File size: 7,757 Bytes
283ba4a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
# Copyright © 2023 Apple Inc.

import math
from typing import Union

import mlx.core as mx
from mlx.nn.layers.base import Module


class Conv1d(Module):
    """Applies a 1-dimensional convolution over the multi-channel input sequence.

    The channels are expected to be last i.e. the input shape should be ``NLC`` where:

    * ``N`` is the batch dimension
    * ``L`` is the sequence length
    * ``C`` is the number of input channels

    Args:
        in_channels (int): The number of input channels
        out_channels (int): The number of output channels
        kernel_size (int): The size of the convolution filters
        stride (int, optional): The stride when applying the filter.
            Default: ``1``.
        padding (int, optional): How many positions to 0-pad the input with.
            Default: ``0``.
        dilation (int, optional): The dilation of the convolution.
        groups (int, optional): The number of groups for the convolution.
            Default: ``1``.
        bias (bool, optional): If ``True`` add a learnable bias to the output.
            Default: ``True``
    """

    def __init__(
        self,
        in_channels: int,
        out_channels: int,
        kernel_size: int,
        stride: int = 1,
        padding: int = 0,
        dilation: int = 1,
        groups: int = 1,
        bias: bool = True,
    ):
        super().__init__()

        if in_channels % groups != 0:
            raise ValueError(
                f"The number of input channels ({in_channels}) must be "
                f"divisible by the number of groups ({groups})"
            )

        scale = math.sqrt(1 / (in_channels * kernel_size))
        self.weight = mx.random.uniform(
            low=-scale,
            high=scale,
            shape=(out_channels, kernel_size, in_channels // groups),
        )
        if bias:
            self.bias = mx.zeros((out_channels,))

        self.padding = padding
        self.dilation = dilation
        self.stride = stride
        self.groups = groups

    def _extra_repr(self):
        return (
            f"{self.weight.shape[-1]}, {self.weight.shape[0]}, "
            f"kernel_size={self.weight.shape[1]}, stride={self.stride}, "
            f"padding={self.padding}, dilation={self.dilation}, "
            f"groups={self.groups}, "
            f"bias={'bias' in self}"
        )

    def __call__(self, x):
        y = mx.conv1d(
            x, self.weight, self.stride, self.padding, self.dilation, self.groups
        )
        if "bias" in self:
            y = y + self.bias
        return y


class Conv2d(Module):
    """Applies a 2-dimensional convolution over the multi-channel input image.

    The channels are expected to be last i.e. the input shape should be ``NHWC`` where:

    * ``N`` is the batch dimension
    * ``H`` is the input image height
    * ``W`` is the input image width
    * ``C`` is the number of input channels

    Args:
        in_channels (int): The number of input channels.
        out_channels (int): The number of output channels.
        kernel_size (int or tuple): The size of the convolution filters.
        stride (int or tuple, optional): The size of the stride when
            applying the filter. Default: ``1``.
        padding (int or tuple, optional): How many positions to 0-pad
            the input with. Default: ``0``.
        dilation (int or tuple, optional): The dilation of the convolution.
        groups (int, optional): The number of groups for the convolution.
            Default: ``1``.
        bias (bool, optional): If ``True`` add a learnable bias to the
            output. Default: ``True``
    """

    def __init__(
        self,
        in_channels: int,
        out_channels: int,
        kernel_size: Union[int, tuple],
        stride: Union[int, tuple] = 1,
        padding: Union[int, tuple] = 0,
        dilation: Union[int, tuple] = 1,
        groups: int = 1,
        bias: bool = True,
    ):
        super().__init__()

        if in_channels % groups != 0:
            raise ValueError(
                f"The number of input channels ({in_channels}) must be "
                f"divisible by the number of groups ({groups})"
            )

        kernel_size, stride, padding = map(
            lambda x: (x, x) if isinstance(x, int) else x,
            (kernel_size, stride, padding),
        )
        scale = math.sqrt(1 / (in_channels * kernel_size[0] * kernel_size[1]))
        self.weight = mx.random.uniform(
            low=-scale,
            high=scale,
            shape=(out_channels, *kernel_size, in_channels // groups),
        )
        if bias:
            self.bias = mx.zeros((out_channels,))

        self.padding = padding
        self.stride = stride
        self.dilation = dilation
        self.groups = groups

    def _extra_repr(self):
        return (
            f"{self.weight.shape[-1]}, {self.weight.shape[0]}, "
            f"kernel_size={self.weight.shape[1:3]}, stride={self.stride}, "
            f"padding={self.padding}, dilation={self.dilation}, "
            f"groups={self.groups}, "
            f"bias={'bias' in self}"
        )

    def __call__(self, x):
        y = mx.conv2d(
            x, self.weight, self.stride, self.padding, self.dilation, self.groups
        )
        if "bias" in self:
            y = y + self.bias
        return y


class Conv3d(Module):
    """Applies a 3-dimensional convolution over the multi-channel input image.

    The channels are expected to be last i.e. the input shape should be ``NDHWC`` where:

    * ``N`` is the batch dimension
    * ``D`` is the input image depth
    * ``H`` is the input image height
    * ``W`` is the input image width
    * ``C`` is the number of input channels

    Args:
        in_channels (int): The number of input channels.
        out_channels (int): The number of output channels.
        kernel_size (int or tuple): The size of the convolution filters.
        stride (int or tuple, optional): The size of the stride when
            applying the filter. Default: ``1``.
        dilation (int or tuple, optional): The dilation of the convolution.
        padding (int or tuple, optional): How many positions to 0-pad
            the input with. Default: ``0``.
        bias (bool, optional): If ``True`` add a learnable bias to the
            output. Default: ``True``
    """

    def __init__(
        self,
        in_channels: int,
        out_channels: int,
        kernel_size: Union[int, tuple],
        stride: Union[int, tuple] = 1,
        padding: Union[int, tuple] = 0,
        dilation: Union[int, tuple] = 1,
        bias: bool = True,
    ):
        super().__init__()

        kernel_size, stride, padding = map(
            lambda x: (x, x, x) if isinstance(x, int) else x,
            (kernel_size, stride, padding),
        )
        scale = math.sqrt(
            1 / (in_channels * kernel_size[0] * kernel_size[1] * kernel_size[2])
        )
        self.weight = mx.random.uniform(
            low=-scale,
            high=scale,
            shape=(out_channels, *kernel_size, in_channels),
        )
        if bias:
            self.bias = mx.zeros((out_channels,))

        self.padding = padding
        self.stride = stride
        self.dilation = dilation

    def _extra_repr(self):
        return (
            f"{self.weight.shape[-1]}, {self.weight.shape[0]}, "
            f"kernel_size={self.weight.shape[1:4]}, stride={self.stride}, "
            f"padding={self.padding}, dilation={self.dilation}, "
            f"bias={'bias' in self}"
        )

    def __call__(self, x):
        y = mx.conv3d(x, self.weight, self.stride, self.padding, self.dilation)
        if "bias" in self:
            y = y + self.bias
        return y