Modernize OpenVINO-based Nuclio functions and allow them to run on Kubernetes (#6129)

Currently, OpenVINO-based functions assume that a local directory will
be mounted into the container. In Kubernetes, that isn't possible, so
implement an alternate approach: create a separate base image and
inherit the function image from it.

In addition, implement some modernizations:

* Upgrade the version of OpenVINO to the latest (2022.3). Make the
necessary updates to the code. Note that 2022.1 introduced an entirely
new inference API, but I haven't switched to it yet to minimize changes.

* Use the runtime version of the Docker image as the base instead of the
dev version. This significantly reduces the size of the final image (by
~3GB).

* Replace the `faster_rcnn_inception_v2_coco` model with
`faster_rcnn_inception_resnet_v2_atrous_coco`, as the former has been
  removed from OMZ.

* Ditto with `person-reidentification-retail-0300` -> `0277`.

* The IRs used in the DEXTR function are not supported by OpenVINO
anymore (format too old), so rewrite the build process to create them
from the original code/weights instead.

CHANGELOG.md

@@ -11,6 +11,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 - Running SAM masks decoder on frontend (<https://github.com/opencv/cvat/pull/6019>)
+- The `person-reidentification-retail-0300` and
+  `faster_rcnn_inception_v2_coco` Nuclio functions were replaced with
+  `person-reidentification-retail-0277` and
+  `faster_rcnn_inception_resnet_v2_atrous_coco`, respectively
+  (<https://github.com/opencv/cvat/pull/6129>).
+- OpenVINO-based Nuclio functions now use the OpenVINO 2022.3 runtime
+  (<https://github.com/opencv/cvat/pull/6129>).
 
 ### Deprecated
 - TDB
@@ -24,6 +31,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - The issue azure.core.exceptions.ResourceExistsError: The specified blob already exists (<https://github.com/opencv/cvat/pull/6082>)
 - Image scaling when moving between images with different resolution (<https://github.com/opencv/cvat/pull/6081>)
 - Invalid completed job count reporting (<https://github.com/opencv/cvat/issues/6098>)
+- OpenVINO-based Nuclio functions can now be deployed to Kubernetes
+  (<https://github.com/opencv/cvat/pull/6129>).
 
 ### Security
 - TDB

helm-chart/nuclio_func_common_files

-../serverless/common/openvino
\ No newline at end of file

helm-chart/templates/cvat_nuclio/config.yml

-{{- if .Values.nuclio.enabled }}
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: cvat-nuclio-openvino-common
-  namespace: {{ .Release.Namespace }}
-  labels:
-    {{- include "cvat.labels" . | nindent 4 }}
-    app: cvat-app
-    tier: nuclio
-{{- if semverCompare ">=1.21-0" .Capabilities.KubeVersion.GitVersion }}
-immutable: true
-{{- end }}
-binaryData:
-  python3: |-
-    {{ .Files.Get "nuclio_func_common_files/python3" | b64enc }}
-  model_loader.py:
-    {{ .Files.Get "nuclio_func_common_files/model_loader.py" | b64enc }}
-{{- end}}

serverless/common/openvino/python3

-#!/bin/bash
-
-args=$@
-
-. /opt/intel/openvino/bin/setupvars.sh
-PYTHONPATH=/opt/nuclio/common/openvino:$PYTHONPATH
-/usr/bin/python3 $args

serverless/deploy_cpu.sh

 #!/bin/bash
 # Sample commands to deploy nuclio functions on CPU
 
+set -eu
+
 SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 FUNCTIONS_DIR=${1:-$SCRIPT_DIR}
 
-nuctl create project cvat
+export DOCKER_BUILDKIT=1
+
+docker build -t cvat.openvino.base "$SCRIPT_DIR/openvino/base"
+
+nuctl create project cvat --platform local
 
 shopt -s globstar
 
 for func_config in "$FUNCTIONS_DIR"/**/function.yaml
 do
-    func_root=$(dirname "$func_config")
-    echo Deploying $(dirname "$func_root") function...
-    nuctl deploy --project-name cvat --path "$func_root" \
-        --volume "$SCRIPT_DIR/common:/opt/nuclio/common" \
-        --platform local
-done
+    func_root="$(dirname "$func_config")"
+    func_rel_path="$(realpath --relative-to="$SCRIPT_DIR" "$(dirname "$func_root")")"
 
-nuctl get function
+    if [ -f "$func_root/Dockerfile" ]; then
+        docker build -t "cvat.${func_rel_path//\//.}.base" "$func_root"
+    fi
 
+    echo "Deploying $func_rel_path function..."
+    nuctl deploy --project-name cvat --path "$func_root" --platform local
+done
 
+nuctl get function --platform local

serverless/deploy_gpu.sh

 #!/bin/bash
 # Sample commands to deploy nuclio functions on GPU
 
+set -eu
+
 SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 FUNCTIONS_DIR=${1:-$SCRIPT_DIR}
 
-nuctl create project cvat
+nuctl create project cvat --platform local
 
 shopt -s globstar
 
 for func_config in "$FUNCTIONS_DIR"/**/function-gpu.yaml
 do
-    func_root=$(dirname "$func_config")
-    echo "Deploying $(dirname "$func_root") function..."
+    func_root="$(dirname "$func_config")"
+    func_rel_path="$(realpath --relative-to="$SCRIPT_DIR" "$(dirname "$func_root")")"
+
+    echo "Deploying $func_rel_path function..."
     nuctl deploy --project-name cvat --path "$func_root" \
-        --volume "$SCRIPT_DIR/common:/opt/nuclio/common" \
         --file "$func_config" --platform local
 done
 
-nuctl get function
+nuctl get function --platform local

serverless/openvino/base/Dockerfile

+FROM openvino/ubuntu20_runtime:2022.3.0
+
+USER root
+
+RUN apt-get update \
+    && apt-get -y --no-install-recommends install python-is-python3 \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN pip install --no-cache-dir opencv-python-headless pillow pyyaml
+
+COPY model_loader.py shared.py /opt/nuclio/common/openvino/
+
+ENV PYTHONPATH=/opt/nuclio/common/openvino:$PYTHONPATH
+
+USER openvino

serverless/common/openvino/model_loader.py → serverless/openvino/base/model_loader.py

@@ -14,24 +14,22 @@ class ModelLoader:
 
         # Initialize input blobs
         self._input_info_name = None
-        for blob_name in network.inputs:
-            if len(network.inputs[blob_name].shape) == 4:
+        for blob_name in network.input_info:
+            if len(network.input_info[blob_name].tensor_desc.dims) == 4:
                 self._input_blob_name = blob_name
-            elif len(network.inputs[blob_name].shape) == 2:
+                self._input_layout = network.input_info[blob_name].tensor_desc.dims
+            elif len(network.input_info[blob_name].tensor_desc.dims) == 2:
                 self._input_info_name = blob_name
             else:
                 raise RuntimeError(
                     "Unsupported {}D input layer '{}'. Only 2D and 4D input layers are supported"
-                    .format(len(network.inputs[blob_name].shape), blob_name))
+                    .format(len(network.input_info[blob_name].tensor_desc.dims), blob_name))
 
