Feature Extraction
Transformers
PyTorch
English
motion
vqvae
motion-tokenization
motion-generation
human-motion
vector-quantization
Instructions to use khania/motion-mgvqvae with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use khania/motion-mgvqvae with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="khania/motion-mgvqvae")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("khania/motion-mgvqvae", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "input_dim": 272, | |
| "code_dim": 512, | |
| "nb_code": 512, | |
| "num_groups": 64, | |
| "down_t": 2, | |
| "stride_t": 2, | |
| "width": 1024, | |
| "depth": 3, | |
| "dilation_growth_rate": 3, | |
| "kernel_size": 3, | |
| "activation": "relu", | |
| "use_mgvq": true, | |
| "absolute_root": true | |
| } |