Merge pull request #4 from openvinotoolkit/master

Rebase

README.md

@@ -1,5 +1,5 @@
 # [OpenVINO™ Toolkit](https://01.org/openvinotoolkit) - Deep Learning Deployment Toolkit repository
-[![Stable release](https://img.shields.io/badge/version-2020.2-green.svg)](https://github.com/openvinotoolkit/openvino/releases/tag/2020.2)
+[![Stable release](https://img.shields.io/badge/version-2020.3-green.svg)](https://github.com/openvinotoolkit/openvino/releases/tag/2020.3.0)
 [![Apache License Version 2.0](https://img.shields.io/badge/license-Apache_2.0-green.svg)](LICENSE)
 
 This toolkit allows developers to deploy pre-trained deep learning models 

build-instruction.md

@@ -28,7 +28,6 @@
 - [Add Inference Engine to Your Project](#add-inference-engine-to-your-project)
 - [(Optional) Additional Installation Steps for the Intel® Movidius™ Neural Compute Stick and Neural Compute Stick 2](#optional-additional-installation-steps-for-the-intel-movidius-neural-compute-stick-and-neural-compute-stick-2)
   - [For Linux, Raspbian Stretch* OS](#for-linux-raspbian-stretch-os)
-  - [For Windows](#for-windows-1)
 - [Next Steps](#next-steps)
 - [Additional Resources](#additional-resources)
 
@@ -60,12 +59,12 @@ The software was validated on:
 - [CMake]\* 3.11 or higher
 - GCC\* 4.8 or higher to build the Inference Engine
 - Python 2.7 or higher for Inference Engine Python API wrapper
-- (Optional) [Install Intel® Graphics Compute Runtime for OpenCL™ Driver package 19.41.14441].
+- (Optional) [Install Intel® Graphics Compute Runtime for OpenCL™ Driver package 20.13.16352].
 
 ### Build Steps
 1. Clone submodules:
     ```sh
-    cd dldt
+    cd openvino
     git submodule update --init --recursive
     ```
 2. Install build dependencies using the `install_dependencies.sh` script in the
@@ -78,7 +77,7 @@ The software was validated on:
    ```
 3. By default, the build enables the Inference Engine GPU plugin to infer models
    on your Intel® Processor Graphics. This requires you to
-   [Install Intel® Graphics Compute Runtime for OpenCL™ Driver package 19.41.14441]
+   [Install Intel® Graphics Compute Runtime for OpenCL™ Driver package 20.13.16352]
    before running the build. If you don't want to use the GPU plugin, use the
    `-DENABLE_CLDNN=OFF` CMake build option and skip the installation of the
    Intel® Graphics Compute Runtime for OpenCL™ Driver.
@@ -172,10 +171,10 @@ Native compilation of the Inference Engine is the most straightforward solution.
   sudo apt-get install -y git cmake libusb-1.0-0-dev
   ```
 
-2. Go to the cloned `dldt` repository:
+2. Go to the cloned `openvino` repository:
 
   ```bash
-  cd dldt
+  cd openvino
   ```
 
 3. Initialize submodules:
@@ -262,15 +261,15 @@ with the following content:
 5. Run Docker\* container with mounted source code folder from host:
 
   ```bash
-  docker run -it -v /absolute/path/to/dldt:/dldt ie_cross_armhf /bin/bash
+  docker run -it -v /absolute/path/to/openvino:/openvino ie_cross_armhf /bin/bash
   ```
 
 6. While in the container:
 
-    1. Go to the cloned `dldt` repository:
+    1. Go to the cloned `openvino` repository:
 
       ```bash
-      cd dldt
+      cd openvino
       ```
 
     2. Create a build folder:
@@ -291,8 +290,8 @@ with the following content:
       ```
 
 7. Press **Ctrl+D** to exit from Docker. You can find the resulting binaries
-   in the `dldt/bin/armv7l/` directory and the OpenCV*
-   installation in the `dldt/inference-engine/temp`.
+   in the `openvino/bin/armv7l/` directory and the OpenCV*
+   installation in the `openvino/inference-engine/temp`.
 
 >**NOTE**: Native applications that link to cross-compiled Inference Engine
 library require an extra compilation flag `-march=armv7-a`.
@@ -381,8 +380,8 @@ cmake -G "Visual Studio 15 2017 Win64" -T "Intel C++ Compiler 18.0" ^
 
 6. Before running the samples, add paths to the TBB and OpenCV binaries used for
    the build to the `%PATH%` environment variable. By default, TBB binaries are
-   downloaded by the CMake-based script to the `<dldt_repo>/inference-engine/temp/tbb/bin`
-   folder, OpenCV binaries to the `<dldt_repo>/inference-engine/temp/opencv_4.3.0/opencv/bin`
+   downloaded by the CMake-based script to the `<openvino_repo>/inference-engine/temp/tbb/bin`
+   folder, OpenCV binaries to the `<openvino_repo>/inference-engine/temp/opencv_4.3.0/opencv/bin`
    folder.
 
 ### Additional Build Options
@@ -437,7 +436,7 @@ cmake -G "Visual Studio 15 2017 Win64" -T "Intel C++ Compiler 18.0" ^
 call "C:\Program Files (x86)\IntelSWTools\compilers_and_libraries_2018\windows\bin\ipsxe-comp-vars.bat" intel64 vs2017
 set CXX=icl
 set CC=icl
-:: clean TBBROOT value set by ipsxe-comp-vars.bat, required TBB package will be downloaded by dldt cmake script
+:: clean TBBROOT value set by ipsxe-comp-vars.bat, required TBB package will be downloaded by openvino cmake script
 set TBBROOT=
 cmake -G Ninja -Wno-dev -DCMAKE_BUILD_TYPE=Release ..
 cmake --build . --config Release
@@ -461,7 +460,7 @@ The software was validated on:
 
 1. Clone submodules:
     ```sh
-    cd dldt
+    cd openvino
     git submodule update --init --recursive
     ```
 2. Install build dependencies using the `install_dependencies.sh` script in the
@@ -545,7 +544,7 @@ This section describes how to build Inference Engine for Android x86 (64-bit) op
 
 2. Clone submodules
   ```sh
-  cd dldt
+  cd openvino
   git submodule update --init --recursive
   ```
 
@@ -610,7 +609,7 @@ before running the Inference Engine build:
 For CMake projects, set the `InferenceEngine_DIR` environment variable:
 
