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
7ad30f15d5
blakeblackshear.frigate/docker/tensorrt/trt.mk

27 lines
1.9 KiB
Makefile
Raw Normal View History

Community Supported Boards Framework (#7114) * Make main frigate build non rpi specific and build rpi using base image * Add boards to sidebar * Fix docker build * Fix docs build * Update pr branch for testing * remove target from rpi build * Remove manual build * Add push build for rpi * fix typos, improve wording * Add arm build for rpi * Cleanup and add default github ref name * Cleanup docker build file system * Setup to use docker bake * Add ci/cd for bake * Fix path * Fix devcontainer * Set targets * Fix build * Fix syntax * Add wheels target * Move dev container to trt * Update key and fix rpi local * Move requirements files and set intermediate targets * Add back --load * Update docs for community board development * Update installation docs to reflect different builds available * Update docs with official and community supported headers * Update codeowners docs * Update docs * Assemble main and standard builds * Change order of pushes * Remove community board after successful build * Fix rpi bake file names
2023-07-23 23:45:29 +02:00
BOARDS += trt
Nvidia Jetson ffmpeg + TensorRT support (#6458) * Non-Jetson changes Required for later commits: - Allow base image to be overridden (and don't assume its WORKDIR) - Ensure python3.9 - Map hwaccel decode presets as strings instead of lists Not required: - Fix existing documentation - Simplify hwaccel scale logic * Prepare for multi-arch tensorrt build * Add tensorrt images for Jetson boards * Add Jetson ffmpeg hwaccel * Update docs * Add CODEOWNERS * CI * Change default model from yolov7-tiny-416 to yolov7-320 In my experience the tiny models perform markedly worse without being much faster * fixup! Update docs
2023-07-26 12:50:41 +02:00
JETPACK4_BASE ?= timongentzsch/l4t-ubuntu20-opencv:latest # L4T 32.7.1 JetPack 4.6.1
JETPACK5_BASE ?= nvcr.io/nvidia/l4t-tensorrt:r8.5.2-runtime # L4T 35.3.1 JetPack 5.1.1
Pass computes value to libyolo_layer build (#10210)
2024-03-05 13:04:13 +01:00
X86_DGPU_ARGS := ARCH=amd64 COMPUTE_LEVEL="50 60 70 80 90"
Nvidia Jetson ffmpeg + TensorRT support (#6458) * Non-Jetson changes Required for later commits: - Allow base image to be overridden (and don't assume its WORKDIR) - Ensure python3.9 - Map hwaccel decode presets as strings instead of lists Not required: - Fix existing documentation - Simplify hwaccel scale logic * Prepare for multi-arch tensorrt build * Add tensorrt images for Jetson boards * Add Jetson ffmpeg hwaccel * Update docs * Add CODEOWNERS * CI * Change default model from yolov7-tiny-416 to yolov7-320 In my experience the tiny models perform markedly worse without being much faster * fixup! Update docs
2023-07-26 12:50:41 +02:00
JETPACK4_ARGS := ARCH=arm64 BASE_IMAGE=$(JETPACK4_BASE) SLIM_BASE=$(JETPACK4_BASE) TRT_BASE=$(JETPACK4_BASE)
JETPACK5_ARGS := ARCH=arm64 BASE_IMAGE=$(JETPACK5_BASE) SLIM_BASE=$(JETPACK5_BASE) TRT_BASE=$(JETPACK5_BASE)
Community Supported Boards Framework (#7114) * Make main frigate build non rpi specific and build rpi using base image * Add boards to sidebar * Fix docker build * Fix docs build * Update pr branch for testing * remove target from rpi build * Remove manual build * Add push build for rpi * fix typos, improve wording * Add arm build for rpi * Cleanup and add default github ref name * Cleanup docker build file system * Setup to use docker bake * Add ci/cd for bake * Fix path * Fix devcontainer * Set targets * Fix build * Fix syntax * Add wheels target * Move dev container to trt * Update key and fix rpi local * Move requirements files and set intermediate targets * Add back --load * Update docs for community board development * Update installation docs to reflect different builds available * Update docs with official and community supported headers * Update codeowners docs * Update docs * Assemble main and standard builds * Change order of pushes * Remove community board after successful build * Fix rpi bake file names
2023-07-23 23:45:29 +02:00
local-trt: version
Nvidia Jetson ffmpeg + TensorRT support (#6458) * Non-Jetson changes Required for later commits: - Allow base image to be overridden (and don't assume its WORKDIR) - Ensure python3.9 - Map hwaccel decode presets as strings instead of lists Not required: - Fix existing documentation - Simplify hwaccel scale logic * Prepare for multi-arch tensorrt build * Add tensorrt images for Jetson boards * Add Jetson ffmpeg hwaccel * Update docs * Add CODEOWNERS * CI * Change default model from yolov7-tiny-416 to yolov7-320 In my experience the tiny models perform markedly worse without being much faster * fixup! Update docs
2023-07-26 12:50:41 +02:00
