Arun 6ec8560436 Update hieradet.py ...

Not used  
head_dim = dim_out // num_heads
self.scale = head_dim**-0.5

F.scaled_dot_product_attention takes care of this automatically.

2024-08-07 11:35:46 +05:30

..

backbones

Update hieradet.py

2024-08-07 11:35:46 +05:30

sam

Make it optional to build CUDA extension for SAM 2; also fallback to all available kernels if Flash Attention fails (#155)

2024-08-06 10:52:01 -07:00

__init__.py

Initial commit

2024-07-29 21:54:20 +00:00

memory_attention.py

Initial commit

2024-07-29 21:54:20 +00:00

memory_encoder.py

Initial commit

2024-07-29 21:54:20 +00:00

position_encoding.py

Initial commit

2024-07-29 21:54:20 +00:00

sam2_base.py

Initial commit

2024-07-29 21:54:20 +00:00

sam2_utils.py

Initial commit

2024-07-29 21:54:20 +00:00