 ```sh
-export InferenceEngine_DIR=/path/to/dldt/build/
+export InferenceEngine_DIR=/path/to/openvino/build/
 ```
 
 Then you can find Inference Engine by `find_package`:
@@ -660,20 +659,6 @@ sudo ldconfig
 rm 97-myriad-usbboot.rules
 ```
 
-### For Windows
-
-For Intel® Movidius™ Neural Compute Stick and Intel® Neural Compute Stick 2,
-install the Movidius™ VSC driver:
-
-1. Go to the `<DLDT_ROOT_DIR>/inference-engine/thirdparty/movidius/MovidiusDriver`
-   directory, where the `DLDT_ROOT_DIR` is the directory to which the DLDT
-   repository was cloned.
-2. Right click on the `Movidius_VSC_Device.inf` file and choose **Install** from
-   the pop-up menu.
-
-You have installed the driver for your Intel® Movidius™ Neural Compute Stick
-or Intel® Neural Compute Stick 2.
-
 ## Next Steps
 
 Congratulations, you have built the Inference Engine. To get started with the
@@ -706,7 +691,7 @@ This target collects all dependencies, prepares the nGraph package and copies it
 
 [Intel® Distribution of OpenVINO™]:https://software.intel.com/en-us/openvino-toolkit
 [CMake]:https://cmake.org/download/
-[Install Intel® Graphics Compute Runtime for OpenCL™ Driver package 19.41.14441]:https://github.com/intel/compute-runtime/releases/tag/19.41.14441
+[Install Intel® Graphics Compute Runtime for OpenCL™ Driver package 20.13.16352]:https://github.com/intel/compute-runtime/releases/tag/20.13.16352
 [MKL-DNN repository]:https://github.com/intel/mkl-dnn/releases/download/v0.19/mklml_lnx_2019.0.5.20190502.tgz
 [MKL-DNN repository for Windows]:(https://github.com/intel/mkl-dnn/releases/download/v0.19/mklml_win_2019.0.5.20190502.zip)
 [OpenBLAS]:https://sourceforge.net/projects/openblas/files/v0.2.14/OpenBLAS-v0.2.14-Win64-int64.zip/download

get-started-linux.md

@@ -1,7 +1,7 @@
-# Get Started with OpenVINO™ Deep Learning Deployment Toolkit (DLDT) on Linux*
+# Get Started with OpenVINO™ Toolkit on Linux*
 
