Commit Graph

228 Commits

Author SHA1 Message Date
Brett Kuprel
97d22f0fdd handle log2_mid_count=0 2022-07-04 17:46:31 -04:00
Brett Kuprel
1702d3c439 log2_mid_count 2022-07-04 17:27:23 -04:00
Brett Kuprel
059d8f3448 update colab to use log2_mid_count 2022-07-04 17:27:02 -04:00
Brett Kuprel
8c068f0dcd display_size parameter in colab 2022-07-04 16:30:39 -04:00
Brett Kuprel
0d9998926d display intermediate images 2022-07-04 16:06:49 -04:00
Brett Kuprel
b634375edf display intermediate images 2022-07-04 16:06:14 -04:00
Brett Kuprel
672f325b3b 14s now for 4x4 on A100 2022-07-04 11:19:39 -04:00
Brett Kuprel
8f7f0ba756 update readme 2022-07-04 10:54:25 -04:00
Brett Kuprel
ecc1534f87 5x5 grid works on colab P100 so should work on replicate 2022-07-04 10:28:47 -04:00
Brett Kuprel
3dc92b19bd update readme 2022-07-04 10:22:45 -04:00
Brett Kuprel
e405577d99 4x4 works on colab T4 and P100 2022-07-04 10:21:12 -04:00
Brett Kuprel
486c73c741 update cog.yaml 2022-07-04 10:06:09 -04:00
Brett Kuprel
deefd24919 decode_row 2022-07-04 09:58:00 -04:00
Brett Kuprel
884202239f update notebook 2022-07-04 09:29:54 -04:00
Brett Kuprel
e0fd4d4bff update cog.yaml 2022-07-04 09:21:31 -04:00
Brett Kuprel
6f617fe98f inplace attention state, faster and less memory 2022-07-04 09:14:37 -04:00
Brett Kuprel
aca617dc64 new decoder self attention reduced memory usage and 3x3 grids now work on T4 in colab 2022-07-04 08:25:50 -04:00
Brett Kuprel
461890486e update python version to 0.2.15 2022-07-04 08:10:27 -04:00
Brett Kuprel
377d15cb16 faster decoder self attention 2022-07-04 08:05:55 -04:00
Brett Kuprel
a79d30f718 png -> jpg 2022-07-04 07:38:16 -04:00
Brett Kuprel
a21ea6ea14 update replicate, clear cuda cache if cuda available 2022-07-04 07:28:44 -04:00
Brett Kuprel
256fd1aab0 empty cache if cuda available 2022-07-04 07:21:54 -04:00
Brett Kuprel
9602055eaa
Merge pull request #57 from w4ffl35/bugfix-for-mega-model
Fixes #16 - mega model running out of memory
2022-07-04 07:16:39 -04:00
w4ffl35
7d549505da Fixes #16 - mega model running out of memory
Prior to this fix the mega model will (more often than not) fail when running in succession.

Clearing the cache seems to fix the issue.
2022-07-04 00:26:17 -06:00
Brett Kuprel
6b433d5ba6 update colab 2022-07-03 18:40:27 -04:00
Brett Kuprel
53741154c7 update readme 2022-07-03 17:29:53 -04:00
Brett Kuprel
aa08f7f93c update readme 2022-07-03 16:49:38 -04:00
Brett Kuprel
ec14eeba62 convert pngs to jpgs 2022-07-03 16:30:36 -04:00
Brett Kuprel
2661074589 update readme 2022-07-03 16:26:49 -04:00
Brett Kuprel
6ce60179ff update cog.yaml 2022-07-03 16:16:23 -04:00
Brett Kuprel
948e05c0dd update readme 2022-07-03 15:40:58 -04:00
Brett Kuprel
e20c4a8c9f updated colab 2022-07-03 15:35:33 -04:00
Brett Kuprel
a5004efad0 update readme 2022-07-03 13:35:36 -04:00
Brett Kuprel
b939a1e5ac update cog.yaml 2022-07-03 12:20:03 -04:00
Brett Kuprel
f0f9c5e83e update replicate predict.py 2022-07-03 12:14:24 -04:00
Brett Kuprel
8d808599d3 h100 stat tbd 2022-07-03 11:53:45 -04:00
Brett Kuprel
229af7233d h100 stat tbd 2022-07-03 11:34:58 -04:00
Brett Kuprel
107213b28b 3x3 only works on colab if P100 is allocated 2022-07-03 11:28:28 -04:00
Brett Kuprel
f1bb562ac1 update readme 2022-07-03 11:22:52 -04:00
Brett Kuprel
134fdaf76b add nvidia-smi to notebook 2022-07-03 11:17:37 -04:00
Brett Kuprel
9bdba57195 update replicate 2022-07-02 16:36:51 -04:00
Brett Kuprel
9e146e6675 update readme 2022-07-02 14:56:42 -04:00
Brett Kuprel
cbee448f11 update notebook 2022-07-02 14:54:18 -04:00
Brett Kuprel
a22d510270 update readme 2022-07-02 13:06:48 -04:00
Brett Kuprel
d8a0cbcaf5 update readme 2022-07-02 13:06:03 -04:00
Brett Kuprel
1351478ee5 update readme 2022-07-02 12:55:59 -04:00
Brett Kuprel
05d9d5f07f update readme 2022-07-02 12:34:11 -04:00
Brett Kuprel
bf1acab78a update readme 2022-07-02 12:32:54 -04:00
Brett Kuprel
ec37a2dafe update replicate cog yaml file 2022-07-02 12:02:55 -04:00
Brett Kuprel
e8dac15810 update replicate max grid size 2022-07-02 11:59:26 -04:00