def __init__(self, num_inter, num_out, dropout_ratio=.5):
kwargs = {
'initialW': normal.Normal(0.01),
'initial_bias': constant.Zero(),
}
super(VGG16BNFC3, self).__init__()
with self.init_scope():
self.conv1_1 = Convolution2D(3, 64, 3, 1, 1, **kwargs)
self.conv1_2 = Convolution2D(64, 64, 3, 1, 1, **kwargs)
self.conv2_1 = Convolution2D(64, 128, 3, 1, 1, **kwargs)
self.conv2_2 = Convolution2D(128, 128, 3, 1, 1, **kwargs)
self.conv3_1 = Convolution2D(128, 256, 3, 1, 1, **kwargs)
self.conv3_2 = Convolution2D(256, 256, 3, 1, 1, **kwargs)
self.conv3_3 = Convolution2D(256, 256, 3, 1, 1, **kwargs)
self.conv4_1 = Convolution2D(256, 512, 3, 1, 1, **kwargs)
self.conv4_2 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv4_3 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_1 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_2 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_3 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.bn1 = L.BatchNormalization(512)
self.fc6 = Linear(512 * 7 * 7, num_inter, **kwargs)
self.bn2 = L.BatchNormalization(num_inter)
self.fc7 = Linear(num_inter, num_inter, **kwargs)
self.bn3 = L.BatchNormalization(num_inter)
self.fc8 = Linear(num_inter, num_out, **kwargs)
self.dropout_ratio = dropout_ratio
def __init__(self, pretrained_model='auto', n_layers=16):
super(VGGLayers, self).__init__()
kwargs = {}
if n_layers not in [16, 19]:
raise ValueError(
'The n_layers argument should be either 16 or 19,'
'but {} was given.'.format(n_layers)
)
with self.init_scope():
self.conv1_1 = Convolution2D(3, 64, 3, 1, 1, **kwargs)
self.conv1_2 = Convolution2D(64, 64, 3, 1, 1, **kwargs)
self.conv2_1 = Convolution2D(64, 128, 3, 1, 1, **kwargs)
self.conv2_2 = Convolution2D(128, 128, 3, 1, 1, **kwargs)
self.conv3_1 = Convolution2D(128, 256, 3, 1, 1, **kwargs)
self.conv3_2 = Convolution2D(256, 256, 3, 1, 1, **kwargs)
self.conv3_3 = Convolution2D(256, 256, 3, 1, 1, **kwargs)
self.conv4_1 = Convolution2D(256, 512, 3, 1, 1, **kwargs)
self.conv4_2 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv4_3 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_1 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_2 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_3 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.fc6 = Linear(512 * 7 * 7, 4096, **kwargs)
self.fc7 = Linear(4096, 4096, **kwargs)
self.fc8 = Linear(4096, 1000, **kwargs)
if n_layers == 19:
self.conv3_4 = Convolution2D(256, 256, 3, 1, 1, **kwargs)
self.conv4_4 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_4 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
def __init__(self, num_inter, num_out):
kwargs = {
'initialW': normal.Normal(0.01),
'initial_bias': constant.Zero(),
}
self.num_out = num_out
super(VGG16, self).__init__()
with self.init_scope():
self.conv1_1 = Convolution2D(3, 64, 3, 1, 1, **kwargs)
self.conv1_2 = Convolution2D(64, 64, 3, 1, 1, **kwargs)
self.conv2_1 = Convolution2D(64, 128, 3, 1, 1, **kwargs)
self.conv2_2 = Convolution2D(128, 128, 3, 1, 1, **kwargs)
self.conv3_1 = Convolution2D(128, 256, 3, 1, 1, **kwargs)
self.conv3_2 = Convolution2D(256, 256, 3, 1, 1, **kwargs)
self.conv3_3 = Convolution2D(256, 256, 3, 1, 1, **kwargs)
self.conv4_1 = Convolution2D(256, 512, 3, 1, 1, **kwargs)
self.conv4_2 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv4_3 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_1 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_2 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_3 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.fc6 = Linear(512 * 7 * 7, num_inter, **kwargs)
self.fc7 = Linear(num_inter, num_inter, **kwargs)
self.fc8 = Linear(num_inter, num_out, **kwargs)
def __init__(self, pretrained_model='auto', n_layers=16):
super(VGGLayers, self).__init__()
if pretrained_model:
