Remove Artpec-7

.github/workflows/hello-world-python.yml

@@ -14,11 +14,6 @@ jobs:
     env:
       EXREPO: acap-computer-vision-examples
       EXNAME: hello-world-python
-    strategy:
-      matrix:
-        include:
-          - arch: armv7hf
-          - arch: aarch64
     steps:
       - uses: actions/checkout@v2
       - uses: docker/setup-buildx-action@v2
@@ -30,4 +25,4 @@ jobs:
           imagetag: ${{ env.EXREPO }}_${{ env.EXNAME }}:1.0
         run: |
           cd $EXNAME
-          docker build --no-cache --build-arg ARCH=${{ matrix.arch }} --tag $imagetag .
+          docker build --no-cache --tag $imagetag .

.github/workflows/minimal-ml-inference.yml

@@ -17,12 +17,8 @@ jobs:
     strategy:
       matrix:
         include:
-          - arch: armv7hf
-            chip: cpu
-          - arch: armv7hf
-            chip: edgetpu
-          - arch: aarch64
-            chip: artpec8
+          - chip: cpu
+          - chip: artpec8
     steps:
       - uses: actions/checkout@v2
       - uses: docker/setup-buildx-action@v2
@@ -36,5 +32,5 @@ jobs:
         run: |
           cd $EXNAME
           docker run --rm --privileged multiarch/qemu-user-static --credential yes --persistent yes
-          docker build --no-cache --build-arg CHIP=${{ matrix.chip }} --build-arg ARCH=${{ matrix.arch }} --tag $imagetag .
-          docker build --file Dockerfile.model --tag $modeltag --build-arg ARCH=${{ matrix.arch }} .
+          docker build --no-cache --build-arg CHIP=${{ matrix.chip }} --tag $imagetag .
+          docker build --file Dockerfile.model --tag $modeltag  .

.github/workflows/object-detector-python.yml

@@ -14,12 +14,8 @@ jobs:
     strategy:
       matrix:
         include:
-          - arch: armv7hf
-            chip: cpu
-          - arch: armv7hf
-            chip: edgetpu
-          - arch: aarch64
-            chip: artpec8
+          - chip: cpu
+          - chip: artpec8
     env:
       EXREPO: acap-computer-vision-examples
       EXNAME: object-detector-python
@@ -35,5 +31,5 @@ jobs:
           modeltag: ${{ env.EXREPO }}_${{ env.EXNAME }}-${{ matrix.chip }}-model:1.0
         run: |
           cd $EXNAME
-          docker build --no-cache --build-arg CHIP=${{ matrix.chip }} --build-arg ARCH=${{ matrix.arch }} --tag $imagetag .
-          docker build --file Dockerfile.model --tag $modeltag --build-arg ARCH=${{ matrix.arch }} .
+          docker build --no-cache --build-arg CHIP=${{ matrix.chip }} --tag $imagetag .
+          docker build --file Dockerfile.model --tag $modeltag  .

.github/workflows/opencv-qr-decoder-python.yml

@@ -14,11 +14,6 @@ jobs:
     env:
       EXREPO: acap-computer-vision-examples
       EXNAME: opencv-qr-decoder-python
-    strategy:
-      matrix:
-        include:
-          - arch: armv7hf
-          - arch: aarch64
     steps:
       - uses: actions/checkout@v2
       - uses: docker/setup-buildx-action@v2
@@ -30,4 +25,4 @@ jobs:
           imagetag: ${{ env.EXREPO }}_${{ env.EXNAME }}:1.0
         run: |
           cd $EXNAME
-          docker build --no-cache --build-arg ARCH=${{ matrix.arch }} --tag $imagetag .
+          docker build --no-cache --tag $imagetag .

.github/workflows/parameter-api-python.yml

@@ -14,11 +14,6 @@ jobs:
     env:
       EXREPO: acap-computer-vision-examples
       EXNAME: parameter-api-python
-    strategy:
-      matrix:
-        include:
-          - arch: armv7hf
-          - arch: aarch64
     steps:
       - uses: actions/checkout@v2
       - uses: docker/setup-buildx-action@v2
@@ -30,4 +25,4 @@ jobs:
           imagetag: ${{ env.EXREPO }}_${{ env.EXNAME }}:1.0
         run: |
           cd $EXNAME
-          docker build --no-cache --build-arg ARCH=${{ matrix.arch }} --tag $imagetag .
+          docker build --no-cache --tag $imagetag .

