Image Feature Extraction
Transformers
Safetensors
English
Korean
vision-encoder
multimodal
custom_code
Instructions to use skt/A.X-VE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use skt/A.X-VE with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="skt/A.X-VE", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("skt/A.X-VE", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoImageProcessor": "image_processing_ax_ve.AXVEImageProcessor", | |
| "AutoProcessor": "processing_ax_ve.AXVEProcessor" | |
| }, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_tile_pad": false, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "AXVEImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "processor_class": "AXVEProcessor", | |
| "rescale_factor": 0.00392156862745098, | |
| "min_pixels": 65536, | |
| "max_pixels": 16777216, | |
| "patch_size": 16, | |
| "merge_size": 2 | |
| } |