# As a sampling process is time-consuming,
# we employ a zero initializer for faster computation.
init = constant.Zero()
kwargs = {'initialW': init, 'initial_bias': init}
else:
# employ default initializers used in the original paper
kwargs = {
'initialW': normal.Normal(0.01),
'initial_bias': constant.Zero(),
}
if n_layers not in [16, 19]:
raise ValueError(
'The n_layers argument should be either 16 or 19, '
'but {} was given.'.format(n_layers)
)
with self.init_scope():
self.conv1_1 = Convolution2D(3, 64, 3, 1, 1, **kwargs)
self.conv1_2 = Convolution2D(64, 64, 3, 1, 1, **kwargs)
self.conv2_1 = Convolution2D(64, 128, 3, 1, 1, **kwargs)
self.conv2_2 = Convolution2D(128, 128, 3, 1, 1, **kwargs)
self.conv3_1 = Convolution2D(128, 256, 3, 1, 1, **kwargs)
self.conv3_2 = Convolution2D(256, 256, 3, 1, 1, **kwargs)
self.conv3_3 = Convolution2D(256, 256, 3, 1, 1, **kwargs)
self.conv4_1 = Convolution2D(256, 512, 3, 1, 1, **kwargs)
self.conv4_2 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv4_3 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_1 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_2 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_3 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.fc6 = Linear(512 * 7 * 7, 4096, **kwargs)
self.fc7 = Linear(4096, 4096, **kwargs)
self.fc8 = Linear(4096, 1000, **kwargs)
if n_layers == 19:
self.conv3_4 = Convolution2D(256, 256, 3, 1, 1, **kwargs)
self.conv4_4 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_4 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
if pretrained_model == 'auto':
if n_layers == 16:
_retrieve(
'VGG_ILSVRC_16_layers.npz',
'https://www.robots.ox.ac.uk/%7Evgg/software/very_deep/'
'caffe/VGG_ILSVRC_16_layers.caffemodel',
self)
else:
_retrieve(
'VGG_ILSVRC_19_layers.npz',
'http://www.robots.ox.ac.uk/%7Evgg/software/very_deep/'
'caffe/VGG_ILSVRC_19_layers.caffemodel',
self)
elif pretrained_model:
npz.load_npz(pretrained_model, self)
def __init__(self, pretrained_model='auto'):
if pretrained_model:
# As a sampling process is time-consuming,
# we employ a zero initializer for faster computation.
init = constant.Zero()
conv_kwargs = {'initialW': init, 'initial_bias': init}
fc_kwargs = conv_kwargs
else:
# employ default initializers used in the original paper
conv_kwargs = {
'initialW': normal.Normal(0.01),
'initial_bias': constant.Zero(),
}
fc_kwargs = {
'initialW': normal.Normal(0.005),
'initial_bias': constant.One(),
}
super(C3DVersion1, self).__init__(
conv1a=ConvolutionND(3, 3, 64, 3, 1, 1, **conv_kwargs),
conv2a=ConvolutionND(3, 64, 128, 3, 1, 1, **conv_kwargs),
conv3a=ConvolutionND(3, 128, 256, 3, 1, 1, **conv_kwargs),
conv3b=ConvolutionND(3, 256, 256, 3, 1, 1, **conv_kwargs),
conv4a=ConvolutionND(3, 256, 512, 3, 1, 1, **conv_kwargs),
conv4b=ConvolutionND(3, 512, 512, 3, 1, 1, **conv_kwargs),
conv5a=ConvolutionND(3, 512, 512, 3, 1, 1, **conv_kwargs),
conv5b=ConvolutionND(3, 512, 512, 3, 1, 1, **conv_kwargs),
fc6=Linear(512 * 4 * 4, 4096, **fc_kwargs),
fc7=Linear(4096, 4096, **fc_kwargs),
fc8=Linear(4096, 101, **fc_kwargs),
)
if pretrained_model == 'auto':
_retrieve(
'conv3d_deepnetA_ucf.npz', 'http://vlg.cs.dartmouth.edu/c3d/'
'c3d_ucf101_finetune_whole_iter_20000', self)
elif pretrained_model:
npz.load_npz(pretrained_model, self)
self.functions = collections.OrderedDict([
('conv1a', [self.conv1a, relu]),
('pool1', [_max_pooling_2d]),
('conv2a', [self.conv2a, relu]),
('pool2', [_max_pooling_3d]),
('conv3a', [self.conv3a, relu]),
('conv3b', [self.conv3b, relu]),
('pool3', [_max_pooling_3d]),
