Instructions to use minchul/cvlface_DFA_resnet50 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use minchul/cvlface_DFA_resnet50 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="minchul/cvlface_DFA_resnet50", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("minchul/cvlface_DFA_resnet50", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "CVLFaceAlignmentModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "wrapper.ModelConfig", | |
| "AutoModel": "wrapper.CVLFaceAlignmentModel" | |
| }, | |
| "conf": { | |
| "arch": "resnet50", | |
| "color_space": "RGB", | |
| "freeze": true, | |
| "input_padding_ratio": 0, | |
| "input_padding_val": "zero", | |
| "input_size": 160, | |
| "name": "differentiable_face_aligner", | |
| "output_size": 112, | |
| "start_from": "", | |
| "yaml_path": "aligners/configs/dfa.yaml" | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.33.0" | |
| } | |