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:
from notebook.utils import setup_sam_3d_body estimator = setup_sam_3d_body(embedl/sam-3d-body) outputs = estimator.process_one_image(image) rend_img = visualize_sample_together(image, outputs, estimator.faces)
- 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
Update card to 512 + 3D mesh demo + TRT 10.16 benchmarks
Browse files- infer_trt.py +1 -1
infer_trt.py
CHANGED
|
@@ -34,7 +34,7 @@ except ImportError as e: # pragma: no cove
|
|
| 34 |
HERE = Path(__file__).resolve().parent
|
| 35 |
ONNX = HERE / "embedl_sam3dbody_int8.onnx"
|
| 36 |
ENGINE = HERE / "embedl_sam3dbody_int8.engine"
|
| 37 |
-
INPUT_SIZE =
|
| 38 |
IMAGENET_MEAN = np.array([0.485, 0.456, 0.406], dtype=np.float32)
|
| 39 |
IMAGENET_STD = np.array([0.229, 0.224, 0.225], dtype=np.float32)
|
| 40 |
LOG = trt.Logger(trt.Logger.WARNING)
|
|
|
|
| 34 |
HERE = Path(__file__).resolve().parent
|
| 35 |
ONNX = HERE / "embedl_sam3dbody_int8.onnx"
|
| 36 |
ENGINE = HERE / "embedl_sam3dbody_int8.engine"
|
| 37 |
+
INPUT_SIZE = 512
|
| 38 |
IMAGENET_MEAN = np.array([0.485, 0.456, 0.406], dtype=np.float32)
|
| 39 |
IMAGENET_STD = np.array([0.229, 0.224, 0.225], dtype=np.float32)
|
| 40 |
LOG = trt.Logger(trt.Logger.WARNING)
|