Instructions to use zeroone012012/detr_custom with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zeroone012012/detr_custom with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("zeroone012012/detr_custom", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from zeroone012012/detr_custom: direct link, hf CLI and curl.
- Browser
- Download file 426 Bytes
-
https://huggingface.co/zeroone012012/detr_custom/resolve/main/config.json
- Command line
-
hf download hf://zeroone012012/detr_custom/config.json
-
curl -L -o config.json https://huggingface.co/zeroone012012/detr_custom/resolve/main/config.json
426 Bytes
| { | |
| "hidden_dim": 256, | |
| "nheads": 8, | |
| "num_encoder_layers": 6, | |
| "num_decoder_layers": 6, | |
| "dim_feedforward": 2048, | |
| "dropout": 0.1, | |
| "activation": "relu", | |
| "num_classes": 10, | |
| "num_queries": 100, | |
| "aux_loss": true, | |
| "bbox_loss_coef": 5, | |
| "giou_loss_coef": 2, | |
| "eos_coef": 0.1, | |
| "set_cost_class": 0.1, | |
| "set_cost_bbox": 5.0, | |
| "set_cost_giou": 2.0, | |
| "scale_loss_weight": 0.1 | |
| } |