         # Initialize output blob
         self._output_blob_name = next(iter(network.outputs))
 
         # Load network
         self._net = ie_core.load_network(network, "CPU", num_requests=2)
-        input_type = network.inputs[self._input_blob_name]
-        self._input_layout = input_type if isinstance(input_type, list) else input_type.shape
-
 
     def _prepare_inputs(self, image, preprocessing):
         image = np.array(image)
@@ -67,5 +65,5 @@ class ModelLoader:
         return self._input_layout[2:]
 
     @property
-    def layers(self):
-        return self._network.layers
+    def network(self):
+        return self._network

serverless/openvino/dextr/nuclio/Dockerfile

+FROM openvino/ubuntu20_dev:2022.3.0 AS build
+
+USER root
+
+RUN apt-get update \
+    && apt-get -y --no-install-recommends install patch \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /root
+
+ARG DEXTR_COMMIT=352ccc76067156ebcf7267b07e0a5e43d32e83d5
+
+# TODO: use `ADD --checksum` when that feature becomes stable
+ADD https://data.vision.ee.ethz.ch/csergi/share/DEXTR/dextr_pascal-sbd.pth ./
+
+ADD https://github.com/scaelles/DEXTR-PyTorch/archive/$DEXTR_COMMIT.zip dextr.zip
+
+RUN python3 -m zipfile -e dextr.zip .
+
+WORKDIR /root/DEXTR-PyTorch-$DEXTR_COMMIT
+
+ADD export.py adaptive-pool.patch .
+
+RUN patch -p1 -i adaptive-pool.patch
+
+RUN python3 export.py /root/dextr_pascal-sbd.pth /root/dextr.onnx
+
+RUN mo --input_model=/root/dextr.onnx --model_name=dextr --output_dir=/root
+
+FROM cvat.openvino.base
+
+COPY --from=build --chown=root:root /root/dextr.xml /root/dextr.bin /opt/nuclio/

serverless/openvino/dextr/nuclio/adaptive-pool.patch

+This is a hack to work around the the lack of support for AdaptiveAvgPool2d
+in PyTorch's ONNX exporter (<https://github.com/pytorch/pytorch/issues/42653>).
+
+It might become unnecessary in the future, since OpenVINO 2023 is to add support
+for AdaptiveAvgPool2d exported with operator_export_type=ONNX_ATEN_FALLBACK
+(<https://github.com/openvinotoolkit/openvino/pull/14682>).
+
+diff --git a/networks/deeplab_resnet.py b/networks/deeplab_resnet.py
+index ecfa084..e8ff297 100644
+--- a/networks/deeplab_resnet.py
++++ b/networks/deeplab_resnet.py
+@@ -99,7 +99,14 @@ class PSPModule(nn.Module):
+         self.final = nn.Conv2d(out_features, n_classes, kernel_size=1)
+
+     def _make_stage_1(self, in_features, size):
+-        prior = nn.AdaptiveAvgPool2d(output_size=(size, size))
++        kernel_size, stride = {
++            1: (64, 64),
++            2: (32, 32),
++            3: (22, 21),
++            6: (11, 9),
++        }[size]
++
++        prior = nn.AvgPool2d(kernel_size=kernel_size, stride=stride)
+         conv = nn.Conv2d(in_features, in_features//4, kernel_size=1, bias=False)
+         bn = nn.BatchNorm2d(in_features//4, affine=affine_par)
+         relu = nn.ReLU(inplace=True)

serverless/openvino/dextr/nuclio/export.py

+#!/usr/bin/env python3
+
+import sys
+
+import torch
+import torch.nn
+import torch.onnx
+
+import networks.deeplab_resnet as resnet
+
+net = resnet.resnet101(1, nInputChannels=4, classifier='psp')
+
+state_dict_checkpoint = torch.load(sys.argv[1], map_location=torch.device('cpu'))
+
+net.load_state_dict(state_dict_checkpoint)
+
+full_net = torch.nn.Sequential(
+    net,
+    torch.nn.Upsample((512, 512), mode='bilinear', align_corners=True),
+    torch.nn.Sigmoid(),
+)
+full_net.eval()
+
+input_tensor = torch.randn((1, 4, 512, 512))
+
+torch.onnx.export(full_net, input_tensor, sys.argv[2])

serverless/openvino/dextr/nuclio/function.yaml

@@ -13,43 +13,13 @@ metadata:
 
 spec:
   description: Deep Extreme Cut
-  runtime: 'python:3.6'
+  runtime: 'python:3.8'
   handler: main:handler
   eventTimeout: 30s
-  env:
-    - name: NUCLIO_PYTHON_EXE_PATH
-      value: /opt/nuclio/common/openvino/python3
-
-  volumes:
-    - volume:
-        name: openvino-common
-        configMap:
-          name: "cvat-nuclio-openvino-common"
-          defaultMode: 0750
-      volumeMount:
-        name: openvino-common
-        mountPath: /opt/nuclio/common/openvino
 
   build:
-    image: cvat/openvino.dextr
-    baseImage: openvino/ubuntu18_runtime:2020.2
-
-    directives:
-      preCopy:
-        - kind: USER
-          value: root
-        - kind: WORKDIR
-          value: /opt/nuclio
-        - kind: RUN
-          value: ln -s /usr/bin/pip3 /usr/bin/pip
-
-      postCopy:
-        - kind: RUN
-          value: curl -O https://download.01.org/openvinotoolkit/models_contrib/cvat/dextr_model_v1.zip
-        - kind: RUN
-          value: unzip dextr_model_v1.zip
-        - kind: RUN
-          value: pip3 install -U pip && pip3 install wheel Pillow
+    image: cvat.openvino.dextr
+    baseImage: cvat.openvino.dextr.base
 
   triggers:
     myHttpTrigger:

serverless/openvino/omz/intel/face-detection-0205/nuclio/Dockerfile

+FROM openvino/ubuntu20_dev:2022.3.0 AS build
+
+USER root
+
+RUN omz_downloader \
+    --name face-detection-0205,emotions-recognition-retail-0003,age-gender-recognition-retail-0013 \
+    --precisions FP32 \
+    -o /opt/nuclio/open_model_zoo
+
+FROM cvat.openvino.base
+
+COPY --from=build --chown=root:root /opt/nuclio/open_model_zoo /opt/nuclio/open_model_zoo

serverless/openvino/omz/intel/face-detection-0205/nuclio/function.yaml

 metadata:
-  name: openvino-omz-face-detection-0205
+  name: openvino-omz-intel-face-detection-0205
   namespace: cvat
   annotations:
     name: Attributed face detection
@@ -28,47 +28,13 @@ metadata:
 
 spec:
   description: Detection network finding faces and defining age, gender and emotion attributes
-  runtime: 'python:3.6'
+  runtime: 'python:3.8'
   handler: main:handler
   eventTimeout: 30000s
-  env:
-    - name: NUCLIO_PYTHON_EXE_PATH
-      value: /opt/nuclio/common/openvino/python3
-
-  volumes:
-    - volume:
-        name: openvino-common
-        configMap:
-          name: "cvat-nuclio-openvino-common"
-          defaultMode: 0750
-      volumeMount:
-        name: openvino-common
-        mountPath: /opt/nuclio/common/openvino
 
