv) # n_classes
self.upscore16 = rm.Deconv2d(num_class,
filter=32,
stride=16,
padding=0,
ignore_bias=True,
initializer=init_deconv) # n_classes
def __init__(self,):
channel = 8
intermidiate_dim = 128
self.cnn1 = rm.Sequential([
# 28x28 -> 28x28
rm.Conv2d(channel=channel,filter=3,stride=1,padding=1),
rm.LeakyRelu(),
rm.Dropout(),
# 28x28 -> 14x14
rm.Conv2d(channel=channel*2,filter=3,stride=2,padding=1),
rm.LeakyRelu(),
rm.Dropout(),
# 14x14 -> 8x8
rm.Conv2d(channel=channel*4,filter=3,stride=2,padding=2),
rm.LeakyRelu(),
rm.Dropout(),
# 8x8 -> 4x4
rm.Conv2d(channel=channel*8,filter=3,stride=2,padding=1),
rm.LeakyRelu(),
rm.Dropout(),
])
self.cnn2 = rm.Sequential([
#rm.Dropout(),
rm.Flatten(),
#rm.Dense(intermidiate_dim)
])
self.output = rm.Dense(1)
def __init__(self, num_class=1000):
self.block1 = layer_factory(channel=64, conv_layer_num=1)
self.block2 = layer_factory(channel=128, conv_layer_num=1)
self.block3 = layer_factory(channel=256, conv_layer_num=2)
self.block4 = layer_factory(channel=512, conv_layer_num=2)
self.block5 = layer_factory(channel=512, conv_layer_num=2)
self.fc1 = rm.Dense(4096)
self.dropout1 = rm.Dropout(dropout_ratio=0.5)
self.fc2 = rm.Dense(4096)
self.dropout2 = rm.Dropout(dropout_ratio=0.5)
self.fc3 = rm.Dense(num_class)
def __init__(self, classes=10):
super(VGG19, self).__init__([
layer_factory(channel=64, conv_layer_num=2),
layer_factory(channel=128, conv_layer_num=2),
layer_factory(channel=256, conv_layer_num=4),
layer_factory(channel=512, conv_layer_num=4),
layer_factory(channel=512, conv_layer_num=4),
rm.Flatten(),
rm.Dense(4096),
rm.Dropout(0.5),
rm.Dense(4096),
rm.Dropout(0.5),
rm.Dense(classes)
])
def __init__(self, num_class):
self.block1 = rm.Sequential([InceptionV4Stem(),
InceptionV4BlockA(),
InceptionV4BlockA(),
InceptionV4BlockA(),
InceptionV4BlockA(),
InceptionV4ReductionA()])
self.block2 = rm.Sequential([
InceptionV4BlockB(),
InceptionV4BlockB(),
InceptionV4BlockB(),
InceptionV4BlockB(),
InceptionV4BlockB(),
InceptionV4BlockB(),
InceptionV4BlockB(),
InceptionV4ReductionB()])
self.block3 = rm.Sequential([
InceptionV4BlockC(),
InceptionV4BlockC(),
InceptionV4BlockC(),
rm.AveragePool2d(filter=8),
rm.Flatten(),
rm.Dropout(0.2)
])
self.fc = rm.Dense(num_class)
def __init__(self, num_class):
self.block1 = layer_factory(channel=64, conv_layer_num=2)
self.block2 = layer_factory(channel=128, conv_layer_num=2)
self.block3 = layer_factory(channel=256, conv_layer_num=3)
self.block4 = layer_factory(channel=512, conv_layer_num=3)
self.block5 = layer_factory(channel=512, conv_layer_num=3)
self.fc6 = rm.Conv2d(4096, filter=7, padding=3)
self.dr1 = rm.Dropout(0.5)
self.fc7 = rm.Conv2d(4096, filter=1)
self.dr2 = rm.Dropout(0.5)
self.score_fr = rm.Conv2d(num_class, filter=1)
self.upscore2 = rm.Deconv2d(num_class, filter=2, stride=2, padding=0)
self.upscore8 = rm.Deconv2d(num_class, filter=8, stride=8, padding=0)
self.score_pool3 = rm.Conv2d(num_class, filter=1)
self.score_pool4 = rm.Conv2d(num_class, filter=1)
self.upscore_pool4 = rm.Deconv2d(num_class,
filter=2,
stride=2,
padding=0)
def test_dropout(tmpdir):
model = rm.Sequential([rm.Dropout(0.5)])
input = renom.Variable(np.random.random((10, 10, 10, 10)))
m = _run_onnx(tmpdir, model, input)
# check input
id_input, = m.graph.node[0].input
assert get_shape(m.graph.input[0]) == input.shape
# check output
assert get_shape(m.graph.output[0]) == input.shape
attrs = dict((a.name, a) for a in m.graph.node[0].attribute)
assert attrs['ratio'].f == 0.5
def __init__(self,
class_map=None,
cells=7,
bbox=2,
imsize=(224, 224),
load_pretrained_weight=False,
train_whole_network=False):
if not hasattr(cells, "__getitem__"):
cells = (cells, cells)
self._cells = cells
self._bbox = bbox
model = Darknet()
super(Yolov1, self).__init__(class_map, imsize, load_pretrained_weight,
train_whole_network, model)
self._last_dense_size = (self.num_class +
5 * bbox) * cells[0] * cells[1]
self._freezed_network = rm.Sequential(model[:-4])
