pytorch-labs / segment-anything-fast

A batched offline inference oriented version of segment-anything
Apache License 2.0
1.21k stars 72 forks source link

How did Automatic Mask Generator support batching before applying nested tensors #104

Open bely66 opened 11 months ago

bely66 commented 11 months ago

In the benchmark of the model on Torch.compile and CudaSync Operations, It's benchmarked on different batch size.

Meanwhile the batch size was introduced when adding nested tensors and isn't available in the Segment Anything original repo

so how are we benchmarking with various batch sizes meanwhile it wasn't implemented yet