openvinotoolkit · IRDonch · Mar 15, 2021 · Mar 4, 2021 · Mar 4, 2021 · Mar 5, 2021
diff --git a/data/dataset_classes/aclnet.txt → data/dataset_classes/aclnet_53cl.txt b/data/dataset_classes/aclnet.txt → data/dataset_classes/aclnet_53cl.txt
diff --git a/data/dataset_classes/cityscapes19.txt → data/dataset_classes/cityscapes_19cl.txt b/data/dataset_classes/cityscapes19.txt → data/dataset_classes/cityscapes_19cl.txt
diff --git a/data/dataset_classes/voc_20cl.txt b/data/dataset_classes/voc_20cl.txt
@@ -0,0 +1,20 @@
+aeroplane
+bicycle
+bird
+boat
+bottle
+bus
+car
+cat
+chair
+cow
+diningtable
+dog
+horse
+motorbike
+person
+pottedplant
+sheep
+sofa
+train
+tvmonitor
diff --git a/data/dataset_classes/voc.txt → data/dataset_classes/voc_20cl_bkgr.txt b/data/dataset_classes/voc.txt → data/dataset_classes/voc_20cl_bkgr.txt
diff --git a/demos/interactive_face_detection_demo/cpp/README.md b/demos/interactive_face_detection_demo/cpp/README.md
@@ -94,9 +94,19 @@ Options:
 
 Running the application with an empty list of options yields the usage message given above and an error message.
 
-To run the demo, you can use public or pre-trained models. To download the pre-trained models, use the OpenVINO [Model Downloader](../../../tools/downloader/README.md). The list of models supported by the demo is in [models.lst](./models.lst).
+To run the demo, you can use public or Intel pre-trained models. You can download models and if necessary convert them into Inference Engine format using the OpenVINO™ [Model Downloader and other automation tools](../../../tools/downloader/README.md) as shown in the examples below. The models which are supported by the demo are listed in the [models.lst](./models.lst) file.
 
-> **NOTE**: Before running the demo with a trained model, make sure the model is converted to the Inference Engine format (\*.xml + \*.bin) using the [Model Optimizer tool](https://docs.openvinotoolkit.org/latest/_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide.html).
+An example of using the Model Downloader:
+```
+python3 downloader.py --list models.lst
+```
+
+An example of using the Model Converter:
+```
+python3 converter.py --list models.lst
+```
+
+> **NOTE**: Before running the demo with a trained model, make sure the model is downloaded and converted to the Inference Engine format (\*.xml + \*.bin) using OpenVINO™ [Model Downloader and other automation tools](../../../tools/downloader/README.md).
 
 For example, to do inference on a GPU with the OpenVINO&trade; toolkit pre-trained models, run the following command:
 

diff --git a/demos/interactive_face_detection_demo/cpp_gapi/README.md b/demos/interactive_face_detection_demo/cpp_gapi/README.md
@@ -67,7 +67,17 @@ Options:
 
 Running the application with an empty list of options yields the usage message given above and an error message.
 
-To run the demo, you can use public or pre-trained models. To download the pre-trained models, use the OpenVINO [Model Downloader](../../../tools/downloader/README.md). The list of models supported by the demo is in [models.lst](models.lst).
+To run the demo, you can use public or Intel pre-trained models. You can download models and if necessary convert them into Inference Engine format using the OpenVINO™ [Model Downloader and other automation tools](../../../tools/downloader/README.md) as shown in the examples below. The models which are supported by the demo are listed in the [models.lst](./models.lst) file.
+
+An example of using the Model Downloader:
+```
+python3 downloader.py --list models.lst
+```
+
+An example of using the Model Converter:
+```
+python3 converter.py --list models.lst
+```
 
 > **NOTE**: Before running the demo with a trained model, make sure the model is converted to the Inference Engine format (\*.xml + \*.bin) using the [Model Optimizer tool](https://docs.openvinotoolkit.org/latest/_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide.html).
 

diff --git a/models/intel/icnet-camvid-ava-0001/description/icnet-camvid-ava-0001.md b/models/intel/icnet-camvid-ava-0001/description/icnet-camvid-ava-0001.md
@@ -6,7 +6,19 @@ A trained model of ICNet for fast semantic segmentation, trained on the CamVid\*
 
 The model input is a blob that consists of a single image of `1x3x720x960` in the BGR order. The pixel values are integers in the [0, 255] range.
 
