Instructions to use kerasformers/mask2former-swin-tiny-coco-instance with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasFormers
How to use kerasformers/mask2former-swin-tiny-coco-instance with KerasFormers:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Keras
How to use kerasformers/mask2former-swin-tiny-coco-instance with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://kerasformers/mask2former-swin-tiny-coco-instance") - Notebooks
- Google Colab
- Kaggle
| { | |
| "library_name": "kerasformers", | |
| "kerasformers_version": "1.1.3", | |
| "model_module": "kerasformers.models.mask2former", | |
| "model_class": "Mask2FormerUniversalSegment", | |
| "variant": "mask2former-swin-tiny-coco-instance", | |
| "weights": "model.weights.h5", | |
| "model_type": "mask2former", | |
| "backbone_embed_dim": 96, | |
| "backbone_depths": [ | |
| 2, | |
| 2, | |
| 6, | |
| 2 | |
| ], | |
| "backbone_num_heads": [ | |
| 3, | |
| 6, | |
| 12, | |
| 24 | |
| ], | |
| "backbone_window_size": 7, | |
| "hidden_dim": 256, | |
| "mask_feature_size": 256, | |
| "encoder_num_layers": 6, | |
| "encoder_ffn_dim": 1024, | |
| "decoder_num_layers": 9, | |
| "decoder_ffn_dim": 2048, | |
| "num_heads": 8, | |
| "num_queries": 100, | |
| "num_classes": 80, | |
| "image_size": 384 | |
| } |