Instructions to use asdafdfafffg/sam-3d-objects with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAM 3D Objects
How to use asdafdfafffg/sam-3d-objects with SAM 3D Objects:
from inference import Inference, load_image, load_single_mask from huggingface_hub import hf_hub_download path = hf_hub_download("asdafdfafffg/sam-3d-objects", "pipeline.yaml") inference = Inference(path, compile=False) image = load_image("path_to_image.png") mask = load_single_mask("path_to_mask.png", index=14) output = inference(image, mask) - Notebooks
- Google Colab
- Kaggle
| _target_: sam3d_objects.model.backbone.tdfy_dit.models.structured_latent_vae.decoder_gs.SLatGaussianDecoderTdfyWrapper | |
| resolution: 64 | |
| model_channels: 768 | |
| latent_channels: 8 | |
| num_blocks: 12 | |
| num_heads: 12 | |
| mlp_ratio: 4 | |
| attn_mode: swin | |
| window_size: 8 | |
| representation_config: | |
| lr: | |
| _xyz: 1.0 | |
| _features_dc: 1.0 | |
| _opacity: 1.0 | |
| _scaling: 1.0 | |
| _rotation: 0.1 | |
| perturb_offset: true | |
| voxel_size: 1.5 | |
| num_gaussians: 4 | |
| 2d_filter_kernel_size: 0.1 | |
| 3d_filter_kernel_size: 0.0009 | |
| scaling_bias: 0.004 | |
| opacity_bias: 0.1 | |
| scaling_activation: softplus | |
| use_fp16: true | |