('conv4a', [self.conv4a, relu]),
('conv4b', [self.conv4b, relu]),
('pool4', [_max_pooling_3d]),
('conv5a', [self.conv5a, relu]),
('conv5b', [self.conv5b, relu]),
('pool5', [_max_pooling_3d]),
('fc6', [self.fc6, relu, dropout]),
('fc7', [self.fc7, relu, dropout]),
('fc8', [self.fc8]),
('prob', [softmax]),
])
def __init__(self, pretrained_model='auto'):
super(GoogLeNet, self).__init__(
conv1=Convolution2D(3, 64, 7, stride=2, pad=3),
conv2_reduce=Convolution2D(64, 64, 1),
conv2=Convolution2D(64, 192, 3, stride=1, pad=1),
inc3a=Inception(192, 64, 96, 128, 16, 32, 32),
inc3b=Inception(256, 128, 128, 192, 32, 96, 64),
inc4a=Inception(480, 192, 96, 208, 16, 48, 64),
inc4b=Inception(512, 160, 112, 224, 24, 64, 64),
inc4c=Inception(512, 128, 128, 256, 24, 64, 64),
inc4d=Inception(512, 112, 144, 288, 32, 64, 64),
inc4e=Inception(528, 256, 160, 320, 32, 128, 128),
inc5a=Inception(832, 256, 160, 320, 32, 128, 128),
inc5b=Inception(832, 384, 192, 384, 48, 128, 128),
loss3_fc=Linear(1024, 1000),
loss1_conv=Convolution2D(512, 128, 1),
loss1_fc1=Linear(4 * 4 * 128, 1024),
loss1_fc2=Linear(1024, 1000),
loss2_conv=Convolution2D(528, 128, 1),
loss2_fc1=Linear(4 * 4 * 128, 1024),
loss2_fc2=Linear(1024, 1000),
)
if pretrained_model == 'auto':
_retrieve(
'bvlc_googlenet.npz',
'http://dl.caffe.berkeleyvision.org/bvlc_googlenet.caffemodel',
self)
elif pretrained_model:
npz.load_npz(pretrained_model, self)
self.functions = OrderedDict([
('conv1', [self.conv1, relu]),
('pool1', [
lambda x: max_pooling_2d(x, ksize=3, stride=2),
lambda x: local_response_normalization(x, n=5)
]), ('conv2_reduce', [self.conv2_reduce, relu]),
('conv2', [self.conv2, relu]),
('pool2', [
lambda x: local_response_normalization(x, n=5),
lambda x: max_pooling_2d(x, ksize=3, stride=2)
]), ('inc3a', [self.inc3a]), ('inc3b', [self.inc3b]),
('pool3', [lambda x: max_pooling_2d(x, ksize=3, stride=2)]),
('inc4a', [self.inc4a]), ('inc4b', [self.inc4b]),
('inc4c', [self.inc4c]), ('inc4d', [self.inc4d]),
('inc4e', [self.inc4e]),
('pool4', [lambda x: max_pooling_2d(x, ksize=3, stride=2)]),
('inc5a', [self.inc5a]), ('inc5b', [self.inc5b]),
('pool6', [lambda x: average_pooling_2d(x, ksize=7, stride=1)]),
('prob', [lambda x: dropout(x, ratio=0.4), self.loss3_fc])
])
def __init__(self, pretrained_model, n_layers):
super(ResNetLayers, self).__init__()
if pretrained_model:
# As a sampling process is time-consuming,
# we employ a zero initializer for faster computation.
kwargs = {'initialW': constant.Zero()}
else:
# employ default initializers used in the original paper
kwargs = {'initialW': normal.HeNormal(scale=1.0)}
if n_layers == 50:
block = [3, 4, 6, 3]
elif n_layers == 101:
block = [3, 4, 23, 3]
elif n_layers == 152:
block = [3, 8, 36, 3]
else:
raise ValueError('The n_layers argument should be either 50, 101,'
' or 152, but {} was given.'.format(n_layers))
with self.init_scope():
self.conv1 = Convolution2D(3, 64, 7, 2, 3, **kwargs)
self.bn1 = BatchNormalization(64)
self.res2 = BuildingBlock(block[0], 64, 64, 256, 1, **kwargs)
self.res3 = BuildingBlock(block[1], 256, 128, 512, 2, **kwargs)
self.res4 = BuildingBlock(block[2], 512, 256, 1024, 2, **kwargs)
self.res5 = BuildingBlock(block[3], 1024, 512, 2048, 2, **kwargs)
self.fc6 = Linear(2048, 1000)
if pretrained_model and pretrained_model.endswith('.caffemodel'):
_retrieve(n_layers, 'ResNet-{}-model.npz'.format(n_layers),
pretrained_model, self)
elif pretrained_model:
npz.load_npz(pretrained_model, self)
def __init__(self, pretrained_model='auto'):
if pretrained_model:
