Image Feature Extraction
LiteRT
LiteRT
PerceptionEncoder
on-device
android
gpu
clip
image-encoder
vit
rope
Instructions to use mlboydaisuke/PE-Core-base-patch16-224-LiteRT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use mlboydaisuke/PE-Core-base-patch16-224-LiteRT with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- PerceptionEncoder
How to use mlboydaisuke/PE-Core-base-patch16-224-LiteRT with PerceptionEncoder:
# Use PE-Core models as CLIP models import core.vision_encoder.pe as pe model = pe.CLIP.from_config("mlboydaisuke/PE-Core-base-patch16-224-LiteRT", pretrained=True)# Use any PE model as a vision encoder import core.vision_encoder.pe as pe model = pe.VisionTransformer.from_config("mlboydaisuke/PE-Core-base-patch16-224-LiteRT", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Link the card back to its collection and the request box
Browse files
README.md
CHANGED
|
@@ -116,3 +116,11 @@ original [PE model card](https://huggingface.co/facebook/PE-Core-B16-224) and
|
|
| 116 |
- **Apache-2.0** (original [PE-Core](https://huggingface.co/facebook/PE-Core-B16-224) /
|
| 117 |
[timm checkpoint](https://huggingface.co/timm/vit_pe_core_base_patch16_224.fb)).
|
| 118 |
- This is a format conversion; all credit to the original authors (Meta / FAIR).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 116 |
- **Apache-2.0** (original [PE-Core](https://huggingface.co/facebook/PE-Core-B16-224) /
|
| 117 |
[timm checkpoint](https://huggingface.co/timm/vit_pe_core_base_patch16_224.fb)).
|
| 118 |
- This is a format conversion; all credit to the original authors (Meta / FAIR).
|
| 119 |
+
|
| 120 |
+
<!-- funnel:v1 -->
|
| 121 |
+
|
| 122 |
+
---
|
| 123 |
+
|
| 124 |
+
**Want a different model on-device?** [Open a request](https://github.com/john-rocky/on-device-requests) — free, open weights only; the export and its measured numbers get published publicly.
|
| 125 |
+
|
| 126 |
+
<!-- /funnel:v1 -->
|