docker/main/install_synap1680.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+
+set -euxo pipefail
+
+if [[ "${TARGETARCH}" == "amd64" ]]; then
+    arch="x86_64"
+elif [[ "${TARGETARCH}" == "arm64" ]]; then
+    arch="aarch64"
+fi
+
+wget -qO- "https://github.com/GaryHuang-ASUS/frigate-synaptics-rt/releases/download/v1.5.0-1.0/synaptics-rt-1.0.tar" | tar -C / -xzf -
+wget -P /wheels/ "https://github.com/synaptics-synap/synap-python/releases/download/v0.0.4-preview/synap_python-0.0.4-cp311-cp311-manylinux_2_35_aarch64.whl"
+

docker/synap1680/Dockerfile.toolchain

@@ -0,0 +1,34 @@
+# syntax=docker/dockerfile:1.4
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+FROM --platform=linux/amd64 debian:12-slim AS poky-toolchain
+ARG DEBIAN_FRONTEND
+RUN apt-get update \
+    && apt-get install -y wget xz-utils \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /tmp
+
+RUN wget -O /tmp/toolchain.sh.000 https://github.com/synaptics-astra/sdk/releases/download/v1.5.0/sl1680_oobe-poky-glibc-x86_64-astra-media-oobe-cortexa73-sl1680-toolchain-4.0.17.sh.000 \
+ && wget -O /tmp/toolchain.sh.001 https://github.com/synaptics-astra/sdk/releases/download/v1.5.0/sl1680_oobe-poky-glibc-x86_64-astra-media-oobe-cortexa73-sl1680-toolchain-4.0.17.sh.001 \
+ && cat /tmp/toolchain.sh.* > /tmp/toolchain.sh \
+ && chmod +x /tmp/toolchain.sh \
+ && /tmp/toolchain.sh -y -d /opt/poky/4.0.17
+
+FROM deps AS synap1680-deps
+ARG TARGETARCH
+
+# Install dependencies
+RUN --mount=type=bind,source=docker/synap1680/install_deps.sh,target=/deps/install_deps.sh \
+    /deps/install_deps.sh
+
+WORKDIR /opt/frigate/
+COPY --from=rootfs / /
+COPY --from=poky-toolchain /opt/poky/4.0.17/sysroots/cortexa73-poky-linux/usr/lib/libtim-vx.so /rootfs/usr/lib/
+COPY --from=poky-toolchain /opt/poky/4.0.17/sysroots/cortexa73-poky-linux/usr/lib/libtensorflow-lite.so /rootfs/usr/lib/
+COPY --from=poky-toolchain /opt/poky/4.0.17/sysroots/cortexa73-poky-linux/usr/lib/libvx_delegate.so /rootfs/usr/lib/
+COPY --from=poky-toolchain /opt/poky/4.0.17/sysroots/cortexa73-poky-linux/usr/lib/libsynapnb.so /rootfs/usr/lib/
+COPY --from=poky-toolchain /opt/poky/4.0.17/sysroots/cortexa73-poky-linux/usr/lib/libebg_utils.so /rootfs/usr/lib/
+COPY --from=poky-toolchain /opt/poky/4.0.17/sysroots/cortexa73-poky-linux/usr/lib/libovxlib.so /rootfs/usr/lib/
+ADD https://github.com/synaptics-astra/synap-release/blob/v1.5.0/models/dolphin/object_detection/coco/model/mobilenet224_full80/model.synap /model.synap

docker/synap1680/install_deps.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+set -euxo pipefail
+
+apt-get -qq update
+
+if [[ "${TARGETARCH}" == "amd64" ]]; then
+    arch="x86_64"
+elif [[ "${TARGETARCH}" == "arm64" ]]; then
+    arch="aarch64"
+fi
+
+wget -qO- "https://github.com/GaryHuang-ASUS/frigate-synaptics-rt/releases/download/v1.5.0-1.0/synaptics-rt-1.0.tar" | tar -C / -xzf -
+wget -P /wheels/ "https://github.com/synaptics-synap/synap-python/releases/download/v0.0.4-preview/synap_python-0.0.4-cp311-cp311-manylinux_2_35_aarch64.whl"
+cp /rootfs/usr/local/lib/* /usr/local/lib