-The model output for `icnet-camvid-ava-0001` is the predicted class index of each input pixel belonging to one of the 12 classes of the CamVid dataset.
+The model output for `icnet-camvid-ava-0001` is the predicted class index of each input pixel belonging to one of the 12 classes of the CamVid dataset:
+- Sky
+- Building
+- Pole
+- Road
+- Pavement
+- Tree
+- SignSymbol
+- Fence
+- Vehicle
+- Pedestrian
+- Bike
+- Unlabeled
 
 ## Specification
 

diff --git a/.../icnet-camvid-ava-sparse-30-0001/description/icnet-camvid-ava-sparse-30-0001.md b/.../icnet-camvid-ava-sparse-30-0001/description/icnet-camvid-ava-sparse-30-0001.md
@@ -6,7 +6,19 @@ A trained model of ICNet for fast semantic segmentation, trained on the CamVid\*
 
 The model input is a blob that consists of a single image of `1x3x720x960` in the BGR order. The pixel values are integers in the [0, 255] range.
 
-The model output for `icnet-camvid-ava-sparse-30-0001` is the predicted class index of each input pixel belonging to one of the 12 classes of the CamVid dataset.
+The model output for `icnet-camvid-ava-sparse-30-0001` is the predicted class index of each input pixel belonging to one of the 12 classes of the CamVid dataset:
+- Sky
+- Building
+- Pole
+- Road
+- Pavement
+- Tree
+- SignSymbol
+- Fence
+- Vehicle
+- Pedestrian
+- Bike
+- Unlabeled
 
 ## Specification
 

diff --git a/.../icnet-camvid-ava-sparse-60-0001/description/icnet-camvid-ava-sparse-60-0001.md b/.../icnet-camvid-ava-sparse-60-0001/description/icnet-camvid-ava-sparse-60-0001.md
@@ -6,7 +6,19 @@ A trained model of ICNet for fast semantic segmentation, trained on the CamVid\*
 
 The model input is a blob that consists of a single image of `1x3x720x960` in the BGR order. The pixel values are integers in the [0, 255] range.
 
-The model output for `icnet-camvid-ava-sparse-60-0001` is the predicted class index of each input pixel belonging to one of the 12 classes of the CamVid dataset.
+The model output for `icnet-camvid-ava-sparse-60-0001` is the predicted class index of each input pixel belonging to one of the 12 classes of the CamVid dataset:
+- Sky
+- Building
+- Pole
+- Road
+- Pavement
+- Tree
+- SignSymbol
+- Fence
+- Vehicle
+- Pedestrian
+- Bike
+- Unlabeled
 
 ## Specification
 

diff --git a/models/intel/unet-camvid-onnx-0001/description/unet-camvid-onnx-0001.md b/models/intel/unet-camvid-onnx-0001/description/unet-camvid-onnx-0001.md
@@ -6,7 +6,19 @@ This is a U-Net model that is designed to perform semantic segmentation. The mod
 
 The model input is a blob that consists of a single image of `1x3x368x480` in the BGR order. The pixel values are integers in the [0, 255] range.
 
-The model output for `unet-camvid-onnx-0001` is the per-pixel probabilities of each input pixel belonging to one of the 12 classes of the CamVid dataset.
+The model output for `unet-camvid-onnx-0001` is the per-pixel probabilities of each input pixel belonging to one of the 12 classes of the CamVid dataset:
+- Sky
+- Building
+- Pole
+- Road
+- Pavement
+- Tree
+- SignSymbol
+- Fence
+- Vehicle
+- Pedestrian
+- Bike
+- Unlabeled
 
 ## Specification
 

diff --git a/models/intel/yolo-v2-ava-0001/description/yolo-v2-ava-0001.md b/models/intel/yolo-v2-ava-0001/description/yolo-v2-ava-0001.md
@@ -33,7 +33,7 @@ where each number corresponds to [`num_anchors`, `cls_reg_obj_params`, `y_loc`,
 - `cls_reg_obj_params`: parameters for classification and regression. The values are made up of the following:
   * Regression parameters (4)
   * Objectness score (1)
-  * Class score (20)
+  * Class score (20), mapping to class names provided by `<omz_dir>/data/dataset_classes/voc_20cl.txt` file.
 - `y_loc` and `x_loc`: spatial location of each grid
 
