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,
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,
enc_base, dec,
batch_size,
latent_dim = 2,
mode = 'simple',
label_dim = 0,
prior = 'normal',
prior_dist = None,
hidden = 1000,
full_rate=0.1, # 全体の形を重視するかラベル毎を重視するか
fm_rate=1., # full_rateと同じ目的
):
self.latent_dim = latent_dim
self.mode = mode
self.label_dim = label_dim
self.batch_size = batch_size
self.prior = prior
self.prior_dist = prior_dist
self.full_rate = full_rate
self.fm_rate = fm_rate
if self.mode=='clustering' or self.mode=='reduction':
self.enc = Enc(enc_base, (latent_dim, label_dim),
output_act=(None, rm.softmax))
else:
self.enc = Enc(enc_base, latent_dim)
self.dec = dec
self.dis = rm.Sequential([
rm.Dense(hidden), rm.LeakyRelu(),
rm.Dense(hidden), rm.LeakyRelu(),
rm.Dense(1), rm.Sigmoid()
])
if self.mode=='clustering' or self.mode=='reduction':
self.cds = rm.Sequential([
# xxx rm.BatchNormalize(),
# Disの最初にBNは配置してはだめ
rm.Dense(hidden), rm.LeakyRelu(),
rm.BatchNormalize(),
rm.Dense(hidden), rm.LeakyRelu(),
#rm.BatchNormalize(),
rm.Dense(1), rm.Sigmoid()
])
# --- model configuration ---
enc_base = rm.Sequential([
#rm.BatchNormalize(),
rm.Dense(hidden),
rm.Relu(), #rm.Dropout(),
rm.BatchNormalize(),
rm.Dense(hidden),
rm.Relu(), #rm.Dropout(),
# xxx rm.BatchNormalize(),
# Genの最後にBNを配置してはだめ
rm.Dense(latent_dim, initializer=Uniform())
])
dec = rm.Sequential([
#rm.BatchNormalize(),
rm.Dense(hidden),
rm.LeakyRelu(),
rm.BatchNormalize(),
rm.Dense(hidden),
rm.LeakyRelu(),
#rm.BatchNormalize(),
rm.Dense(28 * 28),
rm.Sigmoid()
])
ae = AAE(enc_base,
dec,
batch_size,
latent_dim=latent_dim,
hidden=200,
prior=model_dist,
mode=model_type,
def __init__(self, num_class=1000, load_pretrained_weight=False):
super(Darknet, self).__init__([
# 1st Block
rm.Conv2d(channel=64,
filter=7,
stride=2,
padding=3,
ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.MaxPool2d(stride=2, filter=2),
# 2nd Block
rm.Conv2d(channel=192, filter=3, padding=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.MaxPool2d(stride=2, filter=2),
# 3rd Block
rm.Conv2d(channel=128, filter=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=256, filter=3, padding=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=256, filter=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=512, filter=3, padding=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.MaxPool2d(stride=2, filter=2),
# 4th Block
rm.Conv2d(channel=256, filter=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=512, filter=3, padding=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=256, filter=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=512, filter=3, padding=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=256, filter=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=512, filter=3, padding=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=256, filter=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=512, filter=3, padding=1, ignore_bias=True),
rm.BatchNormalize(mode='feature'),
rm.LeakyRelu(slope=0.1),
rm.Conv2d(channel=512, filter=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.MaxPool2d(stride=2, filter=2),
# 5th Block
rm.Conv2d(channel=512, filter=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.Conv2d(channel=512, filter=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),
# layers for ImageNet
rm.Conv2d(channel=num_class, filter=1),
rm.LeakyRelu(slope=0.1),
rm.AveragePool2d(filter=7),
rm.Softmax()
])
if load_pretrained_weight:
if isinstance(load_pretrained_weight, bool):
load_pretrained_weight = self.__class__.__name__ + '.h5'
if not os.path.exists(load_pretrained_weight):
download(self.WEIGHT_URL, load_pretrained_weight)
self.load(load_pretrained_weight)
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')