 This guide provides you with the information that will help you to start using 
-the DLDT on Linux\*. With this guide, you will learn how to:
+the OpenVINO™ Toolkit on Linux\*. With this guide, you will learn how to:
 
 1. [Configure the Model Optimizer](#configure-the-model-optimizer)
 2. [Prepare a model for sample inference](#prepare-a-model-for-sample-inference)
@@ -10,13 +10,13 @@ the DLDT on Linux\*. With this guide, you will learn how to:
 3. [Run the Image Classification Sample Application with the model](#run-the-image-classification-sample-application)
 
 ## Prerequisites
-1. This guide assumes that you have already cloned the `dldt` repo and 
+1. This guide assumes that you have already cloned the `openvino` repo and 
    successfully built the Inference Engine and Samples using the 
    [build instructions](inference-engine/README.md). 
 2. The original structure of the repository directories remains unchanged.
 
-> **NOTE**: Below, the directory to which the `dldt` repository is cloned is 
-referred to as `<DLDT_DIR>`.  
+> **NOTE**: Below, the directory to which the `openvino` repository is cloned is 
+referred to as `<OPENVINO_DIR>`.  
 
 ## Configure the Model Optimizer
 
@@ -53,7 +53,7 @@ If you see error messages, check for any missing dependencies.
 
 1.  Go to the Model Optimizer prerequisites directory:
 ```sh
-cd <DLDT_DIR>/model_optimizer/install_prerequisites
+cd <OPENVINO_DIR>/model_optimizer/install_prerequisites
 ```
 2.  Run the script to configure the Model Optimizer for Caffe,
     TensorFlow, MXNet, Kaldi\*, and ONNX:
@@ -68,7 +68,7 @@ Configure individual frameworks separately **ONLY** if you did not select
 
 1.  Go to the Model Optimizer prerequisites directory:
 ```sh
-cd <DLDT_DIR>/model_optimizer/install_prerequisites
+cd <OPENVINO_DIR>/model_optimizer/install_prerequisites
 ```
 2.  Run the script for your model framework. You can run more than one script:
 
@@ -162,20 +162,20 @@ as `<models_dir>` below) with the Model Downloader:
 
    **For CPU (FP32):**
    ```sh  
-   python3 <DLDT_DIR>/model_optimizer/mo.py --input_model <models_dir>/classification/squeezenet/1.1/caffe/squeezenet1.1.caffemodel --data_type FP32 --output_dir <ir_dir>
+   python3 <OPENVINO_DIR>/model_optimizer/mo.py --input_model <models_dir>/classification/squeezenet/1.1/caffe/squeezenet1.1.caffemodel --data_type FP32 --output_dir <ir_dir>
    ```
 
    **For GPU and MYRIAD (FP16):**
    ```sh  
-   python3 <DLDT_DIR>/model_optimizer/mo.py --input_model <models_dir>/classification/squeezenet/1.1/caffe/squeezenet1.1.caffemodel --data_type FP16 --output_dir <ir_dir>
+   python3 <OPENVINO_DIR>/model_optimizer/mo.py --input_model <models_dir>/classification/squeezenet/1.1/caffe/squeezenet1.1.caffemodel --data_type FP16 --output_dir <ir_dir>
    ``` 
    After the Model Optimizer script is completed, the produced IR files (`squeezenet1.1.xml`, `squeezenet1.1.bin`) are in the specified `<ir_dir>` directory.
 
-3. Copy the `squeezenet1.1.labels` file from the `<DLDT_DIR>/inference-engine/samples/sample_data/` 
+3. Copy the `squeezenet1.1.labels` file from the `<OPENVINO_DIR>/scripts/demo/` 
    folder to the model IR directory. This file contains the classes that ImageNet 
    uses so that the inference results show text instead of classification numbers:
    ```sh   
-   cp <DLDT_DIR>/inference-engine/samples/sample_data/squeezenet1.1.labels <ir_dir>
+   cp <OPENVINO_DIR>/scripts/demo/squeezenet1.1.labels <ir_dir>
    ```
 
 Now you are ready to run the Image Classification Sample Application.
@@ -184,28 +184,28 @@ Now you are ready to run the Image Classification Sample Application.
 