# As a sampling process is time-consuming,
# we employ a zero initializer for faster computation.
kwargs = {'initialW': constant.Zero()}
else:
# employ default initializers used in the original paper
kwargs = {'initialW': normal.HeNormal(scale=1.0)}
super(ResNet50Layers, self).__init__(
conv1=Convolution2D(3, 64, 7, 2, 3, **kwargs),
bn1=BatchNormalization(64),
res2=BuildingBlock(3, 64, 64, 256, 1, **kwargs),
res3=BuildingBlock(4, 256, 128, 512, 2, **kwargs),
res4=BuildingBlock(6, 512, 256, 1024, 2, **kwargs),
res5=BuildingBlock(3, 1024, 512, 2048, 2, **kwargs),
fc6=Linear(2048, 1000),
)
if pretrained_model == 'auto':
_retrieve(
'ResNet-50-model.npz', 'ResNet-50-model.caffemodel', self)
elif pretrained_model:
npz.load_npz(pretrained_model, self)
self.functions = OrderedDict([
('conv1', [self.conv1, self.bn1, relu]),
('pool1', [lambda x: max_pooling_2d(x, ksize=3, stride=2)]),
('res2', [self.res2]),
('res3', [self.res3]),
('res4', [self.res4]),
('res5', [self.res5]),
('pool5', [_global_average_pooling_2d]),
('fc6', [self.fc6]),
('prob', [softmax]),
])
def __init__(self, pretrained_model='auto', n_layers=50):
super(ExtractorResNet, self).__init__()
print('Extractor ResNet', n_layers, ' initialization')
kwargs = {'initialW': constant.Zero()}
if pretrained_model == 'auto':
if n_layers == 50:
pretrained_model = 'ResNet-50-model.caffemodel'
block = [3, 4, 6, 3]
elif n_layers == 101:
pretrained_model = 'ResNet-101-model.caffemodel'
block = [3, 4, 23, 3]
with self.init_scope():
self.conv1 = Convolution2D(3, 64, 7, 2, 3, **kwargs)
self.bn1 = BatchNormalization(64)
self.res2 = BuildingBlock(block[0], 64, 64, 256, 1, **kwargs)
self.res3 = BuildingBlock(block[1], 256, 128, 512, 2, **kwargs)
self.res4 = BuildingBlock(block[2], 512, 256, 1024, 2, **kwargs)
self.res5 = BuildingBlock(block[3], 1024, 512, 2048, 1, **kwargs)
self.fc6 = Linear(2048, 1000)
if pretrained_model and pretrained_model.endswith('.caffemodel'):
_retrieve(n_layers, 'ResNet-{}-model.npz'.format(n_layers),
pretrained_model, self)
elif pretrained_model:
npz.load_npz(pretrained_model, self)
del self.fc6
def __init__(self, pretrained_model='auto'):
if pretrained_model:
# As a sampling process is time-consuming,
# we employ a zero initializer for faster computation.
kwargs = {'initialW': constant.Zero()}
else:
# employ default initializers used in BVLC. For more detail, see
# https://github.com/chainer/chainer/pull/2424#discussion_r109642209
kwargs = {'initialW': uniform.LeCunUniform(scale=1.0)}
super(GoogLeNet,
self).__init__(conv1=Convolution2D(3,
64,
7,
stride=2,
pad=3,
**kwargs),
conv2_reduce=Convolution2D(64, 64, 1, **kwargs),
conv2=Convolution2D(64,
192,
3,
stride=1,
pad=1,
**kwargs),
inc3a=Inception(192, 64, 96, 128, 16, 32, 32),
inc3b=Inception(256, 128, 128, 192, 32, 96, 64),
inc4a=Inception(480, 192, 96, 208, 16, 48, 64),
inc4b=Inception(512, 160, 112, 224, 24, 64, 64),
inc4c=Inception(512, 128, 128, 256, 24, 64, 64),
inc4d=Inception(512, 112, 144, 288, 32, 64, 64),
inc4e=Inception(528, 256, 160, 320, 32, 128, 128),
inc5a=Inception(832, 256, 160, 320, 32, 128, 128),
inc5b=Inception(832, 384, 192, 384, 48, 128, 128),
loss3_fc=Linear(1024, 1000, **kwargs),
loss1_conv=Convolution2D(512, 128, 1, **kwargs),
loss1_fc1=Linear(2048, 1024, **kwargs),
loss1_fc2=Linear(1024, 1000, **kwargs),
loss2_conv=Convolution2D(528, 128, 1, **kwargs),
loss2_fc1=Linear(2048, 1024, **kwargs),
loss2_fc2=Linear(1024, 1000, **kwargs))
if pretrained_model == 'auto':
_retrieve(
'bvlc_googlenet.npz',
'http://dl.caffe.berkeleyvision.org/bvlc_googlenet.caffemodel',
self)
elif pretrained_model:
npz.load_npz(pretrained_model, self)
def __init__(self, n_out, entropy_weight):
super(ResNet50Layers_transfer, self).__init__()
with self.init_scope():
self.base = ResNet50Layers(pretrained_model='auto')
self.fc7 = Linear(None, n_out)
#self.base=base
self.entropy_weight = entropy_weight
self.n_out = n_out
def __init__(self, pretrained_model='auto'):
if pretrained_model:
# As a sampling process is time-consuming,
# we employ a zero initializer for faster computation.
init = constant.Zero()
kwargs = {'initialW': init, 'initial_bias': init}
else:
# employ default initializers used in the original paper
kwargs = {
'initialW': normal.Normal(0.01),
'initial_bias': constant.Zero(),
}
super(VGG16Layers, self).__init__()
with self.init_scope():
self.conv1_1 = Convolution2D(3, 64, 3, 1, 1, **kwargs)
self.conv1_2 = Convolution2D(64, 64, 3, 1, 1, **kwargs)
self.conv2_1 = Convolution2D(64, 128, 3, 1, 1, **kwargs)
self.conv2_2 = Convolution2D(128, 128, 3, 1, 1, **kwargs)
self.conv3_1 = Convolution2D(128, 256, 3, 1, 1, **kwargs)
self.conv3_2 = Convolution2D(256, 256, 3, 1, 1, **kwargs)
self.conv3_3 = Convolution2D(256, 256, 3, 1, 1, **kwargs)
self.conv4_1 = Convolution2D(256, 512, 3, 1, 1, **kwargs)
self.conv4_2 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv4_3 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_1 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_2 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.conv5_3 = Convolution2D(512, 512, 3, 1, 1, **kwargs)
self.fc6 = Linear(512 * 7 * 7, 4096, **kwargs)
self.fc7 = Linear(4096, 4096, **kwargs)
self.fc8 = Linear(4096, 1000, **kwargs)
if pretrained_model == 'auto':
_retrieve(
'VGG_ILSVRC_16_layers.npz',
'http://www.robots.ox.ac.uk/%7Evgg/software/very_deep/'
'caffe/VGG_ILSVRC_16_layers.caffemodel',
self)
elif pretrained_model:
npz.load_npz(pretrained_model, self)
def __init__(self, n_joints):
super(VGG16_conv3_3, self).__init__()
with self.init_scope():
self.conv1_1 = Convolution2D(3, 64, 3, 1, 1)
self.conv1_2 = Convolution2D(64, 64, 3, 1, 1)
self.conv2_1 = Convolution2D(64, 128, 3, 1, 1)
self.conv2_2 = Convolution2D(128, 128, 3, 1, 1)
self.conv3_1 = Convolution2D(128, 256, 3, 1, 1)
self.conv3_2 = Convolution2D(256, 256, 3, 1, 1)
self.conv3_3 = Convolution2D(256, 256, 3, 1, 1)
self.conv4_1 = Convolution2D(256, 512, 3, 1, 1)
self.conv4_2 = Convolution2D(512, 512, 3, 1, 1)
self.conv4_3 = Convolution2D(512, 512, 3, 1, 1)
self.conv5_1 = Convolution2D(512, 512, 3, 1, 1)
self.conv5_2 = Convolution2D(512, 512, 3, 1, 1)
self.conv5_3 = Convolution2D(512, 512, 3, 1, 1)
self.bn1 = BatchNormalization(512)
self.fc6 = Linear(None, 4096)
self.bn2 = BatchNormalization(4096)
self.fc7 = Linear(4096, 4096)
self.bn3 = BatchNormalization(4096)
self.fc8 = Linear(4096, n_joints * 2)
def __init__(self, pretrained_model, n_layers):
super(ResNetLayers, self).__init__()
if pretrained_model:
# As a sampling process is time-consuming,
# we employ a zero initializer for faster computation.
kwargs = {'initialW': constant.Zero()}
else:
# employ default initializers used in the original paper
kwargs = {'initialW': normal.HeNormal(scale=1.0)}
if n_layers == 50:
block = [3, 4, 6, 3]
elif n_layers == 101:
block = [3, 4, 23, 3]
elif n_layers == 152:
block = [3, 8, 36, 3]
else:
raise ValueError('The n_layers argument should be either 50, 101,'
' or 152, but {} was given.'.format(n_layers))
with self.init_scope():
self.conv1 = Convolution2D(3, 64, 7, 2, 3, **kwargs)
self.bn1 = BatchNormalization(64)
self.res2 = BuildingBlock(block[0], 64, 64, 256, 1, **kwargs)
self.res3 = BuildingBlock(block[1], 256, 128, 512, 2, **kwargs)
self.res4 = BuildingBlock(block[2], 512, 256, 1024, 2, **kwargs)
self.res5 = BuildingBlock(block[3], 1024, 512, 2048, 2, **kwargs)
self.fc6 = Linear(2048, 1000)
if pretrained_model and pretrained_model.endswith('.caffemodel'):
_retrieve(n_layers, 'ResNet-{}-model.npz'.format(n_layers),
pretrained_model, self)
elif pretrained_model:
npz.load_npz(pretrained_model, self)
self.functions = collections.OrderedDict([
('conv1', [self.conv1, self.bn1, relu]),
('pool1', [lambda x: max_pooling_2d(x, ksize=3, stride=2)]),
('res2', [self.res2]),
('res3', [self.res3]),
('res4', [self.res4]),
('res5', [self.res5]),
('pool5', [_global_average_pooling_2d]),
('fc6', [self.fc6]),
('prob', [softmax]),
])
def __init__(self, pretrained_model='auto'):
if pretrained_model:
# As a sampling process is time-consuming,
# we employ a zero initializer for faster computation.
kwargs = {'initialW': constant.Zero()}
else:
# employ default initializers used in the original paper
kwargs = {'initialW': uniform.GlorotUniform(scale=1.0)}
super(GoogLeNet,
self).__init__(conv1=Convolution2D(3,
64,
7,
stride=2,
pad=3,
**kwargs),
conv2_reduce=Convolution2D(64, 64, 1, **kwargs),
conv2=Convolution2D(64,
192,
3,
stride=1,
pad=1,
**kwargs),
inc3a=Inception(192, 64, 96, 128, 16, 32, 32),
inc3b=Inception(256, 128, 128, 192, 32, 96, 64),
inc4a=Inception(480, 192, 96, 208, 16, 48, 64),
inc4b=Inception(512, 160, 112, 224, 24, 64, 64),
inc4c=Inception(512, 128, 128, 256, 24, 64, 64),
inc4d=Inception(512, 112, 144, 288, 32, 64, 64),
inc4e=Inception(528, 256, 160, 320, 32, 128, 128),
inc5a=Inception(832, 256, 160, 320, 32, 128, 128),
inc5b=Inception(832, 384, 192, 384, 48, 128, 128),
loss3_fc=Linear(1024, 1000, **kwargs),
loss1_conv=Convolution2D(512, 128, 1, **kwargs),
loss1_fc1=Linear(2048, 1024, **kwargs),
loss1_fc2=Linear(1024, 1000, **kwargs),
loss2_conv=Convolution2D(528, 128, 1, **kwargs),
loss2_fc1=Linear(2048, 1024, **kwargs),
loss2_fc2=Linear(1024, 1000, **kwargs))
if pretrained_model == 'auto':
_retrieve(
'bvlc_googlenet.npz',
'http://dl.caffe.berkeleyvision.org/bvlc_googlenet.caffemodel',
self)
elif pretrained_model:
npz.load_npz(pretrained_model, self)
