openai/CLIP
1
0
Fork 0
mirror of https://github.com/openai/CLIP.git synced 2026-04-21 07:58:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Load model from path (#41)

Browse Source 
* 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>
This commit is contained in:
Sebastian Berns
2021-02-16 11:19:42 +00:00
committed by GitHub
parent 8f6deb52a1
commit 4c0275784d
3 changed files with 71 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -56,9 +56,9 @@ Returns the names of the available CLIP models.
#### `clip.load(name, device=..., jit=True)`
Returns the model and the TorchVision transform needed by the model, specified by the model name returned by `clip.available_models()`. It will download the model as necessary. The device to run the model can be optionally specified, and the default is to use the first CUDA device if there is any, otherwise the CPU.
Returns the model and the TorchVision transform needed by the model, specified by the model name returned by `clip.available_models()`. It will download the model as necessary. The `name` argument can also be a path to a local checkpoint.
When `jit` is `False`, a non-JIT version of the model will be loaded.
The device to run the model can be optionally specified, and the default is to use the first CUDA device if there is any, otherwise the CPU. When `jit` is `False`, a non-JIT version of the model will be loaded.
#### `clip.tokenize(text: Union[str, List[str]], context_length=77)`