Fixes in documentation (openvinotoolkit#920)

* Fixes in documentation

Change TF version in Ensemble example since 1.15 is no longer
available in pip3.

* Update docs/developer_guide.md

docs/demultiplexing.md

@@ -1,7 +1,7 @@
 # Demultiplexing in Directed Acyclic Graph Scheduler
 
 ## Pipeline branching
-Directed Acyclic Graph Scheduler allows creating pipelines with optional parameter `demultiply_count: `N` which adds ability to any node to slice outputs into `N` separate sub outputs and branch pipeline execution into `N` sub pipelines. Following nodes will be executed by event loop `N` times independently from each other and results will be gathered and packed into one output just before sending a response. Additionally `gather_from_node: <node_name>` parameter can be used to specify gathering at any point in Directed Acyclic Graph.`demultiply_count` node parameter value has to match first dimension of all node outputs. All node outputs have to have at least 2 dimensions.
+Directed Acyclic Graph Scheduler allows creating pipelines with optional parameter `demultiply_count: N` which adds ability to any node to slice outputs into `N` separate sub outputs and branch pipeline execution into `N` sub pipelines. Following nodes will be executed by event loop `N` times independently from each other and results will be gathered and packed into one output just before sending a response. Additionally `gather_from_node: <node_name>` parameter can be used to specify gathering at any point in Directed Acyclic Graph.`demultiply_count` node parameter value has to match first dimension of all node outputs. All node outputs have to have at least 2 dimensions.
 
 ## Basic demultiplexer example and metadata explanation
 This example contains 2 consecutive models:
@@ -12,7 +12,7 @@ This example has no `gather_from_node` parameter specified in config.json config
 
 ![diagram](demultiplexer.svg)
 
-Example configuration file with one demultiplexer:
+Example configuration file with one demultiplexer (remove everything after arrows in lines containing those):
 ```
 {
     "model_config_list": [

docs/developer_guide.md

@@ -27,8 +27,10 @@ In-case of problems, see <a href="#debug">Debugging</a>.
 ### Step 1: Compile source code
 1. Build the development `openvino/model_server-build` Docker* image
    ```bash
-   make docker_build 
+   make docker_build
+   ```
    or
+   ```
    make docker_build DLDT_PACKAGE_URL=<URL>
    ```
    > **Note**: URL to OpenVINO Toolkit package can be received after registration on [OpenVINO&trade; Toolkit website](https://software.intel.com/en-us/openvino-toolkit/choose-download)
@@ -63,8 +65,8 @@ In-case of problems, see <a href="#debug">Debugging</a>.
 	* With a Docker cache :
 
 	```bash
-	OVMS_CPP_DOCKER_IMAGE=<unique_image_name> make docker_build
-    OVMS_CPP_DOCKER_IMAGE=<unique_image_name> make test_functional
+	OVMS_CPP_DOCKER_IMAGE=<replace_with_unique_image_name> make docker_build
+    OVMS_CPP_DOCKER_IMAGE=<replace_with_unique_image_name> make test_functional
     OVMS_CPP_CONTAINTER_PORT=<unique_network_port> make test_perf
 	```
 
@@ -265,10 +267,10 @@ Two debugging options are available. Click on the required option :
 	```
 	docker run -it --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v ${PWD}:/ovms -p 9178:9178 --entrypoint bash openvino/model_server-build:latest
 	```
-3.	Recompile the OpenVINO Model Server with debug symbols using command. 	
+3.	Assuming resnet50 model is prepared for OVMS in /models catalog recompile the OpenVINO Model Server with debug symbols using command:
     ```
 	[root@72dc3b874772 ovms]# bazel build //src:ovms -c dbg
-    [root@72dc3b874772 ovms]# gdb --args ./bazel-bin/src/ovms --model_name resnet --model_path /model
+    [root@72dc3b874772 ovms]# gdb --args ./bazel-bin/src/ovms --model_name resnet --model_path /models
 	```
     > **NOTE**: For best results, use the makefile parameter `BAZEL_BUILD_TYPE=dbg` to build the dependencies in debug mode as shown above
 

docs/east_ocr.md

@@ -12,7 +12,7 @@ Below is depicted the graph implementing a complete OCR pipelines.
 
 ![OCR graph](east_ocr.png)
 
-It includes the following Nodes:
+It includes the following nodes:
 - Model east-resnet50 - inference execution which takes the user image as input. It returns two outputs including information about all detected boxes, their location and scores.
 - Custom node east_ocr - it includes C++ implementation of east-resnet50 model results processing. It analyses the detected boxes coordinates, filters the results
 based on the configurable score level threshold and and applies non-max suppression algorithm to remove overlaping boxes. Finally the custom node east-ocr crops all detected boxes
@@ -35,7 +35,7 @@ Clone github repository:
 git clone https://github.com/argman/EAST 
 cd EAST 
 ```
-Download and unzip the file east_icdar2015_resnet_v1_50_rbox.zip to EAST folder with the github repository.
+Download and unzip the file east_icdar2015_resnet_v1_50_rbox.zip as instructed in readme.md file to EAST folder with the github repository.
 ```bash
 unzip ./east_icdar2015_resnet_v1_50_rbox.zip
 ```

docs/ensemble_scheduler.md

@@ -25,7 +25,7 @@ This document presents ensemble models as an example of [DAG Scheduler](dag_sche
 ```
 ~$ virtualenv -p python3 .tf_env
 ~$ source .tf_env/bin/activate
-~$ pip3 install tensorflow==1.15
+~$ pip3 install tensorflow==2.3.1
 ```
 3. Prepare argmax model with `(1, 1001)` input shapes to match output of googlenet and resnet output shapes. Generated model will sum inputs and calculate the index with the highest value. The model output will indicate the most likely predicted class from the ImageNet* dataset. <a name="point-3"></a>
 ```
@@ -39,56 +39,53 @@ This document presents ensemble models as an example of [DAG Scheduler](dag_sche
 ~$ docker run -u $(id -u):$(id -g) -v ~/models:/models:rw openvino/ubuntu18_dev:latest deployment_tools/open_model_zoo/tools/downloader/converter.py --name resnet-50-tf --download_dir /models --output_dir /models --precisions FP32
 
