R Zach
R Zach
**Describe the bug** Long-running `python` processes using the `SPTAGClient.py` library which hold a `SPTAGClient.AnnClient` object in memory and frequently call the `SPTAGClient.AnnClient.Search` method will result in a slow but obvious...
the SPTAGClient.AnnClient.Search method treats query and input vectors differently wrt normalization
**Bug description** when we build an `SPTAGClient.AnnClient` object off of a ANN server which loaded a `Index.DistCalcMethod=Cosine` (default) index, I expect that if I `Search` for any vector in that...
file mentioned [here](https://github.com/hukkelas/DSFD-Pytorch-Inference/blob/dde9c7dd9cdc9254c2ca345222c86a8ecfa17f5b/face_detection/retinaface/onnx.py#L22) is gone