Introducing the Intel® Neural Compute Stick 2 - Intel's Next Generation AI Inference Development Kit

Introducing the Intel® Neural Compute Stick 2 - Intel’s Next Generation AI Inference Development Kit

October 22, 2018

https://software.intel.com/en-us/articles/run-intel-openvino-models-on-intel-neural-compute-stick-2

Intel Movidius
https://www.movidius.com/

Intel® Neural Compute Stick 2
https://software.intel.com/en-us/neural-compute-stick

More hardware acceleration for your neural networks

The Intel® Neural Compute Stick 2 (Intel® NCS 2) is Intel’s newest deep learning inference development kit. Packed in an affordable USB-stick form factor, the Intel® NCS 2 is powered by our latest VPU (vision processing unit) - the Intel® Movidius™ Myriad X, which includes an on-chip neural network accelerator called the Neural Compute Engine. With 16 SHAVE cores and a dedicated hardware neural network accelerator, the NCS 2 offers up to 8x performance improvement+ over the previous generation.

Software tools to accelerate deep learning inference

The Intel Distribution of OpenVINO toolkit is the default software development kit1 to optimize performance, integrate deep learning inference and run deep neural networks (DNN) on Intel® Movidius™ Vision Processing Units (VPU). (For the previous generation, developers used the Intel® Movidius NCS SDK). This toolkit supports a broad set of neural networks and streamlines deployment across not only NCS 2 hardware, but the full range of Intel vision accelerator solutions2. At the time of writing this article, this toolkit supports more than 20 pre-trained models3 covering image classification, object detection and image segmentation.

Develop on one platform, deploy across multiple

That’s the mantra and simple elegance of the Intel Distribution of OpenVINO toolkit. Thanks to an intermediate representation (IR) format, you can develop and test a neural network on one type of processor such as a CPU, and deploy the same model on a range of processing units such as Intel® processors (CPU, GPU/Intel® Processor Graphics, VPU, FPGA) or even deploy heterogeneously (splitting the model) across two processors4. The IR concept allows you to run models built using multiple frameworks5 such as TensorFlow™, Caffe*, and MXNet*, and other exchange formats like ONNX*. This flexibility of supporting multiple frameworks, exchange formats and hardware accelerators is made possible due to the toolkit’s modular architecture. Below is a simplified graphical representation of the toolkit’s software components.

在这里插入图片描述
Intel® Distribution of OpenVINO™ Toolkit

Streamlined and easy development workflow

The toolkit has a simple development workflow, and it only takes three steps to develop and deploy a neural network on any of the supported processors and accelerators.

(1) Train a model on your preferred training hardware using one of the supported frameworks5.
You can choose to use one of the many pre-trained models3 shipped with the toolkit.
(2) Convert the trained model into a IR file using the toolkit’s model optimizer.
(3) Offload the IR model onto one of the supported hardware accelerators6 to perform inference.

在这里插入图片描述
Toolkit Workflow

This article walks you through the process of building your first artificial intelligence (AI) app using pre-trained neural networks, Intel Distribution of OpenVINO toolkit, and the Intel NCS 2.

Practical Learning!

You will build…

A set of AI apps that can perform image classification7, object detection8 and image segmentation9 on Intel NCS 2.

You will learn…

  • How to install and configure Intel Distribution of OpenVINO toolkit to support Intel NCS 2
  • How to deploy a pre-trained neural network on Intel NCS 2

You will need…

  • An Intel® Neural Compute Stick 2
  • An x86_64 laptop/desktop running Ubuntu 16.04 (“Development machine”)

If not already done so, follow the instructions on Intel NCS 2 getting started guide to install the toolkit and Intel NCS 2 plugins on your development machine.
https://software.intel.com/en-us/neural-compute-stick/get-started

Let’s build!

Running the toolkit’s pre-trained models on Intel NCS 2

If you followed the Intel NCS 2 getting started guide, you have already run some of the pre-trained models on the Intel NCS 2. This confirms that your development machine is fully set up to convert pre-trained models to IR files, and deploy these IR files onto Intel NCS 2 using the toolkit’s inference engine API. You probably ran one example each for image classification, object detection and image segmentation.

