Tutorial about serverless functions (#3124)

Co-authored-by: Roman Donchenko <roman.donchenko@intel.com>
cvat-ai · Jul 21, 2021 · 0baf794 · 0baf794
1 parent 330b8a8
commit 0baf794
Show file tree

Hide file tree

Showing 73 changed files with 1,581 additions and 64 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -13,6 +13,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Support of cloud storage without copying data into CVAT: server part (<https://github.com/openvinotoolkit/cvat/pull/2620>)
 - Filter `is_active` for user list (<https://github.com/openvinotoolkit/cvat/pull/3235>)
 - Ability to export/import tasks (<https://github.com/openvinotoolkit/cvat/pull/3056>)
+- Add a tutorial for semi-automatic/automatic annotation (<https://github.com/openvinotoolkit/cvat/pull/3124>)
 - Explicit "Done" button when drawing any polyshapes (<https://github.com/openvinotoolkit/cvat/pull/3417>)
 
 ### Changed

diff --git a/README.md b/README.md
@@ -91,6 +91,7 @@ For more information about supported formats look at the
 | [Inside-Outside Guidance](/serverless/pytorch/shiyinzhang/iog/nuclio)                                   | interactor | PyTorch    | X   |     |
 | [Faster RCNN](/serverless/tensorflow/faster_rcnn_inception_v2_coco/nuclio)                              | detector   | TensorFlow | X   | X   |
 | [Mask RCNN](/serverless/tensorflow/matterport/mask_rcnn/nuclio)                                         | detector   | TensorFlow | X   | X   |
+| [RetinaNet](serverless/pytorch/facebookresearch/detectron2/retinanet/nuclio)                            | detector   | PyTorch    | X   | X   |
 
 <!--lint enable maximum-line-length-->
 
@@ -162,8 +163,8 @@ Other ways to ask questions and get our support:
 - [DataIsKey](https://dataiskey.eu/annotation-tool/) uses CVAT as their prime data labeling tool
   to offer annotation services for projects of any size.
 - [Human Protocol](https://hmt.ai) uses CVAT as a way of adding annotation service to the human protocol.
-<!-- prettier-ignore-start -->
-<!-- Badges -->
+  <!-- prettier-ignore-start -->
+  <!-- Badges -->
 
 [docker-server-pulls-img]: https://img.shields.io/docker/pulls/openvino/cvat_server.svg?style=flat-square&label=server%20pulls
 [docker-server-image-url]: https://hub.docker.com/r/openvino/cvat_server

diff --git a/serverless/deploy_cpu.sh b/serverless/deploy_cpu.sh
@@ -6,7 +6,9 @@ FUNCTIONS_DIR=${1:-$SCRIPT_DIR}
 
 nuctl create project cvat
 
-for func_config in $(find "$FUNCTIONS_DIR" -name "function.yaml")
+shopt -s globstar
+
+for func_config in "$FUNCTIONS_DIR"/**/function.yaml
 do
     func_root=$(dirname "$func_config")
     echo Deploying $(dirname "$func_root") function...

diff --git a/serverless/deploy_gpu.sh b/serverless/deploy_gpu.sh
@@ -2,24 +2,19 @@
 # Sample commands to deploy nuclio functions on GPU
 
 SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+FUNCTIONS_DIR=${1:-$SCRIPT_DIR}
 
 nuctl create project cvat
 
-nuctl deploy --project-name cvat \
-    --path "$SCRIPT_DIR/tensorflow/faster_rcnn_inception_v2_coco/nuclio" \
-    --platform local --base-image tensorflow/tensorflow:2.1.1-gpu \
-    --desc "GPU based Faster RCNN from Tensorflow Object Detection API" \
-    --image cvat/tf.faster_rcnn_inception_v2_coco_gpu \
-    --triggers '{"myHttpTrigger": {"maxWorkers": 1}}' \
-    --resource-limit nvidia.com/gpu=1 --verbose
-
-nuctl deploy --project-name cvat \
-    --path "$SCRIPT_DIR/tensorflow/matterport/mask_rcnn/nuclio" \
-    --platform local --base-image tensorflow/tensorflow:1.15.5-gpu-py3 \
-    --desc "GPU based implementation of Mask RCNN on Python 3, Keras, and TensorFlow." \
-    --image cvat/tf.matterport.mask_rcnn_gpu\
-    --triggers '{"myHttpTrigger": {"maxWorkers": 1}}' \
-    --resource-limit nvidia.com/gpu=1 --verbose
+shopt -s globstar
 