.github/workflows/pose-estimator-with-flask.yml

@@ -17,12 +17,8 @@ jobs:
     strategy:
       matrix:
         include:
-          - arch: armv7hf
-            chip: cpu
-          - arch: armv7hf
-            chip: edgetpu
-          - arch: aarch64
-            chip: artpec8
+          - chip: cpu
+          - chip: artpec8
 
     steps:
       - uses: actions/checkout@v2
@@ -37,5 +33,5 @@ jobs:
         run: |
           cd $EXNAME
           docker run --rm --privileged multiarch/qemu-user-static --credential yes --persistent yes
-          docker build --no-cache --build-arg CHIP=${{ matrix.chip }} --build-arg ARCH=${{ matrix.arch }} --tag $imagetag .
-          docker build --file Dockerfile.model --tag $modeltag --build-arg ARCH=${{ matrix.arch }} .
+          docker build --no-cache --build-arg CHIP=${{ matrix.chip }}  --tag $imagetag .
+          docker build --file Dockerfile.model --tag $modeltag .

.github/workflows/web-server.yml

@@ -14,11 +14,6 @@ jobs:
     env:
       EXREPO: acap-computer-vision-examples
       EXNAME: web-server
-    strategy:
-      matrix:
-        include:
-          - arch: armv7hf
-          - arch: aarch64
     steps:
       - uses: actions/checkout@v2
       - uses: docker/setup-buildx-action@v2
@@ -31,4 +26,4 @@ jobs:
         run: |
           cd $EXNAME
           docker run --rm --privileged multiarch/qemu-user-static --credential yes --persistent yes
-          docker build --no-cache --build-arg ARCH=${{ matrix.arch }} --tag $imagetag .
+          docker build --no-cache --tag $imagetag .

README.md

@@ -38,7 +38,6 @@ step-by-step instructions on how to run applications on the camera.
 
 The examples support the following architectures:
 
-* armv7hf
 * aarch64
 
 ### Example applications for video analytics

hello-world-python/Dockerfile

@@ -1,15 +1,13 @@
 # syntax=docker/dockerfile:1
 
-ARG ARCH=armv7hf
 ARG REPO=axisecp
 ARG SDK_VERSION=1.15
 ARG UBUNTU_VERSION=22.04
 
-FROM arm32v7/ubuntu:${UBUNTU_VERSION} as runtime-image-armv7hf
-FROM arm64v8/ubuntu:${UBUNTU_VERSION} as runtime-image-aarch64
 
-FROM ${REPO}/acap-computer-vision-sdk:${SDK_VERSION}-${ARCH} AS cv-sdk
-FROM runtime-image-${ARCH}
+FROM ${REPO}/acap-computer-vision-sdk:${SDK_VERSION}-aarch64 AS cv-sdk
+
+FROM arm64v8/ubuntu:${UBUNTU_VERSION}
 
 # Get the Python package from the CV SDK
 COPY --from=cv-sdk /axis/python /

hello-world-python/README.md

@@ -28,36 +28,23 @@ hello-world-python
 Meet the following requirements to ensure compatibility with the example:
 
 * Axis device
-  * Chip: ARTPEC-{7-8} DLPU devices (e.g., Q1615 MkIII)
-  * Firmware: 10.9 or higher
-  * [Docker ACAP](https://github.com/AxisCommunications/docker-acap#installing) installed and started, using TLS and SD card as storage
+  * Chip: ARTPEC-8 DLPU devices (e.g., Q1656)
+  * Firmware: 11.10 or higher
+  * [Docker ACAP](https://github.com/AxisCommunications/docker-acap#installing) version 3.0 installed and started, using TLS with TCP and IPC socket and SD card as storage
 * Computer
   * Either [Docker Desktop](https://docs.docker.com/desktop/) version 4.11.1 or higher,
   * or [Docker Engine](https://docs.docker.com/engine/) version 20.10.17 or higher with BuildKit enabled using Docker Compose version 1.29.2 or higher
 
 ## How to run the code
 
-### Export the environment variable for the architecture
-
-Export the `ARCH` variable depending on the architecture of your camera:
-
-```sh
-# For arm32
-export ARCH=armv7hf
-
-# For arm64
-export ARCH=aarch64
-```
-
 ### Build the Docker image
 
-With the architecture defined, the `hello-world-python` image can be built. The environment variables are supplied as build arguments such that they are made available to Docker during the build process:
+Define and export the application image name in `APP_NAME` for use in the Docker Compose file.
 
 ```sh
-# Define app name
 export APP_NAME=hello-world-python
 
-docker build --tag $APP_NAME --build-arg ARCH .
+docker build --tag $APP_NAME .
 ```
 
 ### Set your device IP address and clear Docker memory

minimal-ml-inference/Dockerfile

@@ -1,18 +1,14 @@
 # syntax=docker/dockerfile:1
 
-ARG ARCH=armv7hf
 ARG REPO=axisecp
 ARG SDK_VERSION=1.15
 ARG UBUNTU_VERSION=22.04
 
