Zero-Shot Image Classification
OpenCLIP
English
OpenCLIP
clip
biology
biodiversity
agronomy
CV
images
animals
species
taxonomy
rare species
endangered species
evolutionary biology
multimodal
knowledge-guided
Instructions to use BGLab/BioTrove-CLIP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use BGLab/BioTrove-CLIP with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:BGLab/BioTrove-CLIP') tokenizer = open_clip.get_tokenizer('hf-hub:BGLab/BioTrove-CLIP') - Notebooks
- Google Colab
- Kaggle
added trained dataset
Browse files
README.md
CHANGED
|
@@ -20,12 +20,13 @@ tags:
|
|
| 20 |
- multimodal
|
| 21 |
- knowledge-guided
|
| 22 |
datasets:
|
| 23 |
-
-
|
| 24 |
-
- EOL
|
| 25 |
base_model:
|
| 26 |
- openai/clip-vit-base-patch16
|
| 27 |
- openai/clip-vit-large-patch14
|
| 28 |
pipeline_tag: zero-shot-image-classification
|
|
|
|
|
|
|
| 29 |
---
|
| 30 |
|
| 31 |
|
|
|
|
| 20 |
- multimodal
|
| 21 |
- knowledge-guided
|
| 22 |
datasets:
|
| 23 |
+
- BGLab/BioTrove-Train
|
|
|
|
| 24 |
base_model:
|
| 25 |
- openai/clip-vit-base-patch16
|
| 26 |
- openai/clip-vit-large-patch14
|
| 27 |
pipeline_tag: zero-shot-image-classification
|
| 28 |
+
metrics:
|
| 29 |
+
- accuracy
|
| 30 |
---
|
| 31 |
|
| 32 |
|