self.functions = OrderedDict([
('conv1', [self.conv1, relu]),
('pool1', [_max_pooling_2d, _local_response_normalization]),
('conv2_reduce', [self.conv2_reduce, relu]),
('conv2', [self.conv2, relu, _local_response_normalization]),
('pool2', [_max_pooling_2d]),
('inception_3a', [self.inc3a]),
('inception_3b', [self.inc3b]),
('pool3', [_max_pooling_2d]),
('inception_4a', [self.inc4a]),
('inception_4b', [self.inc4b]),
('inception_4c', [self.inc4c]),
('inception_4d', [self.inc4d]),
('inception_4e', [self.inc4e]),
('pool4', [_max_pooling_2d]),
('inception_5a', [self.inc5a]),
('inception_5b', [self.inc5b]),
('pool5', [_average_pooling_2d_k7]),
('loss3_fc', [_dropout, self.loss3_fc]),
('prob', [softmax]),
# Since usually the following outputs are not used, they are put
# after 'prob' to be skipped for efficiency.
('loss1_fc2', [
_average_pooling_2d_k5, self.loss1_conv, relu, self.loss1_fc1,
relu, self.loss1_fc2
]),
('loss2_fc2', [
_average_pooling_2d_k5, self.loss2_conv, relu, self.loss2_fc1,
relu, self.loss2_fc2
])
])
def __init__(self):
super().__init__()
with self.init_scope():
self.conv_input = Convolution2D(3,
64,
ksize=3,
stride=1,
pad=0,
initialW=Normal(0.02))
self.c1 = Convolution2D(64,
64,
ksize=3,
stride=2,
pad=0,
initialW=Normal(0.02))
self.bn1 = BatchNormalization(64)
self.c2 = Convolution2D(64,
128,
ksize=3,
stride=1,
pad=0,
initialW=Normal(0.02))
self.bn2 = BatchNormalization(128)
self.c3 = Convolution2D(128,
128,
ksize=3,
stride=2,
pad=0,
initialW=Normal(0.02))
self.bn3 = BatchNormalization(128)
self.c4 = Convolution2D(128,
256,
ksize=3,
stride=1,
pad=0,
initialW=Normal(0.02))
self.bn4 = BatchNormalization(256)
self.c5 = Convolution2D(256,
256,
ksize=3,
stride=2,
pad=0,
initialW=Normal(0.02))
self.bn5 = BatchNormalization(256)
self.c6 = Convolution2D(256,
512,
ksize=3,
stride=1,
pad=0,
initialW=Normal(0.02))
self.bn6 = BatchNormalization(512)
self.c7 = Convolution2D(512,
512,
ksize=3,
stride=2,
pad=0,
initialW=Normal(0.02))
self.bn7 = BatchNormalization(512)
self.linear1 = Linear(in_size=4608, out_size=1024)
self.linear2 = Linear(in_size=None, out_size=2)
def __init__(self,
pretrained_model='auto',
n_channels=3,
n_outputs=101,
mean_path='datasets/models/mean2.npz'):
super(C3DVersion1UCF101, self).__init__()
if pretrained_model:
# As a sampling process is time-consuming,
# we employ a zero initializer for faster computation.
init = constant.Zero()
conv_kwargs = {'initialW': init, 'initial_bias': init}
fc_kwargs = conv_kwargs
else:
# employ default initializers used in the original paper
conv_kwargs = {
'initialW': normal.Normal(0.01),
'initial_bias': constant.Zero(),
}
fc_kwargs = {
'initialW': normal.Normal(0.005),
'initial_bias': constant.One(),
}
with self.init_scope():
self.conv1a = ConvolutionND(3, n_channels, 64, 3, 1, 1,
**conv_kwargs)
self.conv2a = ConvolutionND(3, 64, 128, 3, 1, 1, **conv_kwargs)
self.conv3a = ConvolutionND(3, 128, 256, 3, 1, 1, **conv_kwargs)
self.conv3b = ConvolutionND(3, 256, 256, 3, 1, 1, **conv_kwargs)
self.conv4a = ConvolutionND(3, 256, 512, 3, 1, 1, **conv_kwargs)
self.conv4b = ConvolutionND(3, 512, 512, 3, 1, 1, **conv_kwargs)
self.conv5a = ConvolutionND(3, 512, 512, 3, 1, 1, **conv_kwargs)
self.conv5b = ConvolutionND(3, 512, 512, 3, 1, 1, **conv_kwargs)
self.fc6 = Linear(512 * 4 * 4, 4096, **fc_kwargs)
self.fc7 = Linear(4096, 4096, **fc_kwargs)
self.fc8 = Linear(4096, n_outputs, **fc_kwargs)