 The Inference Engine sample applications are automatically compiled when you 
 built the Inference Engine using the [build instructions](inference-engine/README.md). 
-The binary files are located in the `<DLDT_DIR>/inference-engine/bin/intel64/Release` 
+The binary files are located in the `<OPENVINO_DIR>/inference-engine/bin/intel64/Release` 
 directory.
 
 To run the Image Classification sample application with an input image on the prepared IR: 
 
 1. Go to the samples build directory:
    ```sh
-   cd <DLDT_DIR>/inference-engine/bin/intel64/Release
+   cd <OPENVINO_DIR>/inference-engine/bin/intel64/Release
 
 2. Run the sample executable with specifying the `car.png` file from the 
-   `<DLDT_DIR>/inference-engine/samples/sample_data/` directory as an input 
+   `<OPENVINO_DIR>/scripts/demo/` directory as an input 
    image, the IR of your model and a plugin for a hardware device to perform 
    inference on:
 
    **For CPU:**
    ```sh
-   ./classification_sample -i <DLDT_DIR>/inference-engine/samples/sample_data/car.png -m <ir_dir>/squeezenet1.1.xml -d CPU
+   ./classification_sample -i <OPENVINO_DIR>/scripts/demo/car.png -m <ir_dir>/squeezenet1.1.xml -d CPU
    ```
 
    **For GPU:**
    ```sh
-   ./classification_sample -i <DLDT_DIR>/inference-engine/samples/sample_data/car.png -m <ir_dir>/squeezenet1.1.xml -d GPU
+   ./classification_sample -i <OPENVINO_DIR>/scripts/demo/car.png -m <ir_dir>/squeezenet1.1.xml -d GPU
    ```
 
    **For MYRIAD:** 
@@ -214,14 +214,14 @@ To run the Image Classification sample application with an input image on the pr
    Stick or Intel® Neural Compute Stick 2) with the MYRIAD plugin requires 
    performing [additional hardware configuration steps](inference-engine/README.md#optional-additional-installation-steps-for-the-intel-movidius-neural-compute-stick-and-neural-compute-stick-2).
    ```sh   
-   ./classification_sample -i <DLDT_DIR>/inference-engine/samples/sample_data/car.png -m <ir_dir>/squeezenet1.1.xml -d MYRIAD
+   ./classification_sample -i <OPENVINO_DIR>/scripts/demo/car.png -m <ir_dir>/squeezenet1.1.xml -d MYRIAD
    ```
 