Running publicly available pre-trained models on Intel NCS 2

The really cool thing about the deep learning community is that they have published several pre-trained models for free. Let’s do our part in preventing global warming by not duplicating their efforts in re-training the same network on the same dataset that would consume power for a week or two. The below steps walk you through the toolkit’s development workflow of converting publicly available pre-trained neural net models to IR files and then running them on Intel NCS 2.

Run the following commands in a terminal window

On most Linux machines, hitting ctrl+alt+t will open a terminal window.

Step 1: Download publicly available models that are known to work with the toolkit

cd ~/intel/computer_vision_sdk/deployment_tools/model_downloader

# List public models that are known to work with OpenVINO
python3 downloader.py --print_all

# Download a specific model, say GoogLeNet V2
python3 downloader.py --name googlenet-v2

You can run downloader.py without the --name option to download all models, but it’ll take quite a while.

If the script ran fine, you should see googlenet-v2.caffemodel and googlenet-v2.prototxt in model_downloader/classification/googlenet/v2/caffe folder.

strong@foreverstrong:~$ cd /opt/intel/computer_vision_sdk/deployment_tools/model_downloader/
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader$ ll
total 116
drwxr-xr-x  2 root root  4096 11月 20 09:17 ./
drwxr-xr-x 10 root root  4096 11月 20 09:17 ../
-rwxr-xr-x  1 root root 10200 11月 20 09:17 downloader.py*
-rw-r--r--  1 root root 21338 11月 20 09:17 license.txt
-rw-r--r--  1 root root 62585 11月 20 09:17 list_topologies.yml
-rw-r--r--  1 root root  4463 11月 20 09:17 README.md
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader$ 
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader$ python3 downloader.py --print_all
densenet-121
densenet-161
densenet-169
densenet-201
squeezenet1.0
squeezenet1.1
mtcnn-p
mtcnn-r
mtcnn-o
mobilenet-ssd
vgg19
vgg16
ssd512
ssd300
inception-resnet-v2
dilation
googlenet-v1
googlenet-v2
googlenet-v4
alexnet
ssd_mobilenet_v2_coco
resnet-50
resnet-101
resnet-152
googlenet-v3
age-gender-recognition-retail-0013
age-gender-recognition-retail-0013-fp16
emotions-recognition-retail-0003
emotions-recognition-retail-0003-fp16
face-detection-adas-0001
face-detection-adas-0001-fp16
face-detection-retail-0004
face-detection-retail-0004-fp16
face-person-detection-retail-0002
face-person-detection-retail-0002-fp16
face-reidentification-retail-0001
face-reidentification-retail-0001-fp16
head-pose-estimation-adas-0001
head-pose-estimation-adas-0001-fp16
landmarks-regression-retail-0001
landmarks-regression-retail-0001-fp16
license-plate-recognition-barrier-0001
license-plate-recognition-barrier-0001-fp16
pedestrian-and-vehicle-detector-adas-0001
pedestrian-and-vehicle-detector-adas-0001-fp16
pedestrian-detection-adas-0002
pedestrian-detection-adas-0002-fp16
person-attributes-recognition-crossroad-0031
person-attributes-recognition-crossroad-0031-fp16
person-detection-action-recognition-0001
person-detection-action-recognition-0001-fp16
person-detection-retail-0001
person-detection-retail-0001-fp16
person-detection-retail-0013
person-detection-retail-0013-fp16
person-reidentification-retail-0031
person-reidentification-retail-0031-fp16
person-reidentification-retail-0076
person-reidentification-retail-0076-fp16
person-reidentification-retail-0079
person-reidentification-retail-0079-fp16
person-vehicle-bike-detection-crossroad-0078
person-vehicle-bike-detection-crossroad-0078-fp16
road-segmentation-adas-0001
road-segmentation-adas-0001-fp16
semantic-segmentation-adas-0001
semantic-segmentation-adas-0001-fp16
vehicle-attributes-recognition-barrier-0039
vehicle-attributes-recognition-barrier-0039-fp16
vehicle-detection-adas-0002
vehicle-detection-adas-0002-fp16
vehicle-license-plate-detection-barrier-0106
vehicle-license-plate-detection-barrier-0106-fp16
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader$ 
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader$ python3 downloader.py