 ## Legal Information

diff --git a/models/intel/yolo-v2-ava-sparse-35-0001/description/yolo-v2-ava-sparse-35-0001.md b/models/intel/yolo-v2-ava-sparse-35-0001/description/yolo-v2-ava-sparse-35-0001.md
@@ -34,7 +34,7 @@ where each number corresponds to [`num_anchors`, `cls_reg_obj_params`, `y_loc`,
 - `cls_reg_obj_params`: parameters for classification and regression. The values are made up of the following:
   * Regression parameters (4)
   * Objectness score (1)
-  * Class score (20)
+  * Class score (20), mapping to class names provided by `<omz_dir>/data/dataset_classes/voc_20cl.txt` file.
 - `y_loc` and `x_loc`: spatial location of each grid
 
 ## Legal Information

diff --git a/models/intel/yolo-v2-ava-sparse-70-0001/description/yolo-v2-ava-sparse-70-0001.md b/models/intel/yolo-v2-ava-sparse-70-0001/description/yolo-v2-ava-sparse-70-0001.md
@@ -34,7 +34,7 @@ where each number corresponds to [`num_anchors`, `cls_reg_obj_params`, `y_loc`,
 - `cls_reg_obj_params`: parameters for classification and regression. The values are made up of the following:
   * Regression parameters (4)
   * Objectness score (1)
-  * Class score (20)
+  * Class score (20), mapping to class names provided by `<omz_dir>/data/dataset_classes/voc_20cl.txt` file.
 - `y_loc` and `x_loc`: spatial location of each grid
 
 ## Legal Information

diff --git a/models/intel/yolo-v2-tiny-ava-0001/description/yolo-v2-tiny-ava-0001.md b/models/intel/yolo-v2-tiny-ava-0001/description/yolo-v2-tiny-ava-0001.md
@@ -33,7 +33,7 @@ where each number corresponds to [`num_anchors`, `cls_reg_obj_params`, `y_loc`,
 - `cls_reg_obj_params`: parameters for classification and regression. The values are made up of the following:
   * Regression parameters (4)
   * Objectness score (1)
-  * Class score (20)
+  * Class score (20), mapping to class names provided by `<omz_dir>/data/dataset_classes/voc_20cl.txt` file.
 - `y_loc` and `x_loc`: spatial location of each grid
 
 ## Legal Information

diff --git a/.../yolo-v2-tiny-ava-sparse-30-0001/description/yolo-v2-tiny-ava-sparse-30-0001.md b/.../yolo-v2-tiny-ava-sparse-30-0001/description/yolo-v2-tiny-ava-sparse-30-0001.md
@@ -34,7 +34,7 @@ where each number corresponds to [`num_anchors`, `cls_reg_obj_params`, `y_loc`,
 - `cls_reg_obj_params`: parameters for classification and regression. The values are made up of the following:
   * Regression parameters (4)
   * Objectness score (1)
-  * Class score (20)
+  * Class score (20), mapping to class names provided by `<omz_dir>/data/dataset_classes/voc_20cl.txt` file.
 - `y_loc` and `x_loc`: spatial location of each grid
 
 ## Legal Information

diff --git a/.../yolo-v2-tiny-ava-sparse-60-0001/description/yolo-v2-tiny-ava-sparse-60-0001.md b/.../yolo-v2-tiny-ava-sparse-60-0001/description/yolo-v2-tiny-ava-sparse-60-0001.md
@@ -34,7 +34,7 @@ where each number corresponds to [`num_anchors`, `cls_reg_obj_params`, `y_loc`,
 - `cls_reg_obj_params`: parameters for classification and regression. The values are made up of the following:
   * Regression parameters (4)
   * Objectness score (1)
-  * Class score (20)
+  * Class score (20), mapping to class names provided by `<omz_dir>/data/dataset_classes/voc_20cl.txt` file.
 - `y_loc` and `x_loc`: spatial location of each grid
 
 ## Legal Information

diff --git a/models/public/Sphereface/Sphereface.md b/models/public/Sphereface/Sphereface.md
@@ -64,6 +64,20 @@ Face embeddings, name - `fc5`,  shape - `1,512`, output data format  - `B,C`, wh
 
 The net outputs on different images are comparable in cosine distance.
 
