def __init__(self):
super(DenseNet, self).__init__()
with self.name_scope():
self.features = nn.HybridSequential()
self.features.add(
nn.Conv2D(64, 3, padding=1, use_bias=False),
nn.BatchNorm(),
nn.Activation('relu'),
# nn.MaxPool2D(pool_size=2, strides=2),
nn.Conv2D(64, 2, strides=2, use_bias=False),
)
self.features.add(_make_dense_block(8, 4, 8, 0, 1))
self.features.add(_make_transition(128, 2, 0, 0.2))
self.features.add(_make_dense_block(8, 4, 8, 0, 2))
self.features.add(_make_transition(192, (2, 1), (0, 1), 0.2))
self.features.add(_make_dense_block(8, 4, 8, 0, 3))
self.features.add(
nn.BatchNorm(), nn.Activation('relu'),
nn.Conv2D(512, 3, padding=0, use_bias=False), nn.BatchNorm(),
nn.Activation('relu'),
nn.Conv2D(1024, 2, padding=(0, 1), use_bias=False),
nn.BatchNorm(), nn.Activation('relu'))
def __init__(self):
super(DenseNet, self).__init__()
with self.name_scope():
self.features = nn.HybridSequential()
self.features.add(
nn.Conv2D(64, 5, padding=2, strides=2, use_bias=False))
self.features.add(_make_dense_block(8, 4, 8, 0, 1))
self.features.add(_make_transition(128, 2, 0, 0.2))
self.features.add(_make_dense_block(8, 4, 8, 0, 2))
self.features.add(_make_transition(128, (2, 1), 0, 0.2))
self.features.add(_make_dense_block(8, 4, 8, 0, 3))
self.features.add(nn.BatchNorm(), nn.Activation('relu'))
def __init__(self,
channels_init=64,
growth_rate=32,
n_layers=10,
bottleneck_factor=4,
dropout=0,
n_labels=1000,
channels_value_head=8,
channels_policy_head=16,
value_fc_size=256,
**kwargs):
"""
Constructor
:param channels_init: Number of channels for the first convolutional layer
:param growth_rate: Number of channels which increase per layer
:param n_layers: Number of layers
:param bottleneck_factor: Bottleneck factor which determines how much more layers used for the 1x1 convolution
:param dropout: Dropout factor, if 0% then no dropout will be used
:param n_labels: Number of final labels to predict, here moves
:param channels_value_head: Number of channels in the final value head
:param channels_policy_head: Number of channels in the final policy head
:param value_fc_size: Size of the fully connected layer in the value head
:param kwargs: Optional additional arguments
"""
super(DenseNet, self).__init__(**kwargs)
with self.name_scope():
self.features = nn.HybridSequential(prefix="")
# add initial convolutional layer
self.features.add(
nn.Conv2D(channels_init,
kernel_size=3,
padding=1,
use_bias=False))
# add dense blocks
for layer_idx in range(n_layers):
self.features.add(
_make_dense_block(n_layers, bottleneck_factor, growth_rate,
dropout, layer_idx))
# we need to add a batch-norm and activation because _make_dense_block() starts with them
self.features.add(nn.BatchNorm())
self.features.add(nn.Activation("relu"))
# create the two heads which will be used in the hybrid fwd pass
self.value_head = _ValueHeadAlphaZero("value", channels_value_head,
value_fc_size, 0.9, "relu")
self.policy_head = _PolicyHeadAlphaZero("policy", channels_policy_head,
n_labels, 0.9, "relu")