-FROM arm32v7/ubuntu:${UBUNTU_VERSION} as runtime-image-armv7hf
-FROM arm64v8/ubuntu:${UBUNTU_VERSION} as runtime-image-aarch64
-
 # Specify which ACAP Computer Vision SDK to use
-FROM ${REPO}/acap-computer-vision-sdk:${SDK_VERSION}-${ARCH} AS cv-sdk
+FROM ${REPO}/acap-computer-vision-sdk:${SDK_VERSION}-aarch64 AS cv-sdk
 
 # Define the runtime image
-FROM runtime-image-${ARCH}
+FROM arm64v8/ubuntu:${UBUNTU_VERSION}
 
 # Get packages from the CV SDK
 COPY --from=cv-sdk /axis/python /

minimal-ml-inference/Dockerfile.model

@@ -1,31 +1,13 @@
 # syntax=docker/dockerfile:1
 
-ARG ARCH=armv7hf
 ARG UBUNTU_VERSION=22.04
 
-FROM arm32v7/alpine as model-image-armv7hf
-FROM arm64v8/alpine as model-image-aarch64
+FROM arm64v8/alpine as model-image
 
-FROM arm32v7/ubuntu:${UBUNTU_VERSION} as local-armv7hf
-FROM arm64v8/ubuntu:${UBUNTU_VERSION} as local-aarch64
-
-FROM local-${ARCH} as local
-
-RUN <<EOF
-apt-get update
-apt-get install -y -f openssl
-EOF
-
-# Generate TSL/SSL test certificate
-RUN openssl req -x509 -batch -subj '/CN=localhost' -days 10000 -newkey rsa:4096 -nodes -out server.pem -keyout server.key
-
-FROM model-image-${ARCH}
 
 # Get SSD Mobilenet V2
-ADD https://github.com/google-coral/edgetpu/raw/master/test_data/ssd_mobilenet_v2_coco_quant_postprocess_edgetpu.tflite models/
 ADD https://github.com/google-coral/edgetpu/raw/master/test_data/ssd_mobilenet_v2_coco_quant_postprocess.tflite models/
 ADD https://github.com/google-coral/edgetpu/raw/master/test_data/coco_labels.txt models/
 ADD https://github.com/google-coral/edgetpu/raw/master/test_data/COPYRIGHT models/
-COPY --from=local server.key server.pem models/
 
 CMD /bin/ls /models

minimal-ml-inference/README.md

@@ -10,12 +10,11 @@ This example composes three different container images into an application that
 
 The first container contains the actual program built in this example. It then uses [gRPC](https://grpc.io/)/[protobuf](https://developers.google.com/protocol-buffers) to call the second container, the *inference-server*, that is used to capture images from the camera and perform the actual inference by implementing the [TensorFlow Serving API](https://github.com/tensorflow/serving). You can find more documentation on the [Machine Learning API documentation page](https://axiscommunications.github.io/acap-documentation/docs/api/computer-vision-sdk-apis.html#machine-learning-api). This example uses a containerized version of the [ACAP Runtime](https://github.com/AxisCommunications/acap-runtime#containerized-version) as the *inference-server*.
 
-Lastly, there is a third container that holds the deep learning model, which is put into a volume that is accessible by the other two images. The layout of the Docker image containing the model is shown below. The *MODEL_PATH* variable in the configuration file you're using specifies what model to use. By default, the armv7hf configuration file uses the edgetpu model, while the aarch64 configuration file uses the vanilla model.
+Lastly, there is a third container that holds the deep learning model, which is put into a volume that is accessible by the other two images. The layout of the Docker image containing the model is shown below. The *MODEL_PATH* variable in the configuration file you're using specifies what model to use.
 
 ```text
 model
-├── ssdlite-mobilenet-v2 - model for CPU
-├── ssdlite-mobilenet-v2-tpu - model for TPU
+├── ssdlite-mobilenet-v2 - tflite model
 └── objects.txt - list of object labels
 ```
 
@@ -26,8 +25,8 @@ Following are the list of files and a brief description of each file in the exam
 ```text
 minimal-ml-inference
 ├── config
-│   ├── env.aarch64
-│   └── env.armv7hf
+│   ├── env.aarch64.artpec8
+│   └── env.aarch64.cpu
 ├── simple_inference.py
 ├── Dockerfile
 ├── Dockerfile.model
@@ -46,52 +45,33 @@ minimal-ml-inference
 Meet the following requirements to ensure compatibility with the example:
 
 * Axis device
-  * Chip: ARTPEC-{7-8} DLPU devices (e.g., Q1615 MkIII)
-  * Firmware: 10.9 or higher
-  * [Docker ACAP](https://github.com/AxisCommunications/docker-acap#installing) installed and started, using TLS and SD card as storage
+  * Chip: ARTPEC-8 DLPU devices (e.g., Q1656)
+  * Firmware: 11.10 or higher
+  * [Docker ACAP](https://github.com/AxisCommunications/docker-acap#installing) version 3.0 installed and started, using TLS with TCP and IPC socket and SD card as storage
 * Computer
   * Either [Docker Desktop](https://docs.docker.com/desktop/) version 4.11.1 or higher,
   * or [Docker Engine](https://docs.docker.com/engine/) version 20.10.17 or higher with BuildKit enabled using Docker Compose version 1.29.2 or higher
 
 ## How to run the code
 
-### Export the environment variable for the architecture
-
-Export the `ARCH` variable depending on the architecture of your camera:
-
-```sh
-# For arm32
-export ARCH=armv7hf
-
-# Valid options for chip on armv7hf are 'tpu' (hardware accelerator) or 'cpu'
-export CHIP=tpu
-```
-
-```sh
-# For arm64
-export ARCH=aarch64
-
-# Valid options for chip on aarch64 are 'artpec8' (hardware accelerator) or 'cpu'
-export CHIP=artpec8
-```
-
 ### Build the Docker images
 
-With the architecture defined, the `acap4-minimal-ml-inference` and `acap-dl-models` images can be built. The environment variables are supplied as build arguments such that they are made available to Docker during the build process:
+Define and export the application image name in `APP_NAME` and the model image name in `MODEL_NAME` for use in the Docker Compose file.
+Define and export also the `CHIP` parameter to be used during the build to select the right manifest file.
 
 ```sh
-# Define app name
 export APP_NAME=acap4-minimal-ml-inference
 export MODEL_NAME=acap-dl-models
+export CHIP=artpec8 # Valid options are 'artpec8' (hardware accelerator) or 'cpu'
 
-# Install qemu to allow build flask for a different architecture
+# Install qemu to allow build for a different architecture
 docker run --rm --privileged multiarch/qemu-user-static --credential yes --persistent yes
 
-# Build app
-docker build --tag $APP_NAME --build-arg ARCH .
+# Build application image
+docker build --tag $APP_NAME .
 
-# Build inference model
-docker build --file Dockerfile.model --tag $MODEL_NAME --build-arg ARCH .
+# Build inference model image
+docker build --file Dockerfile.model --tag $MODEL_NAME .
 ```
 
 ### Set your device IP address and clear Docker memory
@@ -134,17 +114,18 @@ docker save $MODEL_NAME | docker --tlsverify --host tcp://$DEVICE_IP:$DOCKER_POR
 With the application image on the device, it can be started using `docker-compose.yml`:
 
 ```sh
-docker --tlsverify --host tcp://$DEVICE_IP:$DOCKER_PORT compose --env-file ./config/env.$ARCH.$CHIP up
+docker --tlsverify --host tcp://$DEVICE_IP:$DOCKER_PORT compose --env-file ./config/env.aarch64.$CHIP up
 
 # Terminate with Ctrl-C and cleanup
-docker --tlsverify --host tcp://$DEVICE_IP:$DOCKER_PORT compose --env-file ./config/env.$ARCH.$CHIP down --volumes
+docker --tlsverify --host tcp://$DEVICE_IP:$DOCKER_PORT compose --env-file ./config/env.aarch64.$CHIP down --volumes
 ```
 
 The expected output from the application is the raw predictions from the model specified in the environment variable.
 
 ### Hardware acceleration
 
-The `./config` folder contains configuration files with the parameters to run the inference on different camera models, also giving the possibility to use the hardware accelerator. To achieve the best performance we recommend using the TPU (Tensor Processing Unit) equipped with ARTPEC-7 cameras (e.g. [Axis-Q1615 Mk III](https://www.axis.com/products/axis-q1615-mk-iii)) or the DLPU (Deep Learning Processing Unit) equipped in ARTPEC-8 cameras (e.g. [Axis-Q1656](https://www.axis.com/products/axis-q1656)).
+The `./config` folder contains configuration files with the parameters to run the inference on different camera models, also giving the possibility to use the hardware accelerator.
+To achieve the best performance we recommend using DLPU (Deep Learning Processing Unit) equipped ARTPEC-8 cameras. See [ACAP Computer Vision SDK hardware and compatibility](https://axiscommunications.github.io/acap-documentation/docs/axis-devices-and-compatibility/#acap-computer-vision-sdk-hardware-compatibility)
 
 ## License