Instructions to use embedl/sam-3d-body with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAM 3D Body
How to use embedl/sam-3d-body with SAM 3D Body:
import cv2 import numpy as np from notebook.utils import setup_sam_3d_body from tools.vis_utils import visualize_sample_together estimator = setup_sam_3d_body("embedl/sam-3d-body") img_bgr = cv2.imread("path/to/image.jpg") outputs = estimator.process_one_image(cv2.cvtColor(img_bgr, cv2.COLOR_BGR2RGB)) rend_img = visualize_sample_together(img_bgr, outputs, estimator.faces) cv2.imwrite("output.jpg", rend_img.astype(np.uint8)) - TensorRT
How to use embedl/sam-3d-body with TensorRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
NAN results for DINOv3 L16
#1
by RainnCao - opened
Why do I get all NaN results when using your script to process the DINOv3 L16 model? I'm using TensorRT version 10.13
Hi, sorry for the late response. Could you provide some more details on which script you are referring to and whether you are compiling the model with trtexec from the onnx? Sometimes on TensorRT v10.13 we have seen nonsense outputs, could you upgrade to v10.16 and try again? Thanks