def WideResnet(n_blocks=3, widen_factor=1, n_output_classes=10, mode='train'):
"""WideResnet from https://arxiv.org/pdf/1605.07146.pdf.
Args:
n_blocks: int, number of blocks in a group. total layers = 6n + 4.
widen_factor: int, widening factor of each group. k=1 is vanilla resnet.
n_output_classes: int, number of distinct output classes.
mode: Whether we are training or evaluating or doing inference.
Returns:
The list of layers comprising a WideResnet model with the given parameters.
"""
return tl.Model(
tl.ToFloat(),
tl.Conv(16, (3, 3), padding='SAME'),
WideResnetGroup(n_blocks, 16 * widen_factor, mode=mode),
WideResnetGroup(n_blocks, 32 * widen_factor, (2, 2), mode=mode),
WideResnetGroup(n_blocks, 64 * widen_factor, (2, 2), mode=mode),
tl.BatchNorm(mode=mode),
tl.Relu(),
tl.AvgPool(pool_size=(8, 8)),
tl.Flatten(),
tl.Dense(n_output_classes),
tl.LogSoftmax(),
)
def WideResnet(n_blocks=3, d_hidden=64, n_output_classes=10, mode='train'):
"""WideResnet from https://arxiv.org/pdf/1605.07146.pdf.
Args:
n_blocks: int, number of blocks in a group.
d_hidden: Dimensionality of the first hidden layer (multiplied later).
n_output_classes: int, number of distinct output classes.
mode: Whether we are training or evaluating or doing inference.
Returns:
The list of layers comprising a WideResnet model with the given parameters.
"""
del mode
return tl.Model(
tl.ToFloat(),
tl.Conv(d_hidden, (3, 3), padding='SAME'),
WideResnetGroup(n_blocks, d_hidden),
WideResnetGroup(n_blocks, d_hidden * 2, (2, 2)),
WideResnetGroup(n_blocks, d_hidden * 4, (2, 2)),
tl.BatchNorm(),
tl.Relu(),
tl.AvgPool(pool_size=(8, 8)),
tl.Flatten(),
tl.Dense(n_output_classes),
tl.LogSoftmax(),
)
def AtariCnn(hidden_sizes=(32, 32), output_size=128, mode='train'):
"""An Atari CNN."""
del mode
# TODO(jonni): Include link to paper?
# Input shape: (B, T, H, W, C)
# Output shape: (B, T, output_size)
return tl.Model(
tl.ToFloat(),
tl.Div(divisor=255.0),
# Set up 4 successive game frames, concatenated on the last axis.
tl.Dup(),
tl.Dup(),
tl.Dup(),
tl.Parallel(None, _shift_right(1), _shift_right(2), _shift_right(3)),
tl.Concatenate(n_items=4, axis=-1), # (B, T, H, W, 4C)
tl.Conv(hidden_sizes[0], (5, 5), (2, 2), 'SAME'),
tl.Relu(),
tl.Conv(hidden_sizes[1], (5, 5), (2, 2), 'SAME'),
tl.Relu(),
tl.Flatten(n_axes_to_keep=2), # B, T and rest.
tl.Dense(output_size),
tl.Relu(),
)
def Resnet50(d_hidden=64, n_output_classes=1001, mode='train'):
"""ResNet.
Args:
d_hidden: Dimensionality of the first hidden layer (multiplied later).
n_output_classes: Number of distinct output classes.
mode: Whether we are training or evaluating or doing inference.
Returns:
The list of layers comprising a ResNet model with the given parameters.
