Simonas Kazlauskas 4ff81d5877 yolo nas: do not invalidate model when input shape is different (#18799) ... Model can be adjusted ahead of time to NHWC to avoid transpose on CPU, for example. All the model information is already presented in the configuration, and the stringent checks implemented in openvino are not present on other backends anyway. OpenVINO will properly report issues with mismatched layouts anyhow.		2025-06-20 09:11:48 -06:00
..
__init__.py	Convert detectors to factory pattern, ability to set different model for each detector (#4635)	2022-12-15 07:12:52 -06:00
cpu_tfl.py	Add isort and ruff linter (#6575)	2023-05-29 05:31:17 -05:00
deepstack.py	fix: use requests.Session() for DeepStack API (#15505)	2024-12-14 07:54:13 -07:00
edgetpu_tfl.py	Fix model errors (#17171)	2025-03-16 06:01:15 -05:00
hailo8l.py	Fixes (#18379)	2025-05-27 10:25:34 -05:00
onnx.py	Cleanup detection (#17785)	2025-04-18 10:26:34 -06:00
openvino.py	yolo nas: do not invalidate model when input shape is different (#18799)	2025-06-20 09:11:48 -06:00
rknn.py	implement RKNN downloads for yolov9 and yolox models (#17875)	2025-04-23 12:22:23 -05:00
tensorrt.py	Simplify plus submit (#15941)	2025-01-11 07:04:11 -07:00