   build:
     image: cvat.openvino.omz.intel.face-detection-0205
-    baseImage: openvino/ubuntu18_dev:2021.1
-
-    directives:
-      preCopy:
-        - kind: USER
-          value: root
-        - kind: WORKDIR
-          value: /opt/nuclio
-        - kind: RUN
-          value: ln -s /usr/bin/pip3 /usr/bin/pip
-        - kind: RUN
-          value: /opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name face-detection-0205 -o /opt/nuclio/open_model_zoo
-        - kind: RUN
-          value: /opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name emotions-recognition-retail-0003 -o /opt/nuclio/open_model_zoo
-        - kind: RUN
-          value: /opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name age-gender-recognition-retail-0013 -o /opt/nuclio/open_model_zoo
-
-      postCopy:
-        - kind: RUN
-          value: apt update && DEBIAN_FRONTEND=noninteractive apt install --no-install-recommends -y python3-skimage
-        - kind: RUN
-          value: pip3 install "numpy<1.16.0" # workaround for skimage
+    baseImage: cvat.openvino.omz.intel.face-detection-0205.base
 
   triggers:
     myHttpTrigger:

serverless/openvino/omz/intel/person-reidentification-retail-0277/nuclio/Dockerfile

+FROM openvino/ubuntu20_dev:2022.3.0 AS build
+
+USER root
+
+RUN omz_downloader \
+    --name person-reidentification-retail-0277 \
+    --precisions FP32 \
+    -o /opt/nuclio/open_model_zoo
+
+FROM cvat.openvino.base
+
+USER root
+
+RUN pip install --no-cache-dir scipy
+
+COPY --from=build /opt/nuclio/open_model_zoo /opt/nuclio/open_model_zoo
+
+USER openvino

serverless/openvino/omz/intel/person-reidentification-retail-300/nuclio/function.yaml → serverless/openvino/omz/intel/person-reidentification-retail-0277/nuclio/function.yaml

 metadata:
-  name: openvino-omz-intel-person-reidentification-retail-0300
+  name: openvino-omz-intel-person-reidentification-retail-0277
   namespace: cvat
   annotations:
     name: Person reidentification
@@ -9,39 +9,13 @@ metadata:
 
 spec:
   description: Person reidentification model for a general scenario
-  runtime: 'python:3.6'
+  runtime: 'python:3.8'
   handler: main:handler
   eventTimeout: 30s
-  env:
-    - name: NUCLIO_PYTHON_EXE_PATH
-      value: /opt/nuclio/common/openvino/python3
-
-  volumes:
-    - volume:
-        name: openvino-common
-        configMap:
-          name: "cvat-nuclio-openvino-common"
-          defaultMode: 0750
-      volumeMount:
-        name: openvino-common
-        mountPath: /opt/nuclio/common/openvino
 
   build:
-    image: cvat.openvino.omz.intel.person-reidentification-retail-0300
-    baseImage: openvino/ubuntu18_dev:2020.2
-
-    directives:
-      preCopy:
-        - kind: USER
-          value: root
-        - kind: WORKDIR
-          value: /opt/nuclio
-        - kind: RUN
-          value: ln -s /usr/bin/pip3 /usr/bin/pip
-        - kind: RUN
-          value: /opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name person-reidentification-retail-0300 -o /opt/nuclio/open_model_zoo
-        - kind: RUN
-          value: /opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader/converter.py --name person-reidentification-retail-0300 --precisions FP32 -d /opt/nuclio/open_model_zoo -o /opt/nuclio/open_model_zoo
+    image: cvat.openvino.omz.intel.person-reidentification-retail-0277
+    baseImage: cvat.openvino.omz.intel.person-reidentification-retail-0277.base
 
   triggers:
     myHttpTrigger:

serverless/openvino/omz/intel/person-reidentification-retail-300/nuclio/main.py → serverless/openvino/omz/intel/person-reidentification-retail-0277/nuclio/main.py

@@ -13,7 +13,7 @@ def init_context(context):
     context.logger.info("Init context...100%")
 
 def handler(context, event):
-    context.logger.info("Run person-reidentification-retail-0300 model")
+    context.logger.info("Run person-reidentification-retail-0277 model")
     data = event.body
     buf0 = io.BytesIO(base64.b64decode(data["image0"]))
     buf1 = io.BytesIO(base64.b64decode(data["image1"]))

serverless/openvino/omz/intel/person-reidentification-retail-300/nuclio/model_handler.py → serverless/openvino/omz/intel/person-reidentification-retail-0277/nuclio/model_handler.py

@@ -13,9 +13,9 @@ from model_loader import ModelLoader
 class ModelHandler:
     def __init__(self):
         base_dir = os.path.abspath(os.environ.get("MODEL_PATH",
-            "/opt/nuclio/open_model_zoo/intel/person-reidentification-retail-0300/FP32"))
-        model_xml = os.path.join(base_dir, "person-reidentification-retail-0300.xml")
-        model_bin = os.path.join(base_dir, "person-reidentification-retail-0300.bin")
+            "/opt/nuclio/open_model_zoo/intel/person-reidentification-retail-0277/FP32"))
+        model_xml = os.path.join(base_dir, "person-reidentification-retail-0277.xml")
+        model_bin = os.path.join(base_dir, "person-reidentification-retail-0277.bin")
 
         self.model = ModelLoader(model_xml, model_bin)
 

serverless/openvino/omz/intel/semantic-segmentation-adas-0001/nuclio/Dockerfile

+FROM openvino/ubuntu20_dev:2022.3.0 AS build
+
+USER root
+
+RUN omz_downloader \
+    --name semantic-segmentation-adas-0001 \
+    --precisions FP32 \
+    -o /opt/nuclio/open_model_zoo
+
+FROM cvat.openvino.base
+
+COPY --from=build --chown=root:root /opt/nuclio/open_model_zoo /opt/nuclio/open_model_zoo

serverless/openvino/omz/intel/semantic-segmentation-adas-0001/nuclio/function.yaml

 metadata:
-  name: openvino-omz-semantic-segmentation-adas-0001
+  name: openvino-omz-intel-semantic-segmentation-adas-0001
   namespace: cvat
   annotations:
     name: Semantic segmentation for ADAS
@@ -32,43 +32,13 @@ metadata:
 
 spec:
   description: Segmentation network to classify each pixel into typical 20 classes for ADAS
-  runtime: 'python:3.6'
+  runtime: 'python:3.8'
   handler: main:handler
   eventTimeout: 30s
-  env:
-    - name: NUCLIO_PYTHON_EXE_PATH
-      value: /opt/nuclio/common/openvino/python3
-
-  volumes:
-    - volume:
-        name: openvino-common
-        configMap:
-          name: "cvat-nuclio-openvino-common"
-          defaultMode: 0750
-      volumeMount:
-        name: openvino-common
-        mountPath: /opt/nuclio/common/openvino
 
