-
Notifications
You must be signed in to change notification settings - Fork 45
/
simple_mlp.py
86 lines (76 loc) · 2.51 KB
/
simple_mlp.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
# Copyright 2024 The Penzai Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""A simple multi-layer perceptron."""
from __future__ import annotations
from typing import Callable
import jax
from penzai import pz
@pz.pytree_dataclass(has_implicitly_inherited_fields=True)
class MLP(pz.nn.Sequential):
"""Sequence of Affine layers."""
@classmethod
def from_config(
cls,
feature_sizes: list[int],
activation_fn: Callable[[jax.Array], jax.Array] = jax.nn.relu,
feature_axis: str = "features",
) -> MLP:
assert len(feature_sizes) >= 2
children = []
for i, (feats_in, feats_out) in enumerate(
zip(feature_sizes[:-1], feature_sizes[1:])
):
if i:
children.append(pz.nn.Elementwise(activation_fn))
children.append(
pz.nn.add_parameter_prefix(
f"Affine_{i}",
pz.nn.Affine.from_config(
input_axes={feature_axis: feats_in},
output_axes={feature_axis: feats_out},
),
)
)
return cls(sublayers=children)
@pz.pytree_dataclass(has_implicitly_inherited_fields=True)
class DropoutMLP(pz.nn.Sequential):
"""Sequence of Affine layers with dropout."""
@classmethod
def from_config(
cls,
feature_sizes: list[int],
drop_rate: float,
activation_fn: Callable[[jax.Array], jax.Array] = jax.nn.relu,
feature_axis: str = "features",
) -> DropoutMLP:
assert len(feature_sizes) >= 2
children = []
for i, (feats_in, feats_out) in enumerate(
zip(feature_sizes[:-1], feature_sizes[1:])
):
if i:
children.extend([
pz.nn.StochasticDropout(drop_rate),
pz.nn.Elementwise(activation_fn),
])
children.append(
pz.nn.add_parameter_prefix(
f"Affine_{i}",
pz.nn.Affine.from_config(
input_axes={feature_axis: feats_in},
output_axes={feature_axis: feats_out},
),
)
)
return cls(sublayers=children)