 When the Sample Application completes, you will have the label and confidence for the top-10 categories printed on the screen. Below is a sample output with inference results on CPU:    
 ```sh
 Top 10 results:
 
-Image /home/user/dldt/inference-engine/samples/sample_data/car.png
+Image /home/user/openvino/scripts/demo/car.png
 
 classid probability label
 ------- ----------- -----

inference-engine/src/cldnn_engine/cldnn_program.cpp

@@ -2735,6 +2735,8 @@ void Program::CreatePoolingPrimitive(cldnn::topology& topology, InferenceEngine:
             input_offset,
             CldnnTensorFromIEDims(poolLayer->outData[0]->getTensorDesc().getDims()),
             dt);
+        cldnn::tensor pad_end = { 0, 0, -TensorValue(poolLayer->_pads_end[X_AXIS]), -TensorValue(poolLayer->_pads_end[Y_AXIS]), 0 };
+        poolPrim.pad_end = pad_end;
         topology.add(poolPrim);
         primitiveIDs[poolLayerName] = poolLayerName;
     }

inference-engine/src/mkldnn_plugin/mkldnn_memory_solver.hpp

@@ -10,6 +10,8 @@
 
 #include "ie_api.h"
 
+#include <stdint.h>
+
 #include <vector>
 #include <map>
 

inference-engine/src/mkldnn_plugin/nodes/roifeatureextractor_onnx.cpp

@@ -140,6 +140,7 @@ void ROIAlignForward_cpu_kernel(
     const int pooled_width,
     const int sampling_ratio,
     const T* bottom_rois,
+    const bool aligned,
     T* top_data) {
   int roi_cols = 4;
 
@@ -156,11 +157,12 @@ void ROIAlignForward_cpu_kernel(
       offset_bottom_rois++;
     }
 
+    T offset = aligned ? (T)0.5 : (T)0.0;
     // Do not using rounding; this implementation detail is critical
-    T roi_start_w = offset_bottom_rois[0] * spatial_scale;
-    T roi_start_h = offset_bottom_rois[1] * spatial_scale;
-    T roi_end_w = offset_bottom_rois[2] * spatial_scale;
-    T roi_end_h = offset_bottom_rois[3] * spatial_scale;
+    T roi_start_w = offset_bottom_rois[0] * spatial_scale - offset;
+    T roi_start_h = offset_bottom_rois[1] * spatial_scale - offset;
+    T roi_end_w = offset_bottom_rois[2] * spatial_scale - offset;
+    T roi_end_h = offset_bottom_rois[3] * spatial_scale - offset;
 
     // Force malformed ROIs to be 1x1
     T roi_width = (std::max)(roi_end_w - roi_start_w, (T)1.);
@@ -321,6 +323,7 @@ class ExperimentalDetectronROIFeatureExtractorImpl: public ExtLayerBase {
             output_dim_ = layer->GetParamAsInt("output_size");
             pyramid_scales_ = layer->GetParamAsInts("pyramid_scales");
             sampling_ratio_ = layer->GetParamAsInt("sampling_ratio");
+            aligned_ = layer->GetParamAsBool("aligned");
             pooled_height_ = output_dim_;
             pooled_width_ = output_dim_;
 
@@ -374,6 +377,7 @@ class ExperimentalDetectronROIFeatureExtractorImpl: public ExtLayerBase {
                     pooled_width_,
                     sampling_ratio_,
                     &reordered_rois[4 * level_rois_offset],
+                    aligned_,
                     &output_rois_features_temp[feaxels_per_roi * level_rois_offset]);
             }
         }
@@ -394,6 +398,7 @@ class ExperimentalDetectronROIFeatureExtractorImpl: public ExtLayerBase {
     int pooled_width_ = 0;
     std::vector<int> pyramid_scales_;
     int sampling_ratio_ = 0;
+    bool aligned_ = false;
 };
 
 REG_FACTORY_FOR(ExperimentalDetectronROIFeatureExtractorImpl, ExperimentalDetectronROIFeatureExtractor);

inference-engine/tests/functional/plugin/gpu/shared_tests_instances/behavior/core_threading_tests.cpp

@@ -31,11 +31,12 @@ TEST_P(CoreThreadingTestsWithIterations, smoke_LoadNetwork_RemoteContext) {
         networks.emplace_back(ie.ReadNetwork(model.model_xml_str, model.weights_blob));
     }
 
-    networks.emplace_back(InferenceEngine::CNNNetwork(ngraph::builder::subgraph::make2InputSubtract()));
-    networks.emplace_back(InferenceEngine::CNNNetwork(ngraph::builder::subgraph::makeMultiSingleConv()));
-    networks.emplace_back(InferenceEngine::CNNNetwork(ngraph::builder::subgraph::makeSingleConv()));
-    networks.emplace_back(InferenceEngine::CNNNetwork(ngraph::builder::subgraph::makeSplitConvConcat()));
-    networks.emplace_back(InferenceEngine::CNNNetwork(ngraph::builder::subgraph::makeSplitMultiConvConcat()));
+    // TODO: uncomment after fixing *-31414
+    // networks.emplace_back(InferenceEngine::CNNNetwork(ngraph::builder::subgraph::make2InputSubtract()));
+    // networks.emplace_back(InferenceEngine::CNNNetwork(ngraph::builder::subgraph::makeMultiSingleConv()));
+    // networks.emplace_back(InferenceEngine::CNNNetwork(ngraph::builder::subgraph::makeSingleConv()));
+    // networks.emplace_back(InferenceEngine::CNNNetwork(ngraph::builder::subgraph::makeSplitConvConcat()));
+    // networks.emplace_back(InferenceEngine::CNNNetwork(ngraph::builder::subgraph::makeSplitMultiConvConcat()));
 
     auto ocl_instance = std::make_shared<OpenCL>();
     ie.SetConfig(config, deviceName);