###############|| Start downloading models ||###############

Traceback (most recent call last):
  File "downloader.py", line 160, in <module>
    os.makedirs(output, exist_ok=True)
  File "/usr/lib/python3.5/os.py", line 231, in makedirs
    makedirs(head, mode, exist_ok)
  File "/usr/lib/python3.5/os.py", line 231, in makedirs
    makedirs(head, mode, exist_ok)
  File "/usr/lib/python3.5/os.py", line 231, in makedirs
    makedirs(head, mode, exist_ok)
  File "/usr/lib/python3.5/os.py", line 241, in makedirs
    mkdir(name, mode)
PermissionError: [Errno 13] Permission denied: '/opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification'
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader$ 
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader$ cd ..
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools$ cd ..
strong@foreverstrong:/opt/intel/computer_vision_sdk$ sudo chmod 777 -R deployment_tools/
[sudo] password for strong: 
strong@foreverstrong:/opt/intel/computer_vision_sdk$ cd deployment_tools/
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools$ ll
total 40
drwxrwxrwx 10 root root 4096 11月 20 09:17 ./
drwxr-xr-x 11 root root 4096 11月 20 09:17 ../
drwxrwxrwx  6 root root 4096 11月 20 09:17 computer_vision_algorithms/
drwxrwxrwx  2 root root 4096 11月 20 09:17 demo/
drwxrwxrwx  3 root root 4096 11月 20 09:17 documentation/
drwxrwxrwx  4 root root 4096 11月 20 09:17 extension_generator/
drwxrwxrwx  9 root root 4096 11月 20 09:17 inference_engine/
drwxrwxrwx 29 root root 4096 11月 20 09:17 intel_models/
drwxrwxrwx  2 root root 4096 11月 20 09:17 model_downloader/
drwxrwxrwx  6 root root 4096 11月 20 09:17 model_optimizer/
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools$ cd model_downloader/
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader$ ll
total 116
drwxrwxrwx  2 root root  4096 11月 20 09:17 ./
drwxrwxrwx 10 root root  4096 11月 20 09:17 ../
-rwxrwxrwx  1 root root 10200 11月 20 09:17 downloader.py*
-rwxrwxrwx  1 root root 21338 11月 20 09:17 license.txt*
-rwxrwxrwx  1 root root 62585 11月 20 09:17 list_topologies.yml*
-rwxrwxrwx  1 root root  4463 11月 20 09:17 README.md*
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader$ python3 downloader.py

###############|| Start downloading models ||###############

...100%, 74 KB, 29896 KB/s, 0 seconds passed ========= densenet-121.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/densenet/121/caffe/densenet-121.prototxt

...100%, 99 KB, 89929 KB/s, 0 seconds passed ========= densenet-161.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/densenet/161/caffe/densenet-161.prototxt

...100%, 104 KB, 35823 KB/s, 0 seconds passed ========= densenet-169.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/densenet/169/caffe/densenet-169.prototxt

...100%, 124 KB, 69689 KB/s, 0 seconds passed ========= densenet-201.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/densenet/201/caffe/densenet-201.prototxt

...100%, 9 KB, 29780 KB/s, 0 seconds passed ========= squeezenet1.0.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/squeezenet/1.0/caffe/squeezenet1.0.prototxt

...100%, 9 KB, 103257 KB/s, 0 seconds passed ========= squeezenet1.1.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/squeezenet/1.1/caffe/squeezenet1.1.prototxt

...100%, 2 KB, 9029 KB/s, 0 seconds passed ========= mtcnn-p.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/object_detection/common/mtcnn/p/caffe/mtcnn-p.prototxt

...100%, 3 KB, 43328 KB/s, 0 seconds passed ========= mtcnn-r.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/object_detection/common/mtcnn/r/caffe/mtcnn-r.prototxt