$(X86_DGPU_ARGS) docker buildx bake --load --file=docker/tensorrt/trt.hcl --set tensorrt.tags=frigate:latest-tensorrt tensorrt
local-trt-jp4: version
$(JETPACK4_ARGS) docker buildx bake --load --file=docker/tensorrt/trt.hcl --set tensorrt.tags=frigate:latest-tensorrt-jp4 tensorrt
local-trt-jp5: version
$(JETPACK5_ARGS) docker buildx bake --load --file=docker/tensorrt/trt.hcl --set tensorrt.tags=frigate:latest-tensorrt-jp5 tensorrt
Community Supported Boards Framework (#7114) * Make main frigate build non rpi specific and build rpi using base image * Add boards to sidebar * Fix docker build * Fix docs build * Update pr branch for testing * remove target from rpi build * Remove manual build * Add push build for rpi * fix typos, improve wording * Add arm build for rpi * Cleanup and add default github ref name * Cleanup docker build file system * Setup to use docker bake * Add ci/cd for bake * Fix path * Fix devcontainer * Set targets * Fix build * Fix syntax * Add wheels target * Move dev container to trt * Update key and fix rpi local * Move requirements files and set intermediate targets * Add back --load * Update docs for community board development * Update installation docs to reflect different builds available * Update docs with official and community supported headers * Update codeowners docs * Update docs * Assemble main and standard builds * Change order of pushes * Remove community board after successful build * Fix rpi bake file names
2023-07-23 23:45:29 +02:00
build-trt:
Nvidia Jetson ffmpeg + TensorRT support (#6458) * Non-Jetson changes Required for later commits: - Allow base image to be overridden (and don't assume its WORKDIR) - Ensure python3.9 - Map hwaccel decode presets as strings instead of lists Not required: - Fix existing documentation - Simplify hwaccel scale logic * Prepare for multi-arch tensorrt build * Add tensorrt images for Jetson boards * Add Jetson ffmpeg hwaccel * Update docs * Add CODEOWNERS * CI * Change default model from yolov7-tiny-416 to yolov7-320 In my experience the tiny models perform markedly worse without being much faster * fixup! Update docs
2023-07-26 12:50:41 +02:00
$(X86_DGPU_ARGS) docker buildx bake --file=docker/tensorrt/trt.hcl --set tensorrt.tags=$(IMAGE_REPO):${GITHUB_REF_NAME}-$(COMMIT_HASH)-tensorrt tensorrt
$(JETPACK4_ARGS) docker buildx bake --file=docker/tensorrt/trt.hcl --set tensorrt.tags=$(IMAGE_REPO):${GITHUB_REF_NAME}-$(COMMIT_HASH)-tensorrt-jp4 tensorrt
$(JETPACK5_ARGS) docker buildx bake --file=docker/tensorrt/trt.hcl --set tensorrt.tags=$(IMAGE_REPO):${GITHUB_REF_NAME}-$(COMMIT_HASH)-tensorrt-jp5 tensorrt
Community Supported Boards Framework (#7114) * Make main frigate build non rpi specific and build rpi using base image * Add boards to sidebar * Fix docker build * Fix docs build * Update pr branch for testing * remove target from rpi build * Remove manual build * Add push build for rpi * fix typos, improve wording * Add arm build for rpi * Cleanup and add default github ref name * Cleanup docker build file system * Setup to use docker bake * Add ci/cd for bake * Fix path * Fix devcontainer * Set targets * Fix build * Fix syntax * Add wheels target * Move dev container to trt * Update key and fix rpi local * Move requirements files and set intermediate targets * Add back --load * Update docs for community board development * Update installation docs to reflect different builds available * Update docs with official and community supported headers * Update codeowners docs * Update docs * Assemble main and standard builds * Change order of pushes * Remove community board after successful build * Fix rpi bake file names
2023-07-23 23:45:29 +02:00
push-trt: build-trt
Nvidia Jetson ffmpeg + TensorRT support (#6458) * Non-Jetson changes Required for later commits: - Allow base image to be overridden (and don't assume its WORKDIR) - Ensure python3.9 - Map hwaccel decode presets as strings instead of lists Not required: - Fix existing documentation - Simplify hwaccel scale logic * Prepare for multi-arch tensorrt build * Add tensorrt images for Jetson boards * Add Jetson ffmpeg hwaccel * Update docs * Add CODEOWNERS * CI * Change default model from yolov7-tiny-416 to yolov7-320 In my experience the tiny models perform markedly worse without being much faster * fixup! Update docs
2023-07-26 12:50:41 +02:00
$(X86_DGPU_ARGS) docker buildx bake --push --file=docker/tensorrt/trt.hcl --set tensorrt.tags=$(IMAGE_REPO):${GITHUB_REF_NAME}-$(COMMIT_HASH)-tensorrt tensorrt
$(JETPACK4_ARGS) docker buildx bake --push --file=docker/tensorrt/trt.hcl --set tensorrt.tags=$(IMAGE_REPO):${GITHUB_REF_NAME}-$(COMMIT_HASH)-tensorrt-jp4 tensorrt
$(JETPACK5_ARGS) docker buildx bake --push --file=docker/tensorrt/trt.hcl --set tensorrt.tags=$(IMAGE_REPO):${GITHUB_REF_NAME}-$(COMMIT_HASH)-tensorrt-jp5 tensorrt
Reference in New Issue Copy Permalink