Instructions to use camstack/camstack-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TF-Keras
How to use camstack/camstack-models with TF-Keras:
# Note: 'keras<3.x' or 'tf_keras' must be installed (legacy) # See https://github.com/keras-team/tf-keras for more details. from huggingface_hub import from_pretrained_keras model = from_pretrained_keras("camstack/camstack-models") - Notebooks
- Google Colab
- Kaggle
Add publicly-distributable animal-classifier (Open Images V7 CC-BY, EfficientNet-Lite0)
336d7d3 verified | { | |
| "labels": [ | |
| "bird", | |
| "cat", | |
| "cow", | |
| "deer", | |
| "dog", | |
| "horse", | |
| "sheep", | |
| "squirrel" | |
| ], | |
| "input_size": 224, | |
| "num_classes": 8, | |
| "preprocess": { | |
| "normalize": "imagenet", | |
| "mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "channels": "RGB", | |
| "layout": "NCHW" | |
| }, | |
| "arch": "efficientnet_lite0", | |
| "source": "Open Images V7 animal subset (largest-box crops per image), 8 classes; timm ImageNet1K pretrained, full fine-tune", | |
| "dataset": "Open Images V7 (Google)", | |
| "license": "dataset: images CC-BY 2.0 + annotations CC-BY 4.0 (permissive, commercial + redistributable with attribution); weights: Apache-2.0 (timm backbone) \u2014 publicly distributable", | |
| "output": "logits (apply softmax)", | |
| "best_val_acc": 0.8925 | |
| } |