...100%, 3 KB, 43027 KB/s, 0 seconds passed ========= mtcnn-o.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/object_detection/common/mtcnn/o/caffe/mtcnn-o.prototxt

...100%, 28 KB, 54100 KB/s, 0 seconds passed ========= mobilenet-ssd.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/object_detection/common/mobilenet-ssd/caffe/mobilenet-ssd.prototxt

...100%, 5 KB, 19903 KB/s, 0 seconds passed ========= vgg19.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/vgg/19/caffe/vgg19.prototxt

...100%, 4 KB, 17993 KB/s, 0 seconds passed ========= vgg16.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/vgg/16/caffe/vgg16.prototxt

...100%, 187 KB, 554 KB/s, 0 seconds passed ========= inception-resnet-v2.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/inception-resnet/v2/caffe/inception-resnet-v2.prototxt

...100%, 9 KB, 69444 KB/s, 0 seconds passed ========= dilation.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/semantic_segmentation/dilation/cityscapes/caffe/dilation.prototxt

...100%, 35 KB, 3242 KB/s, 0 seconds passed ========= googlenet-v1.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/googlenet/v1/caffe/googlenet-v1.prototxt

...100%, 58 KB, 61925 KB/s, 0 seconds passed ========= googlenet-v2.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/googlenet/v2/caffe/googlenet-v2.prototxt

...100%, 84 KB, 390 KB/s, 0 seconds passed ========= googlenet-v4.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/googlenet/v4/caffe/googlenet-v4.prototxt

...100%, 3 KB, 13036 KB/s, 0 seconds passed ========= alexnet.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/alexnet/caffe/alexnet.prototxt

...100%, 31 KB, 58993 KB/s, 0 seconds passed ========= resnet-50.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/resnet/v1/50/caffe/resnet-50.prototxt

...100%, 63 KB, 77066 KB/s, 0 seconds passed ========= resnet-101.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/resnet/v1/101/caffe/resnet-101.prototxt

...100%, 95 KB, 70622 KB/s, 0 seconds passed ========= resnet-152.prototxt ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/resnet/v1/152/caffe/resnet-152.prototxt

...100%, 13 KB, 8055 KB/s, 0 seconds passed ========= age-gender-recognition-retail-0013.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_attributes/age_gender/dldt/age-gender-recognition-retail-0013.xml

...100%, 13 KB, 7579 KB/s, 0 seconds passed ========= age-gender-recognition-retail-0013-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_attributes/age_gender/dldt/age-gender-recognition-retail-0013-fp16.xml

...100%, 18 KB, 5643 KB/s, 0 seconds passed ========= emotions-recognition-retail-0003.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_attributes/emotions_recognition/0003/dldt/emotions-recognition-retail-0003.xml

...100%, 18 KB, 5371 KB/s, 0 seconds passed ========= emotions-recognition-retail-0003-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_attributes/emotions_recognition/0003/dldt/emotions-recognition-retail-0003-fp16.xml

...100%, 90 KB, 221 KB/s, 0 seconds passed ========= face-detection-adas-0001.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/face/pruned_mobilenet_reduced_ssd_shared_weights/dldt/face-detection-adas-0001.xml

...100%, 90 KB, 294 KB/s, 0 seconds passed ========= face-detection-adas-0001-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/face/pruned_mobilenet_reduced_ssd_shared_weights/dldt/face-detection-adas-0001-fp16.xml

...100%, 47 KB, 183 KB/s, 0 seconds passed ========= face-detection-retail-0004.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/face/sqnet1.0modif-ssd/0004/dldt/face-detection-retail-0004.xml

...100%, 47 KB, 226 KB/s, 0 seconds passed ========= face-detection-retail-0004-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/face/sqnet1.0modif-ssd/0004/dldt/face-detection-retail-0004-fp16.xml

...100%, 164 KB, 374 KB/s, 0 seconds passed ========= face-person-detection-retail-0002.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/face_pedestrian/rmnet-ssssd-2heads/0002/dldt/face-person-detection-retail-0002.xml

