Skip to content
GitLab
Explore
Sign in
Tags
Tags give the ability to mark specific points in history as being important
This project is mirrored from
https://github.com/lucidrains/meshgpt-pytorch
. Pull mirroring updated
Sep 19, 2024
.
0.2.17
f38ae801
·
add a masked mean squeeze excite
·
Dec 14, 2023
0.2.16
a06d4d80
·
oops, should dropout after activation
·
Dec 14, 2023
0.2.15
abcbd16d
·
all dropouts
·
Dec 14, 2023
0.2.14
33a05f94
·
all dropouts
·
Dec 14, 2023
0.2.11
79970185
·
switch to local attention
·
Dec 13, 2023
0.2.10
41e0a2cd
·
make sure linear attentino is paired with a feedforward, place linear...
·
Dec 13, 2023
0.2.9
a7c0ccf9
·
fix a bug with is_neighbor_mask (for auto determining face edges from face vertices)
·
Dec 13, 2023
0.2.8
8d06e6d7
·
handle linear attention and channel first inputs in decoder
·
Dec 13, 2023
0.2.7
eb7b562d
·
oops, thanks Marcus
·
Dec 13, 2023
0.2.6
21caec19
·
remove need for padding computation for graph conv using masked_select and masked_scatter
·
Dec 13, 2023
0.2.5
7a83ebf1
·
remove need for padding computation for graph conv using masked_select and masked_scatter
·
Dec 13, 2023
0.2.4
a4e52b7a
·
able to customize attn kwargs for linear attention autoencoder, default to off
·
Dec 13, 2023
0.2.3
6c38d6c2
·
able to customize attn kwargs for linear attention autoencoder, default to off
·
Dec 13, 2023
0.2.2
43f93120
·
allow for temperature of 0, for testing kv caching, which is more complicated...
·
Dec 13, 2023
0.2.1
05868335
·
0.2.1
·
Dec 13, 2023
0.2.0
f1d71eff
·
complete the hierarchical transformer, disable caching for now, sequence...
·
Dec 13, 2023
0.1.20
d907c0b3
·
fix type of callable in DatasetFromTransforms
·
Dec 12, 2023
0.1.19
a6dcca5e
·
quick fix
·
Dec 12, 2023
0.1.18
22914cf5
·
switch back to discretized version of derived features, thanks to @MarcusLoppe...
·
Dec 12, 2023
0.1.17
e79ce1a8
·
bump
·
Dec 12, 2023
Prev
1
…
3
4
5
6
7
8
9
10
11
Next