 ~$ docker run -u $(id -u):$(id -g) -v ~/models:/models:rw openvino/ubuntu18_dev:latest deployment_tools/model_optimizer/mo_tf.py --input input1,input2 --input_shape [1,1001],[1,1001] --saved_model_dir /models/public/argmax/saved_model/ --output_dir /models/public/argmax/1
-~$ mv ~/models/public/googlenet-v2-tf/FP32 ~/models/public/googlenet-v2-tf/1 && mv ~/models/public/resnet-50-tf/FP32 ~/models/public/resnet-50-tf/1
+~$ mkdir -p ovms_models/googlenet-v2-tf/1
+~$ mkdir -p ovms_models/resnet-50-tf/1
+~$ mkdir -p ovms_models/argmax/1
+~$ cp ~/models/public/googlenet-v2-tf/FP32/googlenet-v2-tf.{bin,xml} ~/ovms_models/googlenet-v2-tf/1/
+~$ cp ~/models/public/resnet-50-tf/FP32/resnet-50-tf.{bin,xml} ~/ovms_models/resnet-50-tf/1/
+~$ cp ~/models/public/argmax/1/saved_model.{bin,xml} ~/ovms_models/argmax/1/
 
 ~$ tree models/public
-models/public
+ovms_models
 ├── argmax
 │   ├── 1
 │   │   ├── saved_model.bin
-│   │   ├── saved_model.mapping
 │   │   └── saved_model.xml
-│   └── saved_model
-│       ├── saved_model.pb
-│       └── variables
 ├── googlenet-v2-tf
 │   ├── 1
 │   │   ├── googlenet-v2-tf.bin
-│   │   ├── googlenet-v2-tf.mapping
 │   │   └── googlenet-v2-tf.xml
-│   └── inception_v2.frozen.pb
 └── resnet-50-tf
     ├── 1
     │   ├── resnet-50-tf.bin
-    │   ├── resnet-50-tf.mapping
     │   └── resnet-50-tf.xml
-    └── resnet_v1-50.pb
 ```
 
 ### Step 2: Define required models and pipeline <a name="define-models"></a>
 Pipelines need to be defined in configuration file to use them. The same configuration file is used to define served models and served pipelines.
 
 Use the config.json as given below
 ```
-~$ cat models/config.json 
+~$ cat ovms_models/config.json
 {
     "model_config_list": [
         {
             "config": {
                 "name": "googlenet",
-                "base_path": "/models/public/googlenet-v2-tf"
+                "base_path": "/models/googlenet-v2-tf"
             }
         },
         {
             "config": {
                 "name": "resnet",
-                "base_path": "/models/public/resnet-50-tf"
+                "base_path": "/models/resnet-50-tf"
             }
         },
         {
             "config": {
                 "name": "argmax",
-                "base_path": "/models/public/argmax"
+                "base_path": "/models/argmax"
             }
         }
     ],
@@ -155,7 +152,7 @@ In `model_config_list` section, three models are defined as usual. We can refer
 
 1. Run command to start model server
 ```
-~$ docker run --rm -v ~/models/:/models:ro -p 9100:9100 -p 8100:8100 openvino/model_server:latest --config_path /models/config.json --port 9100 --rest_port 8100
+~$ docker run --rm -v ~/ovms_models/:/models:ro -p 9100:9100 -p 8100:8100 openvino/model_server:latest --config_path /models/config.json --port 9100 --rest_port 8100
 ```
 
 ### Step 4: Requesting the service

docs/model_version_policy.md

@@ -15,9 +15,9 @@ Accepted values :
 
 Examples:
 
-{"latest": { "num_versions":2 }} # server will serve only 2 latest versions of model
+{"latest": { "num_versions": 2 }} # server will serve only 2 latest versions of model
 
-{"specific": { "versions":[1, 3] }} # server will serve only 1 and 3 versions of given model
+{"specific": { "versions": [1, 3] }} # server will serve only 1 and 3 versions of given model
 
 {"all": {}} # server will serve all available versions of given model
 

example_client/README.md

@@ -397,9 +397,9 @@ usage: get_serving_meta.py [-h] [--grpc_address GRPC_ADDRESS]
 | Argument      | Description |
 | :---        |    :----   |
 | -h, --help | Show help message and exit|
-| --rest_url REST_URL | Specify url to REST API service. Default:http://localhost|
+| --rest_url REST_URL | Specify url to REST API service. Default: http://localhost|
 | --rest_port REST_PORT | Specify port to REST API service. Default: 9000|
-| --model_name MODEL_NAME| Model name to query, must be same as is in service. Default : resnet|
+| --model_name MODEL_NAME| Model name to query, must be same as is in service. Default: resnet|
 | --model_version MODEL_VERSION | Model version to query - must be numerical. List all version if omitted|
 
 - Usage Example

tests/models/argmax_sum.py

@@ -14,7 +14,7 @@
 # limitations under the License.
 #
 
-import tensorflow as tf
+import tensorflow.compat.v1 as tf
 from tensorflow.python.saved_model import signature_constants
 from tensorflow.python.saved_model import tag_constants
 import numpy as np