...100%, 163 KB, 438 KB/s, 0 seconds passed ========= face-person-detection-retail-0002-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/face_pedestrian/rmnet-ssssd-2heads/0002/dldt/face-person-detection-retail-0002-fp16.xml

...100%, 148 KB, 353 KB/s, 0 seconds passed ========= face-reidentification-retail-0001.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/face/rmnet_based/dldt/face-reidentification-retail-0001.xml

...100%, 148 KB, 409 KB/s, 0 seconds passed ========= face-reidentification-retail-0001-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/face/rmnet_based/dldt/face-reidentification-retail-0001-fp16.xml

...100%, 16 KB, 5615 KB/s, 0 seconds passed ========= head-pose-estimation-adas-0001.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_attributes/headpose/vanilla_cnn/dldt/head-pose-estimation-adas-0001.xml

...100%, 16 KB, 8040 KB/s, 0 seconds passed ========= head-pose-estimation-adas-0001-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_attributes/headpose/vanilla_cnn/dldt/head-pose-estimation-adas-0001-fp16.xml

...100%, 16 KB, 6522 KB/s, 0 seconds passed ========= landmarks-regression-retail-0001.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_attributes/landmarks_regression/0001/dldt/landmarks-regression-retail-0001.xml

...100%, 16 KB, 4944 KB/s, 0 seconds passed ========= landmarks-regression-retail-0001-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_attributes/landmarks_regression/0001/dldt/landmarks-regression-retail-0001-fp16.xml

...100%, 22 KB, 181 KB/s, 0 seconds passed ========= license-plate-recognition-barrier-0001.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/optical_character_recognition/license_plate/dldt/license-plate-recognition-barrier-0001.xml

...100%, 22 KB, 1819 KB/s, 0 seconds passed ========= license-plate-recognition-barrier-0001-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/optical_character_recognition/license_plate/dldt/license-plate-recognition-barrier-0001-fp16.xml

...100%, 88 KB, 446 KB/s, 0 seconds passed ========= pedestrian-and-vehicle-detector-adas-0001.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/pedestrian-and-vehicle/mobilenet-reduced-ssd/dldt/pedestrian-and-vehicle-detector-adas-0001.xml

...100%, 88 KB, 2012 KB/s, 0 seconds passed ========= pedestrian-and-vehicle-detector-adas-0001-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/pedestrian-and-vehicle/mobilenet-reduced-ssd/dldt/pedestrian-and-vehicle-detector-adas-0001-fp16.xml

...100%, 88 KB, 2489 KB/s, 0 seconds passed ========= pedestrian-detection-adas-0002.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/pedestrian/mobilenet-reduced-ssd/dldt/pedestrian-detection-adas-0002.xml

...100%, 88 KB, 2704 KB/s, 0 seconds passed ========= pedestrian-detection-adas-0002-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/pedestrian/mobilenet-reduced-ssd/dldt/pedestrian-detection-adas-0002-fp16.xml

...100%, 95 KB, 2808 KB/s, 0 seconds passed ========= person-attributes-recognition-crossroad-0031.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_attributes/pedestrian/person-attributes-recognition-crossroad-0031/dldt/person-attributes-recognition-crossroad-0031.xml

...100%, 95 KB, 2694 KB/s, 0 seconds passed ========= person-attributes-recognition-crossroad-0031-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_attributes/pedestrian/person-attributes-recognition-crossroad-0031/dldt/person-attributes-recognition-crossroad-0031-fp16.xml

...100%, 255 KB, 1176 KB/s, 0 seconds passed ========= person-detection-action-recognition-0001.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/action_detection/pedestrian/rmnet_ssd/0023/dldt/person-detection-action-recognition-0001.xml

...100%, 254 KB, 1279 KB/s, 0 seconds passed ========= person-detection-action-recognition-0001-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/action_detection/pedestrian/rmnet_ssd/0023/dldt/person-detection-action-recognition-0001-fp16.xml