+## Download a Model and Convert it into OpenVINO™ Inference Engine Format
+
+You can download models and if necessary convert them into Inference Engine format using the OpenVINO™ [Model Downloader and other automation tools](../../../tools/downloader/README.md) as shown in the examples below.
+
+An example of using the Model Downloader:
+```
+python3 downloader.py --name <model_name>
+```
+
+An example of using the Model Converter:
+```
+python3 converter.py --name <model_name>
+```
+
 ## Legal Information
 
 The original model is distributed under the following

diff --git a/models/public/aclnet-int8/aclnet-int8.md b/models/public/aclnet-int8/aclnet-int8.md
@@ -50,18 +50,32 @@ Audio, name - `result.1`, shape - `1,1,1,L`, format is `N,C,1,L` where:
 
 ### Original Model
 
-Sound classifier (see labels file, `<omz_dir>/data/dataset_classes/aclnet.txt`), name - `486`, shape - `1,53`, output data format is `N,C` where:
+Sound classifier (see labels file, `<omz_dir>/data/dataset_classes/aclnet_53cl.txt`), name - `486`, shape - `1,53`, output data format is `N,C` where:
 
 - `N` - batch size
 - `C` - Predicted softmax scores for each class in [0, 1] range
 
 ### Converted Model
 
-Sound classifier (see labels file, `<omz_dir>/data/dataset_classes/aclnet.txt`), name - `486`, shape - `1,53`, output data format is `N,C` where:
+Sound classifier (see labels file, `<omz_dir>/data/dataset_classes/aclnet_53cl.txt`), name - `486`, shape - `1,53`, output data format is `N,C` where:
 
 - `N` - batch size
 - `C` - Predicted softmax scores for each class in [0, 1] range
 
+## Download a Model and Convert it into OpenVINO™ Inference Engine Format
+
+You can download models and if necessary convert them into Inference Engine format using the OpenVINO™ [Model Downloader and other automation tools](../../../tools/downloader/README.md) as shown in the examples below.
+
+An example of using the Model Downloader:
+```
+python3 downloader.py --name <model_name>
+```
+
+An example of using the Model Converter:
+```
+python3 converter.py --name <model_name>
+```
+
 ## Legal Information
 
 The original model is distributed under [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0.html).
diff --git a/models/public/aclnet/aclnet.md b/models/public/aclnet/aclnet.md
@@ -49,18 +49,32 @@ Audio, name - `input`, shape - `1,1,1,L`, format is `N,C,1,L` where:
 
 ### Original Model
 
-Sound classifier (see labels file, `<omz_dir>/data/dataset_classes/aclnet.txt`), name - `203`, shape - `1,53`, output data format is `N,C` where:
+Sound classifier (see labels file, `<omz_dir>/data/dataset_classes/aclnet_53cl.txt`), name - `203`, shape - `1,53`, output data format is `N,C` where:
 
 - `N` - batch size
 - `C` - Predicted softmax scores for each class in [0, 1] range
 
 ### Converted Model
 
-Sound classifier (see labels file, `<omz_dir>/data/dataset_classes/aclnet.txt`), name - `203`, shape - `1,53`, output data format is `N,C` where:
+Sound classifier (see labels file, `<omz_dir>/data/dataset_classes/aclnet_53cl.txt`), name - `203`, shape - `1,53`, output data format is `N,C` where:
 
 - `N` - batch size
 - `C` - Predicted softmax scores for each class in [0, 1] range
 
+## Download a Model and Convert it into OpenVINO™ Inference Engine Format
+
+You can download models and if necessary convert them into Inference Engine format using the OpenVINO™ [Model Downloader and other automation tools](../../../tools/downloader/README.md) as shown in the examples below.
+
+An example of using the Model Downloader:
+```
+python3 downloader.py --name <model_name>
+```
+
+An example of using the Model Converter:
+```
+python3 converter.py --name <model_name>
+```
+
 ## Legal Information
 