+for func_config in "$FUNCTIONS_DIR"/**/function-gpu.yaml
+do
+    func_root=$(dirname "$func_config")
+    echo "Deploying $(dirname "$func_root") function..."
+    nuctl deploy --project-name cvat --path "$func_root" \
+        --volume "$SCRIPT_DIR/common:/opt/nuclio/common" \
+        --file "$func_config" --platform local
+done
 
 nuctl get function
diff --git a/serverless/openvino/dextr/nuclio/main.py b/serverless/openvino/dextr/nuclio/main.py
@@ -8,15 +8,15 @@ def init_context(context):
     context.logger.info("Init context...  0%")
 
     model = ModelHandler()
-    setattr(context.user_data, 'model', model)
+    context.user_data.model = model
 
     context.logger.info("Init context...100%")
 
 def handler(context, event):
     context.logger.info("call handler")
     data = event.body
     points = data["pos_points"]
-    buf = io.BytesIO(base64.b64decode(data["image"].encode('utf-8')))
+    buf = io.BytesIO(base64.b64decode(data["image"]))
     image = Image.open(buf)
 
     polygon = context.user_data.model.handle(image, points)

diff --git a/serverless/openvino/omz/intel/person-reidentification-retail-300/nuclio/main.py b/serverless/openvino/omz/intel/person-reidentification-retail-300/nuclio/main.py
@@ -8,15 +8,15 @@ def init_context(context):
     context.logger.info("Init context...  0%")
 
     model = ModelHandler()
-    setattr(context.user_data, 'model', model)
+    context.user_data.model = model
 
     context.logger.info("Init context...100%")
 
 def handler(context, event):
     context.logger.info("Run person-reidentification-retail-0300 model")
     data = event.body
-    buf0 = io.BytesIO(base64.b64decode(data["image0"].encode('utf-8')))
-    buf1 = io.BytesIO(base64.b64decode(data["image1"].encode('utf-8')))
+    buf0 = io.BytesIO(base64.b64decode(data["image0"]))
+    buf1 = io.BytesIO(base64.b64decode(data["image1"]))
     threshold = float(data.get("threshold", 0.5))
     max_distance = float(data.get("max_distance", 50))
     image0 = Image.open(buf0)

diff --git a/serverless/openvino/omz/intel/semantic-segmentation-adas-0001/nuclio/main.py b/serverless/openvino/omz/intel/semantic-segmentation-adas-0001/nuclio/main.py
@@ -9,20 +9,22 @@ def init_context(context):
     context.logger.info("Init context...  0%")
 
     # Read labels
-    functionconfig = yaml.safe_load(open("/opt/nuclio/function.yaml"))
+    with open("/opt/nuclio/function.yaml", 'rb') as function_file:
+        functionconfig = yaml.safe_load(function_file)
+
     labels_spec = functionconfig['metadata']['annotations']['spec']
     labels = {item['id']: item['name'] for item in json.loads(labels_spec)}
 
     # Read the DL model
     model = ModelHandler(labels)
-    setattr(context.user_data, 'model', model)
+    context.user_data.model = model
 
     context.logger.info("Init context...100%")
 
 def handler(context, event):
     context.logger.info("Run semantic-segmentation-adas-0001 model")
     data = event.body
-    buf = io.BytesIO(base64.b64decode(data["image"].encode('utf-8')))
+    buf = io.BytesIO(base64.b64decode(data["image"]))
     threshold = float(data.get("threshold", 0.5))
     image = Image.open(buf)
 

diff --git a/serverless/openvino/omz/intel/text-detection-0004/nuclio/main.py b/serverless/openvino/omz/intel/text-detection-0004/nuclio/main.py
@@ -9,20 +9,21 @@ def init_context(context):
     context.logger.info("Init context...  0%")
 
     # Read labels
-    functionconfig = yaml.safe_load(open("/opt/nuclio/function.yaml"))
+    with open("/opt/nuclio/function.yaml", 'rb') as function_file:
+        functionconfig = yaml.safe_load(function_file)
     labels_spec = functionconfig['metadata']['annotations']['spec']
     labels = {item['id']: item['name'] for item in json.loads(labels_spec)}
 
     # Read the DL model
     model = ModelHandler(labels)
-    setattr(context.user_data, 'model', model)
+    context.user_data.model = model
 
     context.logger.info("Init context...100%")
 
 def handler(context, event):
     context.logger.info("Run text-detection-0004 model")
     data = event.body
-    buf = io.BytesIO(base64.b64decode(data["image"].encode('utf-8')))
+    buf = io.BytesIO(base64.b64decode(data["image"]))
     pixel_threshold = float(data.get("pixel_threshold", 0.8))
     link_threshold = float(data.get("link_threshold", 0.8))
     image = Image.open(buf)

diff --git a/serverless/openvino/omz/public/faster_rcnn_inception_v2_coco/nuclio/main.py b/serverless/openvino/omz/public/faster_rcnn_inception_v2_coco/nuclio/main.py
@@ -9,20 +9,22 @@ def init_context(context):
     context.logger.info("Init context...  0%")
 