...100%, 131 KB, 1116 KB/s, 0 seconds passed ========= person-detection-retail-0001.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/pedestrian/hypernet-rfcn/0026/dldt/person-detection-retail-0001.xml

...100%, 131 KB, 541 KB/s, 0 seconds passed ========= person-detection-retail-0001-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/pedestrian/hypernet-rfcn/0026/dldt/person-detection-retail-0001-fp16.xml

...100%, 157 KB, 396 KB/s, 0 seconds passed ========= person-detection-retail-0013.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/pedestrian/rmnet_ssd/0013/dldt/person-detection-retail-0013.xml

...100%, 157 KB, 243 KB/s, 0 seconds passed ========= person-detection-retail-0013-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/pedestrian/rmnet_ssd/0013/dldt/person-detection-retail-0013-fp16.xml

...100%, 66 KB, 184 KB/s, 0 seconds passed ========= person-reidentification-retail-0031.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/pedestrian/rmnet_based/0031/dldt/person-reidentification-retail-0031.xml

...100%, 66 KB, 185 KB/s, 0 seconds passed ========= person-reidentification-retail-0031-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/pedestrian/rmnet_based/0031/dldt/person-reidentification-retail-0031-fp16.xml

...100%, 152 KB, 317 KB/s, 0 seconds passed ========= person-reidentification-retail-0076.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/pedestrian/rmnet_based/0076/dldt/person-reidentification-retail-0076.xml

...100%, 152 KB, 354 KB/s, 0 seconds passed ========= person-reidentification-retail-0076-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/pedestrian/rmnet_based/0076/dldt/person-reidentification-retail-0076-fp16.xml

...100%, 151 KB, 369 KB/s, 0 seconds passed ========= person-reidentification-retail-0079.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/pedestrian/rmnet_based/0079/dldt/person-reidentification-retail-0079.xml

...100%, 151 KB, 382 KB/s, 0 seconds passed ========= person-reidentification-retail-0079-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/pedestrian/rmnet_based/0079/dldt/person-reidentification-retail-0079-fp16.xml

...100%, 171 KB, 538 KB/s, 0 seconds passed ========= person-vehicle-bike-detection-crossroad-0078.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_detection/crossroad/0078/dldt/person-vehicle-bike-detection-crossroad-0078.xml

...100%, 170 KB, 449 KB/s, 0 seconds passed ========= person-vehicle-bike-detection-crossroad-0078-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_detection/crossroad/0078/dldt/person-vehicle-bike-detection-crossroad-0078-fp16.xml

...100%, 179 KB, 483 KB/s, 0 seconds passed ========= road-segmentation-adas-0001.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/segmentation/curbs/dldt/road-segmentation-adas-0001.xml

...100%, 179 KB, 443 KB/s, 0 seconds passed ========= road-segmentation-adas-0001-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/segmentation/curbs/dldt/road-segmentation-adas-0001-fp16.xml

...100%, 92 KB, 2541 KB/s, 0 seconds passed ========= semantic-segmentation-adas-0001.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/segmentation/semantic_segmentation/icnet_icv/dldt/semantic-segmentation-adas-0001.xml

...100%, 92 KB, 2482 KB/s, 0 seconds passed ========= semantic-segmentation-adas-0001-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/segmentation/semantic_segmentation/icnet_icv/dldt/semantic-segmentation-adas-0001-fp16.xml

...100%, 16 KB, 13206 KB/s, 0 seconds passed ========= vehicle-attributes-recognition-barrier-0039.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_attributes/vehicle/resnet10_update_1/dldt/vehicle-attributes-recognition-barrier-0039.xml

...100%, 16 KB, 8419 KB/s, 0 seconds passed ========= vehicle-attributes-recognition-barrier-0039-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_attributes/vehicle/resnet10_update_1/dldt/vehicle-attributes-recognition-barrier-0039-fp16.xml

...100%, 79 KB, 2625 KB/s, 0 seconds passed ========= vehicle-detection-adas-0002.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/vehicle/mobilenet-reduced-ssd/dldt/vehicle-detection-adas-0002.xml