   build:
     image: cvat.openvino.omz.intel.semantic-segmentation-adas-0001
-    baseImage: openvino/ubuntu18_dev:2020.2
-
-    directives:
-      preCopy:
-        - kind: USER
-          value: root
-        - kind: WORKDIR
-          value: /opt/nuclio
-        - kind: RUN
-          value: ln -s /usr/bin/pip3 /usr/bin/pip
-        - kind: RUN
-          value: /opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name semantic-segmentation-adas-0001 -o /opt/nuclio/open_model_zoo
-
-      postCopy:
-        - kind: RUN
-          value: apt update && DEBIAN_FRONTEND=noninteractive apt install --no-install-recommends -y python3-skimage
-        - kind: RUN
-          value: pip3 install "numpy<1.16.0" # workaround for skimage
+    baseImage: cvat.openvino.omz.intel.semantic-segmentation-adas-0001.base
 
   triggers:
     myHttpTrigger:

serverless/openvino/omz/intel/text-detection-0004/nuclio/Dockerfile

+FROM openvino/ubuntu20_dev:2022.3.0 AS build
+
+USER root
+
+RUN omz_downloader \
+    --name text-detection-0004 \
+    --precisions FP32 \
+    -o /opt/nuclio/open_model_zoo
+
+FROM cvat.openvino.base
+
+COPY --from=build --chown=root:root /opt/nuclio/open_model_zoo /opt/nuclio/open_model_zoo

serverless/openvino/omz/intel/text-detection-0004/nuclio/function.yaml

@@ -12,37 +12,13 @@ metadata:
 
 spec:
   description: Text detector based on PixelLink architecture with MobileNetV2-like as a backbone for indoor/outdoor scenes.
-  runtime: 'python:3.6'
+  runtime: 'python:3.8'
   handler: main:handler
   eventTimeout: 30s
-  env:
-    - name: NUCLIO_PYTHON_EXE_PATH
-      value: /opt/nuclio/common/openvino/python3
-
-  volumes:
-    - volume:
-        name: openvino-common
-        configMap:
-          name: "cvat-nuclio-openvino-common"
-          defaultMode: 0750
-      volumeMount:
-        name: openvino-common
-        mountPath: /opt/nuclio/common/openvino
 
   build:
     image: cvat.openvino.omz.intel.text-detection-0004
-    baseImage: openvino/ubuntu18_dev:2020.2
-
-    directives:
-      preCopy:
-        - kind: USER
-          value: root
-        - kind: WORKDIR
-          value: /opt/nuclio
-        - kind: RUN
-          value: ln -s /usr/bin/pip3 /usr/bin/pip
-        - kind: RUN
-          value: /opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name text-detection-0004 -o /opt/nuclio/open_model_zoo
+    baseImage: cvat.openvino.omz.intel.text-detection-0004.base
 
   triggers:
     myHttpTrigger:

serverless/openvino/omz/public/faster_rcnn_inception_resnet_v2_atrous_coco/nuclio/Dockerfile

+FROM openvino/ubuntu20_dev:2022.3.0 AS build
+
+USER root
+
+RUN omz_downloader \
+    --name faster_rcnn_inception_resnet_v2_atrous_coco \
+    -o /opt/nuclio/open_model_zoo.orig
+
+RUN omz_converter \
+    --name faster_rcnn_inception_resnet_v2_atrous_coco \
+    --precisions FP32 \
+    -d /opt/nuclio/open_model_zoo.orig \
+    -o /opt/nuclio/open_model_zoo
+
+FROM cvat.openvino.base
+
+COPY --from=build --chown=root:root /opt/nuclio/open_model_zoo /opt/nuclio/open_model_zoo

serverless/openvino/omz/public/faster_rcnn_inception_v2_coco/nuclio/function.yaml → serverless/openvino/omz/public/faster_rcnn_inception_resnet_v2_atrous_coco/nuclio/function.yaml

 metadata:
-  name: openvino-omz-public-faster-rcnn-inception-v2-coco
+  name: openvino-omz-public-faster-rcnn-inception-resnet-v2-atrous-coco
   namespace: cvat
   annotations:
     name: Faster RCNN
@@ -90,40 +90,14 @@ metadata:
       ]
 
 spec:
-  description: Faster RCNN inception v2 COCO via Intel OpenVINO toolkit
-  runtime: 'python:3.6'
+  description: Faster R-CNN with Inception ResNet v2 Atrous via Intel OpenVINO toolkit
+  runtime: 'python:3.8'
   handler: main:handler
   eventTimeout: 30s
-  env:
-    - name: NUCLIO_PYTHON_EXE_PATH
-      value: /opt/nuclio/common/openvino/python3
-
-  volumes:
-    - volume:
-        name: openvino-common
-        configMap:
-          name: "cvat-nuclio-openvino-common"
-          defaultMode: 0750
-      volumeMount:
-        name: openvino-common
-        mountPath: /opt/nuclio/common/openvino
 
   build:
-    image: cvat.openvino.omz.public.faster_rcnn_inception_v2_coco
-    baseImage: openvino/ubuntu18_dev:2020.2
-
-    directives:
-      preCopy:
-        - kind: USER
-          value: root
-        - kind: WORKDIR
-          value: /opt/nuclio
-        - kind: RUN
-          value: ln -s /usr/bin/pip3 /usr/bin/pip
-        - kind: RUN
-          value: /opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name faster_rcnn_inception_v2_coco -o /opt/nuclio/open_model_zoo
-        - kind: RUN
-          value: /opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader/converter.py --name faster_rcnn_inception_v2_coco --precisions FP32 -d /opt/nuclio/open_model_zoo -o /opt/nuclio/open_model_zoo
+    image: cvat.openvino.omz.public.faster_rcnn_inception_resnet_v2_atrous_coco
+    baseImage: cvat.openvino.omz.public.faster_rcnn_inception_resnet_v2_atrous_coco.base
 
   triggers:
     myHttpTrigger:

serverless/openvino/omz/public/faster_rcnn_inception_v2_coco/nuclio/main.py → serverless/openvino/omz/public/faster_rcnn_inception_resnet_v2_atrous_coco/nuclio/main.py

@@ -22,7 +22,7 @@ def init_context(context):
     context.logger.info("Init context...100%")
 
 def handler(context, event):
-    context.logger.info("Run faster_rcnn_inception_v2_coco model")
+    context.logger.info("Run faster_rcnn_inception_resnet_v2_atrous_coco model")
     data = event.body
     buf = io.BytesIO(base64.b64decode(data["image"]))
     threshold = float(data.get("threshold", 0.5))

serverless/openvino/omz/public/faster_rcnn_inception_v2_coco/nuclio/model_handler.py → serverless/openvino/omz/public/faster_rcnn_inception_resnet_v2_atrous_coco/nuclio/model_handler.py