     # Read labels
-    functionconfig = yaml.safe_load(open("/opt/nuclio/function.yaml"))
+    with open("/opt/nuclio/function.yaml", 'rb') as function_file:
+        functionconfig = yaml.safe_load(function_file)
+
     labels_spec = functionconfig['metadata']['annotations']['spec']
     labels = {item['id']: item['name'] for item in json.loads(labels_spec)}
 
     # Read the DL model
     model = ModelHandler(labels)
-    setattr(context.user_data, 'model', model)
+    context.user_data.model = model
 
     context.logger.info("Init context...100%")
 
 def handler(context, event):
     context.logger.info("Run faster_rcnn_inception_v2_coco model")
     data = event.body
-    buf = io.BytesIO(base64.b64decode(data["image"].encode('utf-8')))
+    buf = io.BytesIO(base64.b64decode(data["image"]))
     threshold = float(data.get("threshold", 0.5))
     image = Image.open(buf)
 

diff --git a/serverless/openvino/omz/public/mask_rcnn_inception_resnet_v2_atrous_coco/nuclio/main.py b/serverless/openvino/omz/public/mask_rcnn_inception_resnet_v2_atrous_coco/nuclio/main.py
@@ -9,20 +9,22 @@ def init_context(context):
     context.logger.info("Init context...  0%")
 
     # Read labels
-    functionconfig = yaml.safe_load(open("/opt/nuclio/function.yaml"))
+    with open("/opt/nuclio/function.yaml", 'rb') as function_file:
+        functionconfig = yaml.safe_load(function_file)
+
     labels_spec = functionconfig['metadata']['annotations']['spec']
     labels = {item['id']: item['name'] for item in json.loads(labels_spec)}
 
     # Read the DL model
     model = ModelHandler(labels)
-    setattr(context.user_data, 'model', model)
+    context.user_data.model = model
 
     context.logger.info("Init context...100%")
 
 def handler(context, event):
     context.logger.info("Run mask_rcnn_inception_resnet_v2_atrous_coco model")
     data = event.body
-    buf = io.BytesIO(base64.b64decode(data["image"].encode('utf-8')))
+    buf = io.BytesIO(base64.b64decode(data["image"]))
     threshold = float(data.get("threshold", 0.2))
     image = Image.open(buf)
 

diff --git a/serverless/openvino/omz/public/yolo-v3-tf/nuclio/main.py b/serverless/openvino/omz/public/yolo-v3-tf/nuclio/main.py
@@ -9,20 +9,22 @@ def init_context(context):
     context.logger.info("Init context...  0%")
 
     # Read labels
-    functionconfig = yaml.safe_load(open("/opt/nuclio/function.yaml"))
+    with open("/opt/nuclio/function.yaml", 'rb') as function_file:
+        functionconfig = yaml.safe_load(function_file)
+
     labels_spec = functionconfig['metadata']['annotations']['spec']
     labels = {item['id']: item['name'] for item in json.loads(labels_spec)}
 
     # Read the DL model
     model = ModelHandler(labels)
-    setattr(context.user_data, 'model', model)
+    context.user_data.model = model
 
     context.logger.info("Init context...100%")
 
 def handler(context, event):
     context.logger.info("Run yolo-v3-tf model")
     data = event.body
-    buf = io.BytesIO(base64.b64decode(data["image"].encode('utf-8')))
+    buf = io.BytesIO(base64.b64decode(data["image"]))
     threshold = float(data.get("threshold", 0.5))
     image = Image.open(buf)
 

