Mirrors/blakeblackshear.frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2024-11-21 19:07:46 +01:00
Code Issues Projects Releases Wiki Activity
model-fixes
blakeblackshear.frigate/docker/tensorrt/requirements-amd64.txt

15 lines
722 B
Plaintext
Raw Permalink Normal View History

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 17:53:17 +01:00
# NVidia TensorRT Support (amd64 only)
Upgrade TensorRT to 8.5.3 (#7006) * Update to latest tensorrt (8.6.1) release * Build trt libyolo_layer.so in container * Update tensorrt_models script to convert models from the frigate container * Fix typo in model script * Fix paths to yolo lib and models folder * Add S6 scripts to test and convert specified TensortRT models at startup. Rearrange tensorrt files into a docker support folder. * Update TensorRT documentation to reflect the new model conversion process and minimum HW support. * Fix model_cache path to live in config directory * Move tensorrt s6 files to the correct directory * Fix issues in model generation script * Disable global timeout for s6 services * Add version folder to tensorrt model_cache path * Include TensorRT version 8.5.3 * Add numpy requirement prior to removal of np.bool * This TRT version uses a mixture of cuda dependencies * Redirect stdout from noisy model conversion
2023-07-06 21:20:33 +02:00
--extra-index-url 'https://pypi.nvidia.com'
Revert numpy upgrade in -tensorrt image (#7348)
2023-08-05 12:49:06 +02:00
numpy < 1.24; platform_machine == 'x86_64'
Upgrade TensorRT to 8.5.3 (#7006) * Update to latest tensorrt (8.6.1) release * Build trt libyolo_layer.so in container * Update tensorrt_models script to convert models from the frigate container * Fix typo in model script * Fix paths to yolo lib and models folder * Add S6 scripts to test and convert specified TensortRT models at startup. Rearrange tensorrt files into a docker support folder. * Update TensorRT documentation to reflect the new model conversion process and minimum HW support. * Fix model_cache path to live in config directory * Move tensorrt s6 files to the correct directory * Fix issues in model generation script * Disable global timeout for s6 services * Add version folder to tensorrt model_cache path * Include TensorRT version 8.5.3 * Add numpy requirement prior to removal of np.bool * This TRT version uses a mixture of cuda dependencies * Redirect stdout from noisy model conversion
2023-07-06 21:20:33 +02:00
tensorrt == 8.5.3.*; platform_machine == 'x86_64'
cuda-python == 11.8; platform_machine == 'x86_64'
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 17:53:17 +01:00
cython == 0.29.*; platform_machine == 'x86_64'
Upgrade TensorRT to 8.5.3 (#7006) * Update to latest tensorrt (8.6.1) release * Build trt libyolo_layer.so in container * Update tensorrt_models script to convert models from the frigate container * Fix typo in model script * Fix paths to yolo lib and models folder * Add S6 scripts to test and convert specified TensortRT models at startup. Rearrange tensorrt files into a docker support folder. * Update TensorRT documentation to reflect the new model conversion process and minimum HW support. * Fix model_cache path to live in config directory * Move tensorrt s6 files to the correct directory * Fix issues in model generation script * Disable global timeout for s6 services * Add version folder to tensorrt model_cache path * Include TensorRT version 8.5.3 * Add numpy requirement prior to removal of np.bool * This TRT version uses a mixture of cuda dependencies * Redirect stdout from noisy model conversion
2023-07-06 21:20:33 +02:00
nvidia-cuda-runtime-cu12 == 12.1.*; platform_machine == 'x86_64'
nvidia-cuda-runtime-cu11 == 11.8.*; platform_machine == 'x86_64'
nvidia-cublas-cu11 == 11.11.3.6; platform_machine == 'x86_64'
Support ONNX model caching (#13780) * Support model caching * Cleanup
2024-09-17 02:18:11 +02:00
nvidia-cudnn-cu11 == 8.6.0.*; platform_machine == 'x86_64'
Add support for yolonas via ONNX and allow TensorRT execution provider to work correctly (#13776) * Add support for yolonas in onnx * Add correct deps * Set ld library path * Refactor cudnn to only be used in amd64 * Add onnx to docs and add explainer at the top * Undo change * Update comment * Remove uneccesary * Remove line change
2024-09-16 23:17:31 +02:00
nvidia-cufft-cu11==10.*; platform_machine == 'x86_64'
Upgrade TensorRT to 8.5.3 (#7006) * Update to latest tensorrt (8.6.1) release * Build trt libyolo_layer.so in container * Update tensorrt_models script to convert models from the frigate container * Fix typo in model script * Fix paths to yolo lib and models folder * Add S6 scripts to test and convert specified TensortRT models at startup. Rearrange tensorrt files into a docker support folder. * Update TensorRT documentation to reflect the new model conversion process and minimum HW support. * Fix model_cache path to live in config directory * Move tensorrt s6 files to the correct directory * Fix issues in model generation script * Disable global timeout for s6 services * Add version folder to tensorrt model_cache path * Include TensorRT version 8.5.3 * Add numpy requirement prior to removal of np.bool * This TRT version uses a mixture of cuda dependencies * Redirect stdout from noisy model conversion
2023-07-06 21:20:33 +02:00
onnx==1.14.0; platform_machine == 'x86_64'
Add support for yolonas via ONNX and allow TensorRT execution provider to work correctly (#13776) * Add support for yolonas in onnx * Add correct deps * Set ld library path * Refactor cudnn to only be used in amd64 * Add onnx to docs and add explainer at the top * Undo change * Update comment * Remove uneccesary * Remove line change
2024-09-16 23:17:31 +02:00
onnxruntime-gpu==1.17.*; platform_machine == 'x86_64'
Add onnxruntime nvidia providers (#13756)
2024-09-16 03:30:30 +02:00
protobuf==3.20.3; platform_machine == 'x86_64'
Reference in New Issue Copy Permalink