"""
return tl.Model(
tl.ToFloat(),
tl.Conv(d_hidden, (7, 7), (2, 2), 'SAME'),
tl.BatchNorm(mode=mode),
tl.Relu(),
tl.MaxPool(pool_size=(3, 3), strides=(2, 2)),
ConvBlock(3, [d_hidden, d_hidden, 4 * d_hidden], (1, 1), mode=mode),
IdentityBlock(3, [d_hidden, d_hidden, 4 * d_hidden], mode=mode),
IdentityBlock(3, [d_hidden, d_hidden, 4 * d_hidden], mode=mode),
ConvBlock(3, [2 * d_hidden, 2 * d_hidden, 8 * d_hidden], (2, 2),
mode=mode),
IdentityBlock(3, [2 * d_hidden, 2 * d_hidden, 8 * d_hidden],
mode=mode),
IdentityBlock(3, [2 * d_hidden, 2 * d_hidden, 8 * d_hidden],
mode=mode),
IdentityBlock(3, [2 * d_hidden, 2 * d_hidden, 8 * d_hidden],
mode=mode),
ConvBlock(3, [4 * d_hidden, 4 * d_hidden, 16 * d_hidden], (2, 2),
mode=mode),
IdentityBlock(3, [4 * d_hidden, 4 * d_hidden, 16 * d_hidden],
mode=mode),
IdentityBlock(3, [4 * d_hidden, 4 * d_hidden, 16 * d_hidden],
mode=mode),
IdentityBlock(3, [4 * d_hidden, 4 * d_hidden, 16 * d_hidden],
mode=mode),
IdentityBlock(3, [4 * d_hidden, 4 * d_hidden, 16 * d_hidden],
mode=mode),
IdentityBlock(3, [4 * d_hidden, 4 * d_hidden, 16 * d_hidden],
mode=mode),
ConvBlock(3, [8 * d_hidden, 8 * d_hidden, 32 * d_hidden], (2, 2),
mode=mode),
IdentityBlock(3, [8 * d_hidden, 8 * d_hidden, 32 * d_hidden],
mode=mode),
IdentityBlock(3, [8 * d_hidden, 8 * d_hidden, 32 * d_hidden],
mode=mode),
tl.AvgPool(pool_size=(7, 7)),
tl.Flatten(),
tl.Dense(n_output_classes),
tl.LogSoftmax(),
)
def AtariCnn(n_frames=4, hidden_sizes=(32, 32), output_size=128, mode='train'):
"""An Atari CNN."""
del mode
# TODO(jonni): Include link to paper?
# Input shape: (B, T, H, W, C)
# Output shape: (B, T, output_size)
return tl.Model(
tl.ToFloat(),
tl.Div(divisor=255.0),
# Set up n_frames successive game frames, concatenated on the last axis.
FrameStack(n_frames=n_frames), # (B, T, H, W, 4C)
tl.Conv(hidden_sizes[0], (5, 5), (2, 2), 'SAME'),
tl.Relu(),
tl.Conv(hidden_sizes[1], (5, 5), (2, 2), 'SAME'),
tl.Relu(),
tl.Flatten(n_axes_to_keep=2), # B, T and rest.
tl.Dense(output_size),
tl.Relu(),
)
def AtariCnn(hidden_sizes=(32, 32), output_size=128):
"""An Atari CNN."""
# Input's shape = (B, T, H, W, C)
return tl.Model(
tl.ToFloat(),
tl.Div(divisor=255.0),
# Have 4 copies of the input, each one shifted to the right by one.
tl.Branch([], [tl.ShiftRight()],
[tl.ShiftRight(), tl.ShiftRight()],
[tl.ShiftRight(),
tl.ShiftRight(),
tl.ShiftRight()]),
# Concatenated on the last axis.
tl.Concatenate(axis=-1), # (B, T, H, W, 4C)
tl.Conv(hidden_sizes[0], (5, 5), (2, 2), 'SAME'),
tl.Relu(),
tl.Conv(hidden_sizes[1], (5, 5), (2, 2), 'SAME'),
tl.Relu(),
tl.Flatten(num_axis_to_keep=2), # B, T and rest.
tl.Dense(output_size),
tl.Relu(),
# Eventually this is shaped (B, T, output_size)
)