 The original model is distributed under [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0.html).
diff --git a/models/public/alexnet/alexnet.md b/models/public/alexnet/alexnet.md
@@ -70,6 +70,20 @@ Object classifier according to ImageNet classes, name - `prob`, shape - `1,1000`
 - `C` - Predicted probabilities for each class in  [0, 1] range
 
 
+## Download a Model and Convert it into OpenVINO™ Inference Engine Format
+
+You can download models and if necessary convert them into Inference Engine format using the OpenVINO™ [Model Downloader and other automation tools](../../../tools/downloader/README.md) as shown in the examples below.
+
+An example of using the Model Downloader:
+```
+python3 downloader.py --name <model_name>
+```
+
+An example of using the Model Converter:
+```
+python3 converter.py --name <model_name>
+```
+
 ## Legal Information
 
 The original model is distributed under the following

diff --git a/models/public/anti-spoof-mn3/anti-spoof-mn3.md b/models/public/anti-spoof-mn3/anti-spoof-mn3.md
@@ -10,9 +10,9 @@ For details see original [repository](https://github.com/kirillProkofiev/light-w
 | Metric                          | Value                                     |
 |---------------------------------|-------------------------------------------|
 | Type                            | Classification                            |
-| GFlops                          | 0.15                                    |
-| MParams                         | 3.02                                    |
-| Source framework                | PyTorch\*                              |
+| GFlops                          | 0.15                                      |
+| MParams                         | 3.02                                      |
+| Source framework                | PyTorch\*                                 |
 
 ## Accuracy
 
@@ -63,6 +63,20 @@ Probabilities for two classes (0 class is a real person, 1 - is a spoof image).
     - B - batch size
     - C - vector of probabilities.
 
+## Download a Model and Convert it into OpenVINO™ Inference Engine Format
+
+You can download models and if necessary convert them into Inference Engine format using the OpenVINO™ [Model Downloader and other automation tools](../../../tools/downloader/README.md) as shown in the examples below.
+
+An example of using the Model Downloader:
+```
+python3 downloader.py --name <model_name>
+```
+
+An example of using the Model Converter:
+```
+python3 converter.py --name <model_name>
+```
+
 ## Legal Information
 
 The original model is distributed under the

diff --git a/models/public/brain-tumor-segmentation-0001/brain-tumor-segmentation-0001.md b/models/public/brain-tumor-segmentation-0001/brain-tumor-segmentation-0001.md
@@ -90,6 +90,20 @@ Probabilities of the given voxel to be in the corresponding class, name - `softm
 
 With the following channels: `background`, `necrotic core`, `edema` and `enhancing tumor`.
 
+## Download a Model and Convert it into OpenVINO™ Inference Engine Format
+
+You can download models and if necessary convert them into Inference Engine format using the OpenVINO™ [Model Downloader and other automation tools](../../../tools/downloader/README.md) as shown in the examples below.
+
+An example of using the Model Downloader:
+```
+python3 downloader.py --name <model_name>
+```
+
+An example of using the Model Converter:
+```
+python3 converter.py --name <model_name>
+```
+
 ## Legal Information
 
 The original model is distributed under the

diff --git a/models/public/brain-tumor-segmentation-0002/brain-tumor-segmentation-0002.md b/models/public/brain-tumor-segmentation-0002/brain-tumor-segmentation-0002.md
@@ -100,6 +100,20 @@ Probabilities of the given voxel to be in the corresponding class, name - `304`,
 
 The channels are ordered as `whole tumor`, `tumor core`, and `enhancing tumor`.
 
+## Download a Model and Convert it into OpenVINOâ„¢ Inference Engine Format
+
+You can download models and if necessary convert them into Inference Engine format using the OpenVINOâ„¢ [Model Downloader and other automation tools](../../../tools/downloader/README.md) as shown in the examples below.
+
+An example of using the Model Downloader:
+```
+python3 downloader.py --name <model_name>
+```
+
+An example of using the Model Converter:
+```
+python3 converter.py --name <model_name>
+```
+
 ## Legal Information
 
 The original model is distributed under the