Update README
Browse files
README.md
CHANGED
@@ -1,12 +1,13 @@
|
|
1 |
---
|
2 |
pipeline_tag: image-classification
|
3 |
tags:
|
4 |
-
- vision
|
5 |
inference: false
|
6 |
widget:
|
7 |
-
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
|
8 |
-
|
9 |
---
|
|
|
10 |
# Category Search from External Databases (CaSED)
|
11 |
|
12 |
Disclaimer: The model card is taken and modified from the official repository, which can be found [here](https://github.com/altndrr/vic). The paper can be found [here](https://arxiv.org/abs/2306.00917).
|
@@ -34,7 +35,7 @@ processor = CLIPProcessor.from_pretrained("openai/clip-vit-large-patch14")
|
|
34 |
|
35 |
# get the model outputs
|
36 |
images = processor(images=[image], return_tensors="pt", padding=True)
|
37 |
-
outputs = model(images, alpha=0.
|
38 |
labels, scores = outputs["vocabularies"][0], outputs["scores"][0]
|
39 |
|
40 |
# print the top 5 most likely labels for the image
|
@@ -47,18 +48,16 @@ for value, index in zip(values, indices):
|
|
47 |
The model depends on some libraries you have to install manually before execution:
|
48 |
|
49 |
```bash
|
50 |
-
pip install torch faiss-cpu flair inflect nltk transformers
|
51 |
```
|
52 |
|
53 |
## Citation
|
54 |
|
55 |
```latex
|
56 |
-
@
|
57 |
title={Vocabulary-free Image Classification},
|
58 |
author={Alessandro Conti and Enrico Fini and Massimiliano Mancini and Paolo Rota and Yiming Wang and Elisa Ricci},
|
59 |
year={2023},
|
60 |
-
|
61 |
-
archivePrefix={arXiv},
|
62 |
-
primaryClass={cs.CV}
|
63 |
}
|
64 |
-
```
|
|
|
1 |
---
|
2 |
pipeline_tag: image-classification
|
3 |
tags:
|
4 |
+
- vision
|
5 |
inference: false
|
6 |
widget:
|
7 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
|
8 |
+
example_title: Cat & Dog
|
9 |
---
|
10 |
+
|
11 |
# Category Search from External Databases (CaSED)
|
12 |
|
13 |
Disclaimer: The model card is taken and modified from the official repository, which can be found [here](https://github.com/altndrr/vic). The paper can be found [here](https://arxiv.org/abs/2306.00917).
|
|
|
35 |
|
36 |
# get the model outputs
|
37 |
images = processor(images=[image], return_tensors="pt", padding=True)
|
38 |
+
outputs = model(images, alpha=0.7)
|
39 |
labels, scores = outputs["vocabularies"][0], outputs["scores"][0]
|
40 |
|
41 |
# print the top 5 most likely labels for the image
|
|
|
48 |
The model depends on some libraries you have to install manually before execution:
|
49 |
|
50 |
```bash
|
51 |
+
pip install torch faiss-cpu flair inflect nltk pyarrow transformers
|
52 |
```
|
53 |
|
54 |
## Citation
|
55 |
|
56 |
```latex
|
57 |
+
@article{conti2023vocabularyfree,
|
58 |
title={Vocabulary-free Image Classification},
|
59 |
author={Alessandro Conti and Enrico Fini and Massimiliano Mancini and Paolo Rota and Yiming Wang and Elisa Ricci},
|
60 |
year={2023},
|
61 |
+
journal={NeurIPS},
|
|
|
|
|
62 |
}
|
63 |
+
```
|