@@ -8,9 +8,9 @@ from model_loader import ModelLoader
 class ModelHandler:
     def __init__(self, labels):
         base_dir = os.path.abspath(os.environ.get("MODEL_PATH",
-            "/opt/nuclio/open_model_zoo/public/faster_rcnn_inception_v2_coco/FP32"))
-        model_xml = os.path.join(base_dir, "faster_rcnn_inception_v2_coco.xml")
-        model_bin = os.path.join(base_dir, "faster_rcnn_inception_v2_coco.bin")
+            "/opt/nuclio/open_model_zoo/public/faster_rcnn_inception_resnet_v2_atrous_coco/FP32"))
+        model_xml = os.path.join(base_dir, "faster_rcnn_inception_resnet_v2_atrous_coco.xml")
+        model_bin = os.path.join(base_dir, "faster_rcnn_inception_resnet_v2_atrous_coco.bin")
         self.model = ModelLoader(model_xml, model_bin)
         self.labels = labels
 
@@ -36,4 +36,4 @@ class ModelHandler:
                     "type": "rectangle",
                 })
 
-        return results
\ No newline at end of file
+        return results

serverless/openvino/omz/public/mask_rcnn_inception_resnet_v2_atrous_coco/nuclio/Dockerfile

+FROM openvino/ubuntu20_dev:2022.3.0 AS build
+
+USER root
+
+RUN omz_downloader \
+    --name mask_rcnn_inception_resnet_v2_atrous_coco \
+    -o /opt/nuclio/open_model_zoo.orig
+
+RUN omz_converter \
+    --name mask_rcnn_inception_resnet_v2_atrous_coco \
+    --precisions FP32 \
+    -d /opt/nuclio/open_model_zoo.orig \
+    -o /opt/nuclio/open_model_zoo
+
+FROM cvat.openvino.base
+
+USER root
+
+RUN pip install --no-cache-dir scikit-image
+
+COPY --from=build /opt/nuclio/open_model_zoo /opt/nuclio/open_model_zoo
+
+USER openvino

serverless/openvino/omz/public/mask_rcnn_inception_resnet_v2_atrous_coco/nuclio/function.yaml

@@ -2,7 +2,7 @@
 # have enough memory (more than 4GB). Look here how to do that
 # https://stackoverflow.com/questions/44417159/docker-process-killed-with-cryptic-killed-message
 metadata:
-  name: openvino-mask-rcnn-inception-resnet-v2-atrous-coco
+  name: openvino-omz-public-mask-rcnn-inception-resnet-v2-atrous-coco
   namespace: cvat
   annotations:
     name: Mask RCNN
@@ -94,45 +94,13 @@ metadata:
 
 spec:
   description: Mask RCNN inception resnet v2 COCO via Intel OpenVINO
-  runtime: 'python:3.6'
+  runtime: 'python:3.8'
   handler: main:handler
   eventTimeout: 60s
-  env:
-    - name: NUCLIO_PYTHON_EXE_PATH
-      value: /opt/nuclio/common/openvino/python3
-
-  volumes:
-    - volume:
-        name: openvino-common
-        configMap:
-          name: "cvat-nuclio-openvino-common"
-          defaultMode: 0750
-      volumeMount:
-        name: openvino-common
-        mountPath: /opt/nuclio/common/openvino
 
   build:
     image: cvat.openvino.omz.public.mask_rcnn_inception_resnet_v2_atrous_coco
-    baseImage: openvino/ubuntu18_dev:2020.2
-
-    directives:
-      preCopy:
-        - kind: USER
-          value: root
-        - kind: WORKDIR
-          value: /opt/nuclio
-        - kind: RUN
-          value: ln -s /usr/bin/pip3 /usr/bin/pip
-        - kind: RUN
-          value: /opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name mask_rcnn_inception_resnet_v2_atrous_coco -o /opt/nuclio/open_model_zoo
-        - kind: RUN
-          value: /opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader/converter.py --name mask_rcnn_inception_resnet_v2_atrous_coco --precisions FP32 -d /opt/nuclio/open_model_zoo -o /opt/nuclio/open_model_zoo
-
-      postCopy:
-        - kind: RUN
-          value: apt update && DEBIAN_FRONTEND=noninteractive apt install --no-install-recommends -y python3-skimage
-        - kind: RUN
-          value: pip3 install "numpy<1.16.0" # workaround for skimage
+    baseImage: cvat.openvino.omz.public.mask_rcnn_inception_resnet_v2_atrous_coco.base
 
   triggers:
     myHttpTrigger:

serverless/openvino/omz/public/yolo-v3-tf/nuclio/Dockerfile

+FROM openvino/ubuntu20_dev:2022.3.0 AS build
+
+USER root
+
+RUN omz_downloader \
+    --name yolo-v3-tf \
+    -o /opt/nuclio/open_model_zoo.orig
+
+RUN omz_converter \
+    --name yolo-v3-tf \
+    --precisions FP32 \
+    -d /opt/nuclio/open_model_zoo.orig \
+    -o /opt/nuclio/open_model_zoo
+
+FROM cvat.openvino.base
+
+COPY --from=build --chown=root:root /opt/nuclio/open_model_zoo /opt/nuclio/open_model_zoo

serverless/openvino/omz/public/yolo-v3-tf/nuclio/function.yaml

@@ -91,39 +91,13 @@ metadata:
 
 spec:
   description: YOLO v3 via Intel OpenVINO
-  runtime: 'python:3.6'
+  runtime: 'python:3.8'
   handler: main:handler
   eventTimeout: 30s
-  env:
-    - name: NUCLIO_PYTHON_EXE_PATH
-      value: /opt/nuclio/common/openvino/python3
-
-  volumes:
-    - volume:
-        name: openvino-common
-        configMap:
-          name: "cvat-nuclio-openvino-common"
-          defaultMode: 0750
-      volumeMount:
-        name: openvino-common
-        mountPath: /opt/nuclio/common/openvino
 
   build:
-    image: cvat/openvino.omz.public.yolo-v3-tf
-    baseImage: openvino/ubuntu18_dev:2020.2
-
-    directives:
-      preCopy:
-        - kind: USER
-          value: root
-        - kind: WORKDIR
-          value: /opt/nuclio
-        - kind: RUN
-          value: ln -s /usr/bin/pip3 /usr/bin/pip
-        - kind: RUN
-          value: /opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name yolo-v3-tf -o /opt/nuclio/open_model_zoo
-        - kind: RUN
-          value: /opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader/converter.py --name yolo-v3-tf --precisions FP32 -d /opt/nuclio/open_model_zoo -o /opt/nuclio/open_model_zoo
+    image: cvat.openvino.omz.public.yolo-v3-tf
+    baseImage: cvat.openvino.omz.public.yolo-v3-tf.base
 
   triggers:
     myHttpTrigger:

serverless/openvino/omz/public/yolo-v3-tf/nuclio/model_handler.py

@@ -4,24 +4,26 @@
 
 import os
 from math import exp
+
+import ngraph
+
 from model_loader import ModelLoader
 