...100%, 79 KB, 2571 KB/s, 0 seconds passed ========= vehicle-detection-adas-0002-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/vehicle/mobilenet-reduced-ssd/dldt/vehicle-detection-adas-0002-fp16.xml

...100%, 93 KB, 2874 KB/s, 0 seconds passed ========= vehicle-license-plate-detection-barrier-0106.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_detection/barrier/0106/dldt/vehicle-license-plate-detection-barrier-0106.xml

...100%, 93 KB, 2746 KB/s, 0 seconds passed ========= vehicle-license-plate-detection-barrier-0106-fp16.xml ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_detection/barrier/0106/dldt/vehicle-license-plate-detection-barrier-0106-fp16.xml

###############|| Start downloading weights ||###############

...100%, 31546 KB, 1910 KB/s, 16 seconds passed ========= densenet-121.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/densenet/121/caffe/densenet-121.caffemodel

...100%, 112964 KB, 3358 KB/s, 33 seconds passed ========= densenet-161.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/densenet/161/caffe/densenet-161.caffemodel

...100%, 55964 KB, 1938 KB/s, 28 seconds passed ========= densenet-169.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/densenet/169/caffe/densenet-169.caffemodel

...100%, 79163 KB, 2070 KB/s, 38 seconds passed ========= densenet-201.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/densenet/201/caffe/densenet-201.caffemodel

...100%, 4884 KB, 2224 KB/s, 2 seconds passed ========= squeezenet1.0.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/squeezenet/1.0/caffe/squeezenet1.0.caffemodel

...100%, 4834 KB, 2138 KB/s, 2 seconds passed ========= squeezenet1.1.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/squeezenet/1.1/caffe/squeezenet1.1.caffemodel

...100%, 27 KB, 277 KB/s, 0 seconds passed ========= mtcnn-p.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/object_detection/common/mtcnn/p/caffe/mtcnn-p.caffemodel

...100%, 398 KB, 848 KB/s, 0 seconds passed ========= mtcnn-r.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/object_detection/common/mtcnn/r/caffe/mtcnn-r.caffemodel

...100%, 1521 KB, 1757 KB/s, 0 seconds passed ========= mtcnn-o.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/object_detection/common/mtcnn/o/caffe/mtcnn-o.caffemodel

...100%, 22605 KB, 1389 KB/s, 16 seconds passed ========= mobilenet-ssd.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/object_detection/common/mobilenet-ssd/caffe/mobilenet-ssd.caffemodel

...100%, 561202 KB, 3284 KB/s, 170 seconds passed ========= vgg19.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/vgg/19/caffe/vgg19.caffemodel

...100%, 540461 KB, 2820 KB/s, 191 seconds passed ========= vgg16.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/vgg/16/caffe/vgg16.caffemodel

...100%, 218272 KB, 3095 KB/s, 70 seconds passed ========= inception-resnet-v2.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/inception-resnet/v2/caffe/inception-resnet-v2.caffemodel

...100%, 524898 KB, 1068 KB/s, 491 seconds passed ========= dilation.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/semantic_segmentation/dilation/cityscapes/caffe/dilation.caffemodel

...100%, 52279 KB, 3417 KB/s, 15 seconds passed ========= googlenet-v1.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/googlenet/v1/caffe/googlenet-v1.caffemodel

...100%, 62935 KB, 3356 KB/s, 18 seconds passed ========= googlenet-v2.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/googlenet/v2/caffe/googlenet-v2.caffemodel

...100%, 166774 KB, 3591 KB/s, 46 seconds passed ========= googlenet-v4.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/googlenet/v4/caffe/googlenet-v4.caffemodel

...100%, 238146 KB, 2369 KB/s, 100 seconds passed ========= alexnet.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/alexnet/caffe/alexnet.caffemodel

...100%, 100060 KB, 3895 KB/s, 25 seconds passed ========= resnet-50.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/resnet/v1/50/caffe/resnet-50.caffemodel

...100%, 174475 KB, 2546 KB/s, 68 seconds passed ========= resnet-101.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/resnet/v1/101/caffe/resnet-101.caffemodel