docker/synap1680/synap1680.hcl

@@ -16,8 +16,8 @@ target rootfs {
   target = "rootfs"
 }
 
-target synaptics {
-  dockerfile = "docker/synaptics/Dockerfile"
+target synap1680 {
+  dockerfile = "docker/synap1680/Dockerfile"
   contexts = {
     wheels = "target:wheels",
     deps = "target:deps",

docker/synap1680/synap1680.mk

@@ -0,0 +1,15 @@
+BOARDS += synap1680
+
+local-synap1680: version
+	docker buildx bake --file=docker/synap1680/synap1680.hcl synap1680 \
+		--set synap1680.tags=frigate:latest-synap1680 \
+		--load
+
+build-synap1680: version
+	docker buildx bake --file=docker/synap1680/synap1680.hcl synap1680 \
+		--set synap1680.tags=$(IMAGE_REPO):${GITHUB_REF_NAME}-$(COMMIT_HASH)-synap1680
+
+push-synap1680: build-synap1680
+	docker buildx bake --file=docker/synap1680/synap1680.hcl synap1680 \
+		--set synap1680.tags=$(IMAGE_REPO):${GITHUB_REF_NAME}-$(COMMIT_HASH)-synap1680 \
+		--push

docker/synaptics/synaptics.mk

@@ -1,15 +0,0 @@
-BOARDS += synaptics
-
-local-synaptics: version
-	docker buildx bake --file=docker/synaptics/synaptics.hcl synaptics \
-		--set synaptics.tags=frigate:latest-synaptics \
-		--load
-
-build-synaptics: version
-	docker buildx bake --file=docker/synaptics/synaptics.hcl synaptics \
-		--set synaptics.tags=$(IMAGE_REPO):${GITHUB_REF_NAME}-$(COMMIT_HASH)-synaptics
-
-push-synaptics: build-synaptics
-	docker buildx bake --file=docker/synaptics/synaptics.hcl synaptics \
-		--set synaptics.tags=$(IMAGE_REPO):${GITHUB_REF_NAME}-$(COMMIT_HASH)-synaptics \
-		--push

docs/docs/configuration/hardware_acceleration_video.md

@@ -428,29 +428,3 @@ cameras:
 ```
 
 :::
-
-## Synaptics
-
-Hardware accelerated video de-/encoding is supported on Synpatics SL-series SoC.
-
-### Prerequisites
-
-Make sure to follow the [Synaptics specific installation instructions](/frigate/installation#synaptics).
-
-### Configuration
-
-Add one of the following FFmpeg presets to your `config.yml` to enable hardware video processing:
-
-```yaml
-ffmpeg:
-  hwaccel_args: -c:v h264_v4l2m2m
-  input_args: preset-rtsp-restream
-output_args:
-  record: preset-record-generic-audio-aac
-```
-
-:::warning
-
-Make sure that your SoC supports hardware acceleration for your input stream and your input stream is h264 encoding. For example, if your camera streams with h264 encoding, your SoC must be able to de- and encode with it. If you are unsure whether your SoC meets the requirements, take a look at the datasheet.
-
-:::

docs/docs/configuration/object_detectors.md

@@ -40,10 +40,6 @@ Frigate supports multiple different detectors that work on different types of ha
 
 - [RKNN](#rockchip-platform): RKNN models can run on Rockchip devices with included NPUs.
 
-**Synaptics**
-
-- [Synaptics](#synaptics): synap models can run on Synaptics devices(e.g astra machina) with included NPUs.
-
 **For Testing**
 
 - [CPU Detector (not recommended for actual use](#cpu-detector-not-recommended): Use a CPU to run tflite model, this is not recommended and in most cases OpenVINO can be used in CPU mode with better results.
@@ -842,35 +838,6 @@ model:
   height: 320 # MUST match the chosen model i.e yolov7-320 -> 320 yolov4-416 -> 416
 ```
 
