Instructions to use nielsr/efficientsam-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nielsr/efficientsam-tiny with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nielsr/efficientsam-tiny", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from nielsr/efficientsam-tiny: direct link, hf CLI and curl.
- Browser
- Download file 596 Bytes
-
https://huggingface.co/nielsr/efficientsam-tiny/resolve/main/config.json
- Command line
-
hf download hf://nielsr/efficientsam-tiny/config.json
-
curl -L -o config.json https://huggingface.co/nielsr/efficientsam-tiny/resolve/main/config.json
596 Bytes
| {"img_size": 1024, "encoder_patch_embed_dim": 192, "encoder_num_heads": 3, "encoder_patch_size": 16, "encoder_depth": 12, "encoder_mlp_ratio": 4.0, "encoder_neck_dims": [256, 256], "decoder_max_num_input_points": 6, "decoder_transformer_depth": 2, "decoder_transformer_mlp_dim": 2048, "decoder_num_heads": 8, "decoder_upscaling_layer_dims": [64, 32], "num_multimask_outputs": 3, "iou_head_depth": 3, "iou_head_hidden_dim": 256, "activation": "gelu", "normalization_type": "layer_norm", "normalize_before_activation": false, "pixel_mean": [0.485, 0.456, 0.406], "pixel_std": [0.229, 0.224, 0.225]} |