Image Segmentation
Transformers
Safetensors
English
prima
text-generation
computer-vision
multi-image-reasoning
pixel-grounding
vision-language
custom-code
custom_code
Instructions to use kanguyen-vn/PRIMA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kanguyen-vn/PRIMA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="kanguyen-vn/PRIMA", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("kanguyen-vn/PRIMA", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Include clean PRIMA code and evaluator; document metrics, initialization, and MIT contributions
91c1e9e verified Download code/tools/outputs.py from kanguyen-vn/PRIMA: direct link, hf CLI and curl.
- Browser
- Download file 455 Bytes
-
https://huggingface.co/kanguyen-vn/PRIMA/resolve/main/code/tools/outputs.py
- Command line
-
hf download hf://kanguyen-vn/PRIMA/code/tools/outputs.py
-
curl -L -o outputs.py https://huggingface.co/kanguyen-vn/PRIMA/resolve/main/code/tools/outputs.py
455 Bytes
| """Map the model's native/explicit grounding slots to ordered input images.""" | |
| def image_mask_slots(pred_masks, num_images): | |
| if pred_masks is None: | |
| return [None] * num_images | |
| if len(pred_masks) == num_images + 1: | |
| pred_masks = pred_masks[1:] | |
| if len(pred_masks) != num_images: | |
| raise ValueError('Grounding output does not match the number of input images.') | |
| return [slot[0] if slot else None for slot in pred_masks] | |