 class YoloParams:
     # ------------------------------------------- Extracting layer parameters ------------------------------------------
     # Magic numbers are copied from yolo samples
     def __init__(self, param, side):
-        self.num = 3 if 'num' not in param else int(param['num'])
-        self.coords = 4 if 'coords' not in param else int(param['coords'])
-        self.classes = 80 if 'classes' not in param else int(param['classes'])
+        self.num = param.get('num', 3)
+        self.coords = param.get('coords', 4)
+        self.classes = param.get('classes', 80)
         self.side = side
-        self.anchors = [10.0, 13.0, 16.0, 30.0, 33.0, 23.0, 30.0, 61.0, 62.0, 45.0, 59.0, 119.0, 116.0, 90.0, 156.0,
-                        198.0,
-                        373.0, 326.0] if 'anchors' not in param else [float(a) for a in param['anchors'].split(',')]
+        self.anchors = param.get('anchors', [
+            10.0, 13.0, 16.0, 30.0, 33.0, 23.0, 30.0, 61.0, 62.0, 45.0, 59.0,
+            119.0, 116.0, 90.0, 156.0, 198.0, 373.0, 326.0])
 
         self.isYoloV3 = False
 
-        if param.get('mask'):
-            mask = [int(idx) for idx in param['mask'].split(',')]
+        if mask := param.get('mask'):
             self.num = len(mask)
 
             maskedAnchors = []
@@ -119,6 +121,19 @@ class ModelHandler:
         self.model = ModelLoader(model_xml, model_bin)
         self.labels = labels
 
+        ng_func = ngraph.function_from_cnn(self.model.network)
+
+        self.output_info = {}
+
+        for node in ng_func.get_ordered_ops():
+            layer_name = node.get_friendly_name()
+            if layer_name not in self.model.network.outputs:
+                continue
+            parent_node = node.inputs()[0].get_source_output().get_node()
+            shape = list(parent_node.shape)
+            yolo_params = YoloParams(node._get_attributes(), shape[2])
+            self.output_info[layer_name] = (shape, yolo_params)
+
     def infer(self, image, threshold):
         output_layer = self.model.infer(image)
 
@@ -126,10 +141,10 @@ class ModelHandler:
         objects = []
         origin_im_size = (image.height, image.width)
         for layer_name, out_blob in output_layer.items():
-            out_blob = out_blob.reshape(self.model.layers[self.model.layers[layer_name].parents[0]].shape)
-            layer_params = YoloParams(self.model.layers[layer_name].params, out_blob.shape[2])
+            shape, yolo_params = self.output_info[layer_name]
+            out_blob = out_blob.reshape(shape)
             objects += parse_yolo_region(out_blob, self.model.input_size(),
-                origin_im_size, layer_params, threshold)
+                origin_im_size, yolo_params, threshold)
 
         # Filtering overlapping boxes (non-maximum suppression)
         IOU_THRESHOLD = 0.4
@@ -157,4 +172,4 @@ class ModelHandler:
                     "type": "rectangle",
                 })
 
-        return results
\ No newline at end of file
+        return results

site/content/en/docs/administration/advanced/installation_automatic_annotation.md

@@ -45,33 +45,16 @@ description: 'Information about the installation of components needed for semi-a
   sudo ln -sf $(pwd)/nuctl-<version>-linux-amd64 /usr/local/bin/nuctl
   ```
 
-- Create `cvat` project inside nuclio dashboard where you will deploy new serverless functions
-  and deploy a couple of DL models. Commands below should be run only after CVAT has been installed
+- Deploy a couple of functions.
+  This will automatically create a `cvat` Nuclio project to contain the functions.
+  Commands below should be run only after CVAT has been installed
   using `docker compose` because it runs nuclio dashboard which manages all serverless functions.
 
   ```bash
-  nuctl create project cvat
+  ./serverless/deploy_cpu.sh serverless/openvino/dextr
+  ./serverless/deploy_cpu.sh serverless/openvino/omz/public/yolo-v3-tf
   ```
 
-  ```bash
-  nuctl deploy --project-name cvat \
-    --path serverless/openvino/dextr/nuclio \
-    --volume `pwd`/serverless/common:/opt/nuclio/common \
-    --platform local
-  ```
-
-  ```bash
-  nuctl deploy --project-name cvat \
-    --path serverless/openvino/omz/public/yolo-v3-tf/nuclio \
-    --volume `pwd`/serverless/common:/opt/nuclio/common \
-    --platform local
-  ```
-
-  **Note:**
-
-  - See [deploy_cpu.sh](https://github.com/cvat-ai/cvat/blob/develop/serverless/deploy_cpu.sh)
-    for more examples.
-
   #### GPU Support
 
   You will need to install [Nvidia Container Toolkit](https://www.tensorflow.org/install/docker#gpu_support).

site/content/en/docs/contributing/setup-additional-components.md

@@ -15,69 +15,14 @@ Follow this [guide](/docs/administration/advanced/installation_automatic_annotat
   of the Nuclio dashboard. All you need in order to run the dashboard is Docker. See
   [nuclio documentation](https://github.com/nuclio/nuclio#quick-start-steps)
   for more details.
-- Create `cvat` project inside nuclio dashboard where you will deploy new
-  serverless functions and deploy a couple of DL models.
+- Deploy a couple of functions.
+  This will automatically create a `cvat` Nuclio project to contain the functions.
 