-## Synaptics
-
-Hardware accelerated object detection is supported on the following SoCs:
-
-- SL1680
-
-This implementation uses the [Synaptics model conversion](https://synaptics-synap.github.io/doc/v/latest/docs/manual/introduction.html#offline-model-conversion), version v3.1.0.
-
-See the [installation docs](../frigate/installation.md#synaptics) for information on configuring the SL-series NPU hardware.
-
-### Configuration
-
-When configuring the Synap detector, you have to specify the model: a local **path**.
-
-#### SSD
-
-Use this configuration for ssd models. Here's a default pre-converted ssd model under the root folder.
-
-```yaml
-detectors:
-  synap_npu:
-    type: synaptics
-
-model:
-  path: /model.synap
-  width: 224
-  height: 224
-```
-
 ## Rockchip platform
 
 Hardware accelerated object detection is supported on the following SoCs:

docs/docs/frigate/hardware.md

@@ -90,21 +90,8 @@ Frigate supports multiple different detectors that work on different types of ha
   - Runs best with tiny or small size models
   - Runs efficiently on low power hardware
 
-**Synaptics**
-
-- [Synaptics](#synaptics): synap models can run on Synaptics devices(e.g astra machina) with included NPUs to provide efficient object detection.
-
 :::
 
-### Synaptics
-
-- **Synaptics** Default model is **mobilenet**
-
-| Name             | Synaptics SL1680 Inference Time |
-| ---------------- | ------------------------------- |
-| ssd mobilenet    | ~ 25 ms                         |
-| yolov5m          | ~ 118 ms                        |
-
 ### Hailo-8
 
 Frigate supports both the Hailo-8 and Hailo-8L AI Acceleration Modules on compatible hardware platforms—including the Raspberry Pi 5 with the PCIe hat from the AI kit. The Hailo detector integration in Frigate automatically identifies your hardware type and selects the appropriate default model when a custom model isn’t provided.

docs/docs/frigate/installation.md

@@ -185,37 +185,6 @@ or add these options to your `docker run` command:
 
 Next, you should configure [hardware object detection](/configuration/object_detectors#rockchip-platform) and [hardware video processing](/configuration/hardware_acceleration_video#rockchip-platform).
 
-### Synaptics
-
-- SL1680
-
-#### Setup
-
-Follow Frigate's default installation instructions, but use a docker image with `-synaptics` suffix for example `ghcr.io/blakeblackshear/frigate:stable-synaptics`.
-
-Next, you need to grant docker permissions to access your hardware:
-
-- During the configuration process, you should run docker in privileged mode to avoid any errors due to insufficient permissions. To do so, add `privileged: true` to your `docker-compose.yml` file or the `--privileged` flag to your docker run command.
-
-```yaml
-devices:
-  - /dev/synap
-  - /dev/video0
-  - /dev/video1
-```
-
-or add these options to your `docker run` command:
-
-```
---device /dev/synap \
---device /dev/video0 \
---device /dev/video1 
-```
-
-#### Configuration
-
-Next, you should configure [hardware object detection](/configuration/object_detectors#synaptics) and [hardware video processing](/configuration/hardware_acceleration_video#synaptics).
-
 ## Docker
 
 Running through Docker with Docker Compose is the recommended install method.

frigate/detectors/plugins/synap1680.py

@@ -1,4 +1,3 @@
-import os
 import logging
 
 from typing_extensions import Literal
@@ -14,7 +13,7 @@ from frigate.detectors.detector_config import BaseDetectorConfig, ModelTypeEnum
 
 logger = logging.getLogger(__name__)
 
-DETECTOR_KEY = "synaptics"
+DETECTOR_KEY = "synap1680"
 
 
 class SynapDetectorConfig(BaseDetectorConfig):