Update model card for concerto-base.pretrain.pointcept
Browse files
README.md
CHANGED
|
@@ -32,6 +32,8 @@ A Concerto self-supervised pretraining model (joint 2D-3D representation encoder
|
|
| 32 |
pip install torch-pointcloud
|
| 33 |
```
|
| 34 |
|
|
|
|
|
|
|
| 35 |
## Usage
|
| 36 |
|
| 37 |
```python
|
|
|
|
| 32 |
pip install torch-pointcloud
|
| 33 |
```
|
| 34 |
|
| 35 |
+
This checkpoint also needs `spconv` and `flash-attn`, which need a build matching your torch and CUDA: see the [installation guide](https://pytorch-pointcloud.org/installation/).
|
| 36 |
+
|
| 37 |
## Usage
|
| 38 |
|
| 39 |
```python
|