if pretrained_model == 'auto':
_retrieve(
'conv3d_deepnetA_ucf.npz', 'http://vlg.cs.dartmouth.edu/c3d/'
'c3d_ucf101_finetune_whole_iter_20000', self)
elif pretrained_model:
npz.load_npz(pretrained_model, self)
self.pre = ConvolutionND(3,
n_channels,
n_channels,
1,
1,
0,
nobias=True,
**conv_kwargs)
self.pre.W.data[:] = 0
self.pre.W.data[[0, 1, 2], [2, 1, 0]] = 128
# self.pre.b.data[:] = 128 - numpy.array([90.25164795, 97.65701294, 101.4083252])
self.mean = Bias(shape=(3, 16, 112, 112))
mean = numpy.load(mean_path)['mean']
self.mean.b.data[:] = 128 - mean[:, :, 8:8 + 112, 8:8 + 112]
self.functions = collections.OrderedDict([
('pre', [self.pre, _resize, self.mean]),
('conv1a', [self.conv1a, relu]),
('pool1', [_max_pooling_2d]),
('conv2a', [self.conv2a, relu]),
('pool2', [_max_pooling_3d]),
('conv3a', [self.conv3a, relu]),
('conv3b', [self.conv3b, relu]),
('pool3', [_max_pooling_3d]),
('conv4a', [self.conv4a, relu]),
('conv4b', [self.conv4b, relu]),
('pool4', [_max_pooling_3d]),
('conv5a', [self.conv5a, relu]),
('conv5b', [self.conv5b, relu]),
('pool5', [_max_pooling_3d, dropout]),
('fc6', [self.fc6, relu, dropout]),
('fc7', [self.fc7, relu, dropout]),
('fc8', [self.fc8]),
('prob', [softmax]),
])
def __init__(self, pretrained_model='auto'):
if pretrained_model:
# As a sampling process is time-consuming,
# we employ a zero initializer for faster computation.
init = constant.Zero()
kwargs = {'initialW': init, 'initial_bias': init}
else:
# employ default initializers used in the original paper
kwargs = {
'initialW': normal.Normal(0.01),
'initial_bias': constant.Zero(),
}
super(VGG16Layers, self).__init__(
conv1_1=Convolution2D(3, 64, 3, 1, 1, **kwargs),
conv1_2=Convolution2D(64, 64, 3, 1, 1, **kwargs),
conv2_1=Convolution2D(64, 128, 3, 1, 1, **kwargs),
conv2_2=Convolution2D(128, 128, 3, 1, 1, **kwargs),
conv3_1=Convolution2D(128, 256, 3, 1, 1, **kwargs),
conv3_2=Convolution2D(256, 256, 3, 1, 1, **kwargs),
conv3_3=Convolution2D(256, 256, 3, 1, 1, **kwargs),
conv4_1=Convolution2D(256, 512, 3, 1, 1, **kwargs),
conv4_2=Convolution2D(512, 512, 3, 1, 1, **kwargs),
conv4_3=Convolution2D(512, 512, 3, 1, 1, **kwargs),
conv5_1=Convolution2D(512, 512, 3, 1, 1, **kwargs),
conv5_2=Convolution2D(512, 512, 3, 1, 1, **kwargs),
conv5_3=Convolution2D(512, 512, 3, 1, 1, **kwargs),
fc6=Linear(512 * 7 * 7, 4096, **kwargs),
fc7=Linear(4096, 4096, **kwargs),
fc8=Linear(4096, 1000, **kwargs),
)
if pretrained_model == 'auto':
_retrieve(
'VGG_ILSVRC_16_layers.npz',
'http://www.robots.ox.ac.uk/%7Evgg/software/very_deep/'
'caffe/VGG_ILSVRC_16_layers.caffemodel', self)
elif pretrained_model:
npz.load_npz(pretrained_model, self)
self.functions = collections.OrderedDict([
('conv1_1', [self.conv1_1, relu]),
('conv1_2', [self.conv1_2, relu]),
('pool1', [_max_pooling_2d]),
('conv2_1', [self.conv2_1, relu]),
('conv2_2', [self.conv2_2, relu]),
('pool2', [_max_pooling_2d]),
('conv3_1', [self.conv3_1, relu]),
('conv3_2', [self.conv3_2, relu]),
('conv3_3', [self.conv3_3, relu]),
('pool3', [_max_pooling_2d]),
('conv4_1', [self.conv4_1, relu]),
('conv4_2', [self.conv4_2, relu]),
('conv4_3', [self.conv4_3, relu]),
('pool4', [_max_pooling_2d]),
('conv5_1', [self.conv5_1, relu]),
('conv5_2', [self.conv5_2, relu]),
('conv5_3', [self.conv5_3, relu]),
('pool5', [_max_pooling_2d]),
('fc6', [self.fc6, relu, dropout]),
('fc7', [self.fc7, relu, dropout]),
('fc8', [self.fc8, relu]),
('prob', [softmax]),
])
