File size: 2,472 Bytes
2568013 |
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 |
# MIT License
# Copyright (c) 2022 Karl Stelzner
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
# This file comes from https://github.com/stelzner/srt
from torch import nn
from .attention import Attention
from .feed_forward import FeedForward
from .pre_norm import PreNorm
class Transformer(nn.Module):
def __init__(
self,
dim,
depth,
heads,
dim_head,
mlp_dim,
dropout=0.0,
selfatt=True,
kv_dim=None,
feed_forward_layer=FeedForward,
):
super().__init__()
self.layers = nn.ModuleList([])
for _ in range(depth):
self.layers.append(
nn.ModuleList(
[
PreNorm(
dim,
Attention(
dim,
heads=heads,
dim_head=dim_head,
dropout=dropout,
selfatt=selfatt,
kv_dim=kv_dim,
),
),
PreNorm(dim, feed_forward_layer(dim, mlp_dim, dropout=dropout)),
]
)
)
def forward(self, x, z=None, **kwargs):
for attn, ff in self.layers:
x = attn(x, z=z) + x
x = ff(x, **kwargs) + x
return x
|