 ```bash
-nuctl create project cvat
+./serverless/deploy_cpu.sh serverless/openvino/dextr
+./serverless/deploy_cpu.sh serverless/openvino/omz/public/yolo-v3-tf
 ```
 
-```bash
-nuctl deploy --project-name cvat \
-    --path serverless/openvino/dextr/nuclio \
-    --volume `pwd`/serverless/common:/opt/nuclio/common \
-    --platform local
-```
-
-<details>
-
-```
-20.07.17 12:02:23.247                     nuctl (I) Deploying function {"name": ""}
-20.07.17 12:02:23.248                     nuctl (I) Building {"versionInfo": "Label: 1.4.8, Git commit: 238d4539ac7783896d6c414535d0462b5f4cbcf1, OS: darwin, Arch: amd64, Go version: go1.14.3", "name": ""}
-20.07.17 12:02:23.447                     nuctl (I) Cleaning up before deployment
-20.07.17 12:02:23.535                     nuctl (I) Function already exists, deleting
-20.07.17 12:02:25.877                     nuctl (I) Staging files and preparing base images
-20.07.17 12:02:25.891                     nuctl (I) Building processor image {"imageName": "cvat/openvino.dextr:latest"}
-20.07.17 12:02:25.891     nuctl.platform.docker (I) Pulling image {"imageName": "quay.io/nuclio/handler-builder-python-onbuild:1.4.8-amd64"}
-20.07.17 12:02:29.270     nuctl.platform.docker (I) Pulling image {"imageName": "quay.io/nuclio/uhttpc:0.0.1-amd64"}
-20.07.17 12:02:33.208            nuctl.platform (I) Building docker image {"image": "cvat/openvino.dextr:latest"}
-20.07.17 12:02:34.464            nuctl.platform (I) Pushing docker image into registry {"image": "cvat/openvino.dextr:latest", "registry": ""}
-20.07.17 12:02:34.464            nuctl.platform (I) Docker image was successfully built and pushed into docker registry {"image": "cvat/openvino.dextr:latest"}
-20.07.17 12:02:34.464                     nuctl (I) Build complete {"result": {"Image":"cvat/openvino.dextr:latest","UpdatedFunctionConfig":{"metadata":{"name":"openvino.dextr","namespace":"nuclio","labels":{"nuclio.io/project-name":"cvat"},"annotations":{"framework":"openvino","spec":"","type":"interactor"}},"spec":{"description":"Deep Extreme Cut","handler":"main:handler","runtime":"python:3.6","env":[{"name":"NUCLIO_PYTHON_EXE_PATH","value":"/opt/nuclio/python3"}],"resources":{},"image":"cvat/openvino.dextr:latest","targetCPU":75,"triggers":{"myHttpTrigger":{"class":"","kind":"http","name":"","maxWorkers":2,"workerAvailabilityTimeoutMilliseconds":10000,"attributes":{"maxRequestBodySize":33554432}}},"volumes":[{"volume":{"name":"volume-1","hostPath":{"path":"/Users/nmanovic/Workspace/cvat/serverless/openvino/common"}},"volumeMount":{"name":"volume-1","mountPath":"/opt/nuclio/common"}}],"build":{"image":"cvat/openvino.dextr","baseImage":"openvino/ubuntu18_runtime:2020.2","directives":{"postCopy":[{"kind":"RUN","value":"curl -O https://download.01.org/openvinotoolkit/models_contrib/cvat/dextr_model_v1.zip"},{"kind":"RUN","value":"unzip dextr_model_v1.zip"},{"kind":"RUN","value":"pip3 install Pillow"},{"kind":"USER","value":"openvino"}],"preCopy":[{"kind":"USER","value":"root"},{"kind":"WORKDIR","value":"/opt/nuclio"},{"kind":"RUN","value":"ln -s /usr/bin/pip3 /usr/bin/pip"}]},"codeEntryType":"image"},"platform":{},"readinessTimeoutSeconds":60,"eventTimeout":"30s"}}}}
-20.07.17 12:02:35.012            nuctl.platform (I) Waiting for function to be ready {"timeout": 60}
-20.07.17 12:02:37.448                     nuctl (I) Function deploy complete {"httpPort": 55274}
-```
-
-</details>
-
-```bash
-nuctl deploy --project-name cvat \
-    --path serverless/openvino/omz/public/yolo-v3-tf/nuclio \
-    --volume `pwd`/serverless/common:/opt/nuclio/common \
-    --platform local
-```
-
-<details>
-
-```
-20.07.17 12:05:23.377                     nuctl (I) Deploying function {"name": ""}
-20.07.17 12:05:23.378                     nuctl (I) Building {"versionInfo": "Label: 1.4.8, Git commit: 238d4539ac7783896d6c414535d0462b5f4cbcf1, OS: darwin, Arch: amd64, Go version: go1.14.3", "name": ""}
-20.07.17 12:05:23.590                     nuctl (I) Cleaning up before deployment
-20.07.17 12:05:23.694                     nuctl (I) Function already exists, deleting
-20.07.17 12:05:24.271                     nuctl (I) Staging files and preparing base images
-20.07.17 12:05:24.274                     nuctl (I) Building processor image {"imageName": "cvat/openvino.omz.public.yolo-v3-tf:latest"}
-20.07.17 12:05:24.274     nuctl.platform.docker (I) Pulling image {"imageName": "quay.io/nuclio/handler-builder-python-onbuild:1.4.8-amd64"}
-20.07.17 12:05:27.432     nuctl.platform.docker (I) Pulling image {"imageName": "quay.io/nuclio/uhttpc:0.0.1-amd64"}
-20.07.17 12:05:31.462            nuctl.platform (I) Building docker image {"image": "cvat/openvino.omz.public.yolo-v3-tf:latest"}
-20.07.17 12:05:32.798            nuctl.platform (I) Pushing docker image into registry {"image": "cvat/openvino.omz.public.yolo-v3-tf:latest", "registry": ""}
-20.07.17 12:05:32.798            nuctl.platform (I) Docker image was successfully built and pushed into docker registry {"image": "cvat/openvino.omz.public.yolo-v3-tf:latest"}
-20.07.17 12:05:32.798                     nuctl (I) Build complete {"result": {"Image":"cvat/openvino.omz.public.yolo-v3-tf:latest","UpdatedFunctionConfig":{"metadata":{"name":"openvino.omz.public.yolo-v3-tf","namespace":"nuclio","labels":{"nuclio.io/project-name":"cvat"},"annotations":{"framework":"openvino","name":"YOLO v3","spec":"[\n  { \"id\": 0, \"name\": \"person\" },\n  { \"id\": 1, \"name\": \"bicycle\" },\n  { \"id\": 2, \"name\": \"car\" },\n  { \"id\": 3, \"name\": \"motorbike\" },\n  { \"id\": 4, \"name\": \"aeroplane\" },\n  { \"id\": 5, \"name\": \"bus\" },\n  { \"id\": 6, \"name\": \"train\" },\n  { \"id\": 7, \"name\": \"truck\" },\n  { \"id\": 8, \"name\": \"boat\" },\n  { \"id\": 9, \"name\": \"traffic light\" },\n  { \"id\": 10, \"name\": \"fire hydrant\" },\n  { \"id\": 11, \"name\": \"stop sign\" },\n  { \"id\": 12, \"name\": \"parking meter\" },\n  { \"id\": 13, \"name\": \"bench\" },\n  { \"id\": 14, \"name\": \"bird\" },\n  { \"id\": 15, \"name\": \"cat\" },\n  { \"id\": 16, \"name\": \"dog\" },\n  { \"id\": 17, \"name\": \"horse\" },\n  { \"id\": 18, \"name\": \"sheep\" },\n  { \"id\": 19, \"name\": \"cow\" },\n  { \"id\": 20, \"name\": \"elephant\" },\n  { \"id\": 21, \"name\": \"bear\" },\n  { \"id\": 22, \"name\": \"zebra\" },\n  { \"id\": 23, \"name\": \"giraffe\" },\n  { \"id\": 24, \"name\": \"backpack\" },\n  { \"id\": 25, \"name\": \"umbrella\" },\n  { \"id\": 26, \"name\": \"handbag\" },\n  { \"id\": 27, \"name\": \"tie\" },\n  { \"id\": 28, \"name\": \"suitcase\" },\n  { \"id\": 29, \"name\": \"frisbee\" },\n  { \"id\": 30, \"name\": \"skis\" },\n  { \"id\": 31, \"name\": \"snowboard\" },\n  { \"id\": 32, \"name\": \"sports ball\" },\n  { \"id\": 33, \"name\": \"kite\" },\n  { \"id\": 34, \"name\": \"baseball bat\" },\n  { \"id\": 35, \"name\": \"baseball glove\" },\n  { \"id\": 36, \"name\": \"skateboard\" },\n  { \"id\": 37, \"name\": \"surfboard\" },\n  { \"id\": 38, \"name\": \"tennis racket\" },\n  { \"id\": 39, \"name\": \"bottle\" },\n  { \"id\": 40, \"name\": \"wine glass\" },\n  { \"id\": 41, \"name\": \"cup\" },\n  { \"id\": 42, \"name\": \"fork\" },\n  { \"id\": 43, \"name\": \"knife\" },\n  { \"id\": 44, \"name\": \"spoon\" },\n  { \"id\": 45, \"name\": \"bowl\" },\n  { \"id\": 46, \"name\": \"banana\" },\n  { \"id\": 47, \"name\": \"apple\" },\n  { \"id\": 48, \"name\": \"sandwich\" },\n  { \"id\": 49, \"name\": \"orange\" },\n  { \"id\": 50, \"name\": \"broccoli\" },\n  { \"id\": 51, \"name\": \"carrot\" },\n  { \"id\": 52, \"name\": \"hot dog\" },\n  { \"id\": 53, \"name\": \"pizza\" },\n  { \"id\": 54, \"name\": \"donut\" },\n  { \"id\": 55, \"name\": \"cake\" },\n  { \"id\": 56, \"name\": \"chair\" },\n  { \"id\": 57, \"name\": \"sofa\" },\n  { \"id\": 58, \"name\": \"pottedplant\" },\n  { \"id\": 59, \"name\": \"bed\" },\n  { \"id\": 60, \"name\": \"diningtable\" },\n  { \"id\": 61, \"name\": \"toilet\" },\n  { \"id\": 62, \"name\": \"tvmonitor\" },\n  { \"id\": 63, \"name\": \"laptop\" },\n  { \"id\": 64, \"name\": \"mouse\" },\n  { \"id\": 65, \"name\": \"remote\" },\n  { \"id\": 66, \"name\": \"keyboard\" },\n  { \"id\": 67, \"name\": \"cell phone\" },\n  { \"id\": 68, \"name\": \"microwave\" },\n  { \"id\": 69, \"name\": \"oven\" },\n  { \"id\": 70, \"name\": \"toaster\" },\n  { \"id\": 71, \"name\": \"sink\" },\n  { \"id\": 72, \"name\": \"refrigerator\" },\n  { \"id\": 73, \"name\": \"book\" },\n  { \"id\": 74, \"name\": \"clock\" },\n  { \"id\": 75, \"name\": \"vase\" },\n  { \"id\": 76, \"name\": \"scissors\" },\n  { \"id\": 77, \"name\": \"teddy bear\" },\n  { \"id\": 78, \"name\": \"hair drier\" },\n  { \"id\": 79, \"name\": \"toothbrush\" }\n]\n","type":"detector"}},"spec":{"description":"YOLO v3 via Intel OpenVINO","handler":"main:handler","runtime":"python:3.6","env":[{"name":"NUCLIO_PYTHON_EXE_PATH","value":"/opt/nuclio/common/python3"}],"resources":{},"image":"cvat/openvino.omz.public.yolo-v3-tf:latest","targetCPU":75,"triggers":{"myHttpTrigger":{"class":"","kind":"http","name":"","maxWorkers":2,"workerAvailabilityTimeoutMilliseconds":10000,"attributes":{"maxRequestBodySize":33554432}}},"volumes":[{"volume":{"name":"volume-1","hostPath":{"path":"/Users/nmanovic/Workspace/cvat/serverless/openvino/common"}},"volumeMount":{"name":"volume-1","mountPath":"/opt/nuclio/common"}}],"build":{"image":"cvat/openvino.omz.public.yolo-v3-tf","baseImage":"openvino/ubuntu18_dev:2020.2","directives":{"postCopy":[{"kind":"USER","value":"openvino"}],"preCopy":[{"kind":"USER","value":"root"},{"kind":"WORKDIR","value":"/opt/nuclio"},{"kind":"RUN","value":"ln -s /usr/bin/pip3 /usr/bin/pip"},{"kind":"RUN","value":"/opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name yolo-v3-tf -o /opt/nuclio/open_model_zoo"},{"kind":"RUN","value":"/opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader/converter.py --name yolo-v3-tf --precisions FP32 -d /opt/nuclio/open_model_zoo -o /opt/nuclio/open_model_zoo"}]},"codeEntryType":"image"},"platform":{},"readinessTimeoutSeconds":60,"eventTimeout":"30s"}}}}
-20.07.17 12:05:33.285            nuctl.platform (I) Waiting for function to be ready {"timeout": 60}
-20.07.17 12:05:35.452                     nuctl (I) Function deploy complete {"httpPort": 57308}
-```
-
-</details>
-
 - Display a list of running serverless functions using `nuctl` command or see them
   in nuclio dashboard:
 
@@ -103,23 +48,23 @@ image=$(curl https://upload.wikimedia.org/wikipedia/en/7/7d/Lenna_%28test_image%
 cat << EOF > /tmp/input.json
 {"image": "$image"}
 EOF
-cat /tmp/input.json | nuctl invoke openvino.omz.public.yolo-v3-tf -c 'application/json'
+cat /tmp/input.json | nuctl invoke openvino-omz-public-yolo-v3-tf -c 'application/json'
 ```
 