diff --git a/serverless/pytorch/facebookresearch/detectron2/retinanet/nuclio/function-gpu.yaml b/serverless/pytorch/facebookresearch/detectron2/retinanet/nuclio/function-gpu.yaml
@@ -0,0 +1,136 @@
+metadata:
+  name: pth.facebookresearch.detectron2.retinanet_r101
+  namespace: cvat
+  annotations:
+    name: RetinaNet R101
+    type: detector
+    framework: pytorch
+    spec: |
+      [
+        { "id": 1, "name": "person" },
+        { "id": 2, "name": "bicycle" },
+        { "id": 3, "name": "car" },
+        { "id": 4, "name": "motorcycle" },
+        { "id": 5, "name": "airplane" },
+        { "id": 6, "name": "bus" },
+        { "id": 7, "name": "train" },
+        { "id": 8, "name": "truck" },
+        { "id": 9, "name": "boat" },
+        { "id":10, "name": "traffic_light" },
+        { "id":11, "name": "fire_hydrant" },
+        { "id":13, "name": "stop_sign" },
+        { "id":14, "name": "parking_meter" },
+        { "id":15, "name": "bench" },
+        { "id":16, "name": "bird" },
+        { "id":17, "name": "cat" },
+        { "id":18, "name": "dog" },
+        { "id":19, "name": "horse" },
+        { "id":20, "name": "sheep" },
+        { "id":21, "name": "cow" },
+        { "id":22, "name": "elephant" },
+        { "id":23, "name": "bear" },
+        { "id":24, "name": "zebra" },
+        { "id":25, "name": "giraffe" },
+        { "id":27, "name": "backpack" },
+        { "id":28, "name": "umbrella" },
+        { "id":31, "name": "handbag" },
+        { "id":32, "name": "tie" },
+        { "id":33, "name": "suitcase" },
+        { "id":34, "name": "frisbee" },
+        { "id":35, "name": "skis" },
+        { "id":36, "name": "snowboard" },
+        { "id":37, "name": "sports_ball" },
+        { "id":38, "name": "kite" },
+        { "id":39, "name": "baseball_bat" },
+        { "id":40, "name": "baseball_glove" },
+        { "id":41, "name": "skateboard" },
+        { "id":42, "name": "surfboard" },
+        { "id":43, "name": "tennis_racket" },
+        { "id":44, "name": "bottle" },
+        { "id":46, "name": "wine_glass" },
+        { "id":47, "name": "cup" },
+        { "id":48, "name": "fork" },
+        { "id":49, "name": "knife" },
+        { "id":50, "name": "spoon" },
+        { "id":51, "name": "bowl" },
+        { "id":52, "name": "banana" },
+        { "id":53, "name": "apple" },
+        { "id":54, "name": "sandwich" },
+        { "id":55, "name": "orange" },
+        { "id":56, "name": "broccoli" },
+        { "id":57, "name": "carrot" },
+        { "id":58, "name": "hot_dog" },
+        { "id":59, "name": "pizza" },
+        { "id":60, "name": "donut" },
+        { "id":61, "name": "cake" },
+        { "id":62, "name": "chair" },
+        { "id":63, "name": "couch" },
+        { "id":64, "name": "potted_plant" },
+        { "id":65, "name": "bed" },
+        { "id":67, "name": "dining_table" },
+        { "id":70, "name": "toilet" },
+        { "id":72, "name": "tv" },
+        { "id":73, "name": "laptop" },
+        { "id":74, "name": "mouse" },
+        { "id":75, "name": "remote" },
+        { "id":76, "name": "keyboard" },
+        { "id":77, "name": "cell_phone" },
+        { "id":78, "name": "microwave" },
+        { "id":79, "name": "oven" },
+        { "id":80, "name": "toaster" },
+        { "id":81, "name": "sink" },
+        { "id":83, "name": "refrigerator" },
+        { "id":84, "name": "book" },
+        { "id":85, "name": "clock" },
+        { "id":86, "name": "vase" },
+        { "id":87, "name": "scissors" },
+        { "id":88, "name": "teddy_bear" },
+        { "id":89, "name": "hair_drier" },
+        { "id":90, "name": "toothbrush" }
+      ]
+
+spec:
+  description: RetinaNet R101 from Detectron2 optimized for GPU
+  runtime: 'python:3.8'
+  handler: main:handler
+  eventTimeout: 30s
+
+  build:
+    image: cvat/pth.facebookresearch.detectron2.retinanet_r101
+    baseImage: ubuntu:20.04
+
+    directives:
+      preCopy:
+        - kind: ENV
+          value: DEBIAN_FRONTEND=noninteractive
+        - kind: RUN
+          value: apt-get update && apt-get -y install curl git python3 python3-pip
+        - kind: WORKDIR
+          value: /opt/nuclio
+        - kind: RUN
+          value: pip3 install torch==1.8.1+cu111 torchvision==0.9.1+cu111 torchaudio==0.8.1 -f https://download.pytorch.org/whl/torch_stable.html
+        - kind: RUN
+          value: pip3 install 'git+https://github.com/facebookresearch/detectron2@v0.4'
+        - kind: RUN
+          value: curl -O https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/retinanet_R_101_FPN_3x/190397697/model_final_971ab9.pkl
+        - kind: RUN
+          value: ln -s /usr/bin/pip3 /usr/local/bin/pip
+
+  triggers:
+    myHttpTrigger:
+      maxWorkers: 1
+      kind: 'http'
+      workerAvailabilityTimeoutMilliseconds: 10000
+      attributes:
+        maxRequestBodySize: 33554432 # 32MB
+
+  resources:
+    limits:
+      nvidia.com/gpu: 1
+
+  platform:
+    attributes:
+      restartPolicy:
+        name: always
+        maximumRetryCount: 3
+      mountMode: volume