Add project page link
Browse filesThis PR adds a link to the project page.
README.md
CHANGED
|
@@ -1,11 +1,12 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- image-feature-extraction
|
| 4 |
- timm
|
| 5 |
- transformers
|
| 6 |
-
library_name: timm
|
| 7 |
-
license: apache-2.0
|
| 8 |
---
|
|
|
|
| 9 |
# Model Details
|
| 10 |
|
| 11 |
This is a `timm` remapped, image encoder only variant of the original weights.
|
|
@@ -13,6 +14,8 @@ This is a `timm` remapped, image encoder only variant of the original weights.
|
|
| 13 |
[\[📃 Tech Report\]](https://arxiv.org/abs/2504.13181)
|
| 14 |
[\[📂 Github\]](https://github.com/facebookresearch/perception_models/)
|
| 15 |
|
|
|
|
|
|
|
| 16 |
Perception Encoder (PE) is a state-of-the-art encoder for image and video understanding trained via simple vision-language learning. It was introduced in "[Perception Encoder: The best visual embeddings
|
| 17 |
are not at the output of the network](https://ai.meta.com/research/publications/perception-encoder-the-best-visual-embeddings-are-not-at-the-output-of-the-network/)".
|
| 18 |
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: timm
|
| 3 |
+
license: apache-2.0
|
| 4 |
tags:
|
| 5 |
- image-feature-extraction
|
| 6 |
- timm
|
| 7 |
- transformers
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
+
|
| 10 |
# Model Details
|
| 11 |
|
| 12 |
This is a `timm` remapped, image encoder only variant of the original weights.
|
|
|
|
| 14 |
[\[📃 Tech Report\]](https://arxiv.org/abs/2504.13181)
|
| 15 |
[\[📂 Github\]](https://github.com/facebookresearch/perception_models/)
|
| 16 |
|
| 17 |
+
Project page: https://ai.meta.com/datasets/plm-data/
|
| 18 |
+
|
| 19 |
Perception Encoder (PE) is a state-of-the-art encoder for image and video understanding trained via simple vision-language learning. It was introduced in "[Perception Encoder: The best visual embeddings
|
| 20 |
are not at the output of the network](https://ai.meta.com/research/publications/perception-encoder-the-best-visual-embeddings-are-not-at-the-output-of-the-network/)".
|
| 21 |
|