Zero-Shot Image Classification
OpenCLIP
Safetensors
PyTorch
English
biology
computer-vision
CV
clip
imageomics
images
taxonomy
hierarchical-classification
animals
plants
fungi
evolutionary biology
knowledge-guided
Instructions to use imageomics/bioclip-hc-hyperbolic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use imageomics/bioclip-hc-hyperbolic with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:imageomics/bioclip-hc-hyperbolic') tokenizer = open_clip.get_tokenizer('hf-hub:imageomics/bioclip-hc-hyperbolic') - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -133,8 +133,6 @@ Primary metrics supported by the current codebase include:
|
|
| 133 |
|
| 134 |
## Evaluation Results
|
| 135 |
|
| 136 |
-
<h2>Evaluation Results</h2>
|
| 137 |
-
|
| 138 |
We evaluate the model on three hierarchical fine-grained biodiversity classification benchmarks:
|
| 139 |
iNat21, Rare Species, and CrypticBio. We report per-level top-1 accuracy across available taxonomic ranks.
|
| 140 |
|
|
|
|
| 133 |
|
| 134 |
## Evaluation Results
|
| 135 |
|
|
|
|
|
|
|
| 136 |
We evaluate the model on three hierarchical fine-grained biodiversity classification benchmarks:
|
| 137 |
iNat21, Rare Species, and CrypticBio. We report per-level top-1 accuracy across available taxonomic ranks.
|
| 138 |
|