localhorst
/
CLIP_on_Tesla_K20Xm
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
42 Commits 1 Branch 0 Tags 16 MiB
Commit Graph

19 Commits

Author SHA1 Message Date
Tan Jia Huei 573315e83f
use `pkg_resources` for PyTorch version comparison (#176) 
use `pkg_resources` from `setuptools` to parse version strings, it is required by Pytorch >= 0.4.1 anyway
 2021-11-09 01:57:26 -05:00
Tan Jia Huei 1a8b4b2899
Fix PyTorch version check for nightly builds (#173) 2021-11-05 01:17:26 -04:00
Santiago Castro 2867559c5f
Fix PyTorch version check (#160) 
* Fix PyTorch version check

* Fix suggestion

Co-authored-by: Jong Wook Kim <jongwook@openai.com>
 2021-11-04 17:32:10 -04:00
Gianluca Gippetto c13005fd42
In Compose, replace lambda function with named function (#151) 
This prevents the following error on Windows (when using
a multi-process DataLoader, for example):

AttributeError: Can't pickle local object '_transform.<locals>.<lambda>'
 2021-09-23 21:42:20 -04:00
or-toledano 3b473b0e68
Reduce half of similarity muls after encoding (#140) 
(cAB)^T = c B^T A^T
Saves half of the similarity products in the CLIP model.py after the visual/text encoding stages
 2021-08-29 05:15:03 -04:00
Kevin Costa 22fde59cbe
Can specify root directory when loading model (#136) 
* Can specify root directory when loading model

* specifying download_root instead

Co-authored-by: Jong Wook Kim <jongwook@openai.com>
 2021-08-08 23:43:22 -07:00
Santiago Castro ff339871f3
Use tqdm with 1024 instead of 1000 unit scale (#131) 2021-08-08 23:20:38 -07:00
Jong Wook Kim dff9d15305 add ViT-B/16 and RN50x16 models 2021-07-19 14:57:31 -07:00
Haofan Wang ea41722f9f
Rename VisualTransformer -> VisionTransformer (#97) 
Fixes #94
 2021-07-18 20:41:49 -07:00
Romain Beaumont a2737ac264
Add truncate option to tokenize (#126) 
* Add truncate_text option to tokenize

This makes it possible to run tokenize on texts that are longer than the number of tokens
that fit the context length without having to try to guess how to cut in number of 
characters beforehand

* add doc, rename to just "truncate", use eot_token

Co-authored-by: Jong Wook Kim <jongwook@openai.com>
 2021-07-18 20:17:40 -07:00
Jong Wook Kim db20393f4a Using non-JIT by default; compat fix with 1.8+ 2021-07-18 18:45:21 -07:00
Jong Wook Kim 8a665a683d fixed model loading issue (#66) 2021-03-23 03:05:17 -04:00
Jong Wook Kim 290ac5cb15
Correctly initializing the logit scale parameter 
adding numpy import
 2021-03-22 22:09:57 -04:00
Jong Wook Kim 43c953e231
Correctly initializing the logit scale parameter 
cf. #46
 2021-03-22 18:07:08 -04:00
Jong Wook Kim fd6c1443c2 add RN101 and RN50x4; update paper URL and model card 2021-03-04 12:30:39 -05:00
Sebastian Berns 4c0275784d
Load model from path (#41) 
* Load model from path

* showing download progress in "MiB"

* clip.load() now can take a file path

Co-authored-by: Jong Wook Kim <jongwook@openai.com>
 2021-02-16 06:19:42 -05:00
Jong Wook Kim 8f6deb52a1 showing download progress in "MiB" 2021-02-15 22:00:33 -05:00
Jong Wook Kim c42a8e3c9e added parameter initialization (fixes #15) 2021-01-30 03:26:10 +09:00
boba_and_beer 3bee28119e
Make the repo installable as a package (#26) 2021-01-30 03:05:01 +09:00