...100%, 235785 KB, 3737 KB/s, 63 seconds passed ========= resnet-152.caffemodel ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/resnet/v1/152/caffe/resnet-152.caffemodel

...100%, 8351 KB, 3818 KB/s, 2 seconds passed ========= age-gender-recognition-retail-0013.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_attributes/age_gender/dldt/age-gender-recognition-retail-0013.bin

...100%, 4175 KB, 1148 KB/s, 3 seconds passed ========= age-gender-recognition-retail-0013-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_attributes/age_gender/dldt/age-gender-recognition-retail-0013-fp16.bin

...100%, 9697 KB, 3861 KB/s, 2 seconds passed ========= emotions-recognition-retail-0003.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_attributes/emotions_recognition/0003/dldt/emotions-recognition-retail-0003.bin

...100%, 4848 KB, 1166 KB/s, 4 seconds passed ========= emotions-recognition-retail-0003-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_attributes/emotions_recognition/0003/dldt/emotions-recognition-retail-0003-fp16.bin

...100%, 4113 KB, 3838 KB/s, 1 seconds passed ========= face-detection-adas-0001.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/face/pruned_mobilenet_reduced_ssd_shared_weights/dldt/face-detection-adas-0001.bin

...100%, 2056 KB, 1034 KB/s, 1 seconds passed ========= face-detection-adas-0001-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/face/pruned_mobilenet_reduced_ssd_shared_weights/dldt/face-detection-adas-0001-fp16.bin

...100%, 2297 KB, 1286 KB/s, 1 seconds passed ========= face-detection-retail-0004.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/face/sqnet1.0modif-ssd/0004/dldt/face-detection-retail-0004.bin

...100%, 1148 KB, 1408 KB/s, 0 seconds passed ========= face-detection-retail-0004-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/face/sqnet1.0modif-ssd/0004/dldt/face-detection-retail-0004-fp16.bin

...100%, 3090 KB, 1207 KB/s, 2 seconds passed ========= face-person-detection-retail-0002.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/face_pedestrian/rmnet-ssssd-2heads/0002/dldt/face-person-detection-retail-0002.bin

...100%, 1545 KB, 1300 KB/s, 1 seconds passed ========= face-person-detection-retail-0002-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/face_pedestrian/rmnet-ssssd-2heads/0002/dldt/face-person-detection-retail-0002-fp16.bin

...100%, 2303 KB, 1300 KB/s, 1 seconds passed ========= face-reidentification-retail-0001.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/face/rmnet_based/dldt/face-reidentification-retail-0001.bin

...100%, 1151 KB, 1408 KB/s, 0 seconds passed ========= face-reidentification-retail-0001-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/face/rmnet_based/dldt/face-reidentification-retail-0001-fp16.bin

...100%, 7466 KB, 3905 KB/s, 1 seconds passed ========= head-pose-estimation-adas-0001.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_attributes/headpose/vanilla_cnn/dldt/head-pose-estimation-adas-0001.bin

...100%, 3733 KB, 1113 KB/s, 3 seconds passed ========= head-pose-estimation-adas-0001-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_attributes/headpose/vanilla_cnn/dldt/head-pose-estimation-adas-0001-fp16.bin

...100%, 744 KB, 1658 KB/s, 0 seconds passed ========= landmarks-regression-retail-0001.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_attributes/landmarks_regression/0001/dldt/landmarks-regression-retail-0001.bin

...100%, 372 KB, 1580 KB/s, 0 seconds passed ========= landmarks-regression-retail-0001-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_attributes/landmarks_regression/0001/dldt/landmarks-regression-retail-0001-fp16.bin

...100%, 4757 KB, 1293 KB/s, 3 seconds passed ========= license-plate-recognition-barrier-0001.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/optical_character_recognition/license_plate/dldt/license-plate-recognition-barrier-0001.bin

...100%, 2378 KB, 1304 KB/s, 1 seconds passed ========= license-plate-recognition-barrier-0001-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/optical_character_recognition/license_plate/dldt/license-plate-recognition-barrier-0001-fp16