blakeblackshear.frigate/frigate
Nate Meyer 3f05f74ecb
Nvidia TensorRT detector (#4718)
* Initial WIP dockerfile and scripts to add tensorrt support

* Add tensorRT detector

* WIP attempt to install TensorRT 8.5

* Updates to detector for cuda python library

* TensorRT Cuda library rework WIP

Does not run

* Fixes from rebase to detector factory

* Fix parsing output memory pointer

* Handle TensorRT logs with the python logger

* Use non-async interface and convert input data to float32. Detection runs without error.

* Make TensorRT a separate build from the base Frigate image.

* Add script and documentation for generating TRT Models

* Add support for TensorRT devcontainer

* Add labelmap to trt model script and docs.  Cleanup of old scripts.

* Update detect to normalize input tensor using model input type

* Add config for selecting GPU. Fix Async inference. Update documentation.

* Update some CUDA libraries to clean up version warning

* Add CI stage to build TensorRT tag

* Add note in docs for image tag and model support
2022-12-30 10:53:17 -06:00
..
comms Fix recordings set name (#4543) 2022-11-28 18:58:41 -06:00
detectors Nvidia TensorRT detector (#4718) 2022-12-30 10:53:17 -06:00
images Replace green screen with error message and force camera_fps to 0 (#4544) 2022-11-28 21:47:20 -06:00
test Use presets by default (#4597) 2022-12-16 07:41:03 -06:00
__init__.py app container and config schema 2021-01-26 21:40:33 -06:00
__main__.py Typing: mypy fixes for 2022-04-17 08:55:38 -05:00
app.py Convert detectors to factory pattern, ability to set different model for each detector (#4635) 2022-12-15 07:12:52 -06:00
config.py Use presets by default (#4597) 2022-12-16 07:41:03 -06:00
const.py Optimize nginx & recordings (#4688) 2022-12-17 17:53:34 -06:00
events.py Typing Part 3: events.py (#3352) 2022-11-19 07:16:33 -06:00
ffmpeg_presets.py Do not apply -user_agent for rtmp streams (#4596) 2022-12-04 09:46:03 -06:00
http.py fix: handle multi-word timezones (#4816) 2022-12-30 08:34:01 -06:00
log.py Support special characters in passwords, redacted logs & debug config (#4057) 2022-11-02 07:00:54 -05:00
models.py Limit recording retention to available storage (#3942) 2022-10-09 06:28:26 -05:00
motion.py Adjust threshold and contour_area with mqtt 2022-07-05 08:46:10 -05:00
mypy.ini Abstract MQTT from communication and make mqtt optional (#4462) 2022-11-23 20:03:20 -06:00
object_detection.py Convert detectors to factory pattern, ability to set different model for each detector (#4635) 2022-12-15 07:12:52 -06:00
object_processing.py Fix end events for mqtt (#4647) 2022-12-08 19:00:44 -06:00
objects.py cleanup print statements 2022-04-16 09:08:10 -05:00
output.py Replace green screen with error message and force camera_fps to 0 (#4544) 2022-11-28 21:47:20 -06:00
plus.py read plus api key from addon options 2022-06-30 07:19:40 -05:00
record.py Optimize nginx & recordings (#4688) 2022-12-17 17:53:34 -06:00
restream.py Update go2rtc, simplify manual stream, and support audio for MSE & WebRTC (#4391) 2022-11-16 06:29:47 -06:00
stats.py Fix gpu stats for ffmpeg presets (#4554) 2022-11-29 19:56:01 -06:00
storage.py FEAT: Storage API & Frontend (#3409) 2022-11-29 19:59:56 -06:00
types.py Refactor to simplify support for additional detector types (#3656) 2022-11-03 21:23:09 -05:00
util.py System page improvements (#4707) 2022-12-14 17:20:47 -06:00
video.py Restart record process if segments stop being written. (#4604) 2022-12-08 20:03:54 -07:00
watchdog.py Typing Part 3: events.py (#3352) 2022-11-19 07:16:33 -06:00
zeroconf.py Add basic typing for multiple modules: 2022-04-15 07:01:43 -05:00