self._network = rm.Sequential([
rm.Conv2d(channel=1024, filter=3, padding=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=1024,
filter=3,
padding=1,
stride=2,
ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=1024, filter=3, padding=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=1024, filter=3, padding=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.Flatten(),
rm.Dense(
4096
), # instead of locally connected layer, we are using Dense layer
rm.LeakyRelu(slope=0.1),
rm.Dropout(0.5),
rm.Dense(self._last_dense_size)
])
self._opt = rm.Sgd(0.0005, 0.9)
def __init__(self,
feature_graph,
num_target=1,
fc_unit=(100, 50),
neighbors=5,
channels=(10, 20, 20)):
super(GCNet, self).__init__()
self.gc1 = GraphCNN(channel=channels[0],
neighbors=neighbors,
feature_graph=feature_graph)
self.gc2 = GraphCNN(channel=channels[1],
neighbors=neighbors,
feature_graph=feature_graph)
self.gc3 = GraphCNN(channel=channels[2],
neighbors=neighbors,
feature_graph=feature_graph)
self.fc1 = rm.Dense(fc_unit[0])
self.fc2 = rm.Dense(fc_unit[1])
self.fc3 = rm.Dense(num_target)
self.dropout = rm.Dropout(dropout_ratio=0.01)
def test_gpu_node_dropout(a):
set_cuda_active(True)
g1 = Variable(a)
layer = rm.Dropout()
np.random.seed(1)
g3 = rm.sum(layer(g1))
g = g3.grad()
g_g1 = g.get(g1)
g3.to_cpu()
set_cuda_active(False)
np.random.seed(1)
c3 = rm.sum(layer(g1))
c = c3.grad()
c_g1 = c.get(g1)
close(g3, c3)
close(c_g1, g_g1)
def __init__(self, last_unit_size, load_weight_path=None):
# TODO: Passing last_unit_size is not good.
assert load_weight_path is None or isinstance(load_weight_path, str)
super(Darknet, self).__init__([
# 1st Block
rm.Conv2d(channel=64, filter=7, stride=2, padding=3),
rm.LeakyRelu(slope=0.1),
rm.MaxPool2d(stride=2, filter=2),
# 2nd Block
rm.Conv2d(channel=192, filter=3, padding=1),
rm.LeakyRelu(slope=0.1),
rm.MaxPool2d(stride=2, filter=2),
# 3rd Block
rm.Conv2d(channel=128, filter=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=256, filter=3, padding=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=256, filter=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=512, filter=3, padding=1),
rm.LeakyRelu(slope=0.1),
rm.MaxPool2d(stride=2, filter=2),
# 4th Block
rm.Conv2d(channel=256, filter=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=512, filter=3, padding=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=256, filter=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=512, filter=3, padding=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=256, filter=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=512, filter=3, padding=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=256, filter=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=512, filter=3, padding=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=512, filter=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=1024, filter=3, padding=1),
rm.LeakyRelu(slope=0.1),
rm.MaxPool2d(stride=2, filter=2),
# 5th Block
rm.Conv2d(channel=512, filter=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=1024, filter=3, padding=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=512, filter=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=1024, filter=3, padding=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=1024, filter=3, padding=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=1024, filter=3, stride=2, padding=1),
rm.LeakyRelu(slope=0.1),
# 6th Block
rm.Conv2d(channel=1024, filter=3, padding=1),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=1024, filter=3, padding=1),
rm.LeakyRelu(slope=0.1),
# 7th Block
rm.Flatten(),
rm.Dense(1024),
rm.LeakyRelu(slope=0.1),
rm.Dense(4096),
rm.LeakyRelu(slope=0.1),
rm.Dropout(0.5),
# 8th Block
rm.Dense(last_unit_size),
])
if load_weight_path is not None:
# Call download method.
path, ext = os.path.splitext(load_weight_path)
if ext:
self.load(load_weight_path)
else:
self.load(path + '.h5')