Image Segmentation
Transformers
Safetensors
concor1
feature-extraction
vision-language-grounding
concept-correspondence
referring-expression-segmentation
phrase-grounding
open-vocabulary-segmentation
custom_code
Instructions to use UWGZQ/ConCor-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UWGZQ/ConCor-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="UWGZQ/ConCor-1", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("UWGZQ/ConCor-1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "processor_class": "ConCor1Processor", | |
| "auto_map": { | |
| "AutoProcessor": "processing_concor1.ConCor1Processor" | |
| }, | |
| "num_bridge_tokens": 385, | |
| "bridge_token_id_start": 248077, | |
| "patch_size": 16, | |
| "merge_size": 2, | |
| "num_mask_upsample_blocks": 2, | |
| "min_pixels": 1003520, | |
| "max_pixels": 1003520, | |
| "presence_threshold": 0.1, | |
| "text_threshold": 0.45, | |
| "image_threshold": 0.45, | |
| "nms_iou_threshold": 0.5 | |
| } | |