Previously we only catch build errors in `BuildExtension` in https://github.com/facebookresearch/segment-anything-2/pull/155. However, in some cases, the `CUDAExtension` instance might not load. So in this PR, we also catch such errors for `CUDAExtension`.
This PR adds an example to provide box prompt in SAM 2 as inputs to the `add_new_points_or_box` API (renamed from`add_new_points`, which is kept for backward compatibility). If `box` is provided, we add it as the first two points with labels 2 and 3, along with the user-provided points (consistent with how SAM 2 is trained).
The video predictor notebook `notebooks/video_predictor_example.ipynb` is updated to include segmenting from box prompt as an example.
This PR suggests a way to resolve the error of `unsupported Microsoft Visual Studio version!` in INSTALL.md.
Adding `-allow-unsupported-compiler` argument for the `nvcc` worked.
Editing [setup.py](https://github.com/facebookresearch/segment-anything-2/blob/main/setup.py) is required to add the `-allow-unsupported-compiler` argument for `nvcc`.
```python
def get_extensions():
srcs = ["sam2/csrc/connected_components.cu"]
compile_args = {
"cxx": [],
"nvcc": [
"-DCUDA_HAS_FP16=1",
"-D__CUDA_NO_HALF_OPERATORS__",
"-D__CUDA_NO_HALF_CONVERSIONS__",
"-D__CUDA_NO_HALF2_OPERATORS__",
"-allow-unsupported-compiler" # Add this argument
],
}
ext_modules = [CUDAExtension("sam2._C", srcs, extra_compile_args=compile_args)]
return ext_modules
```
In this PR, we make it optional to build the SAM 2 CUDA extension, in observation that many users encounter difficulties with the CUDA compilation step.
1. During installation, we catch build errors and print a warning message. We also allow explicitly turning off the CUDA extension building with `SAM2_BUILD_CUDA=0`.
2. At runtime, we catch CUDA kernel errors from connected components and print a warning on skipping the post processing step.
We also fall back to the all available kernels if the Flash Attention kernel fails.
The change is made for researchers to easly clone the project to check out from systems and platforms with SSH not in sync with github. Eg : Google Colab, Remote GPU Servers etc
The phrase "model-in-the-loop" is now hyphenated to align with standard practices in technical literature, where hyphenation of compound adjectives clarifies their function as a single descriptor.
Arun