 <details>
 
 ```
-20.07.17 12:07:44.519    nuctl.platform.invoker (I) Executing function {"method": "POST", "url": "http://:57308", "headers": {"Content-Type":["application/json"],"X-Nuclio-Log-Level":["info"],"X-Nuclio-Target":["openvino.omz.public.yolo-v3-tf"]}}
-20.07.17 12:07:45.275    nuctl.platform.invoker (I) Got response {"status": "200 OK"}
-20.07.17 12:07:45.275                     nuctl (I) >>> Start of function logs
-20.07.17 12:07:45.275 ino.omz.public.yolo-v3-tf (I) Run yolo-v3-tf model {"worker_id": "0", "time": 1594976864570.9353}
-20.07.17 12:07:45.275                     nuctl (I) <<< End of function logs
+23.05.11 22:14:17.275    nuctl.platform.invoker (I) Executing function {"method": "POST", "url": "http://0.0.0.0:32771", "bodyLength": 631790, "headers": {"Content-Type":["application/json"],"X-Nuclio-Log-Level":["info"],"X-Nuclio-Target":["openvino-omz-public-yolo-v3-tf"]}}
+23.05.11 22:14:17.788    nuctl.platform.invoker (I) Got response {"status": "200 OK"}
+23.05.11 22:14:17.789                     nuctl (I) >>> Start of function logs
+23.05.11 22:14:17.789 ino-omz-public-yolo-v3-tf (I) Run yolo-v3-tf model {"worker_id": "0", "time": 1683828857301.8765}
+23.05.11 22:14:17.789                     nuctl (I) <<< End of function logs
 
 > Response headers:
-Date = Fri, 17 Jul 2020 09:07:45 GMT
+Server = nuclio
+Date = Thu, 11 May 2023 18:14:17 GMT
 Content-Type = application/json
 Content-Length = 100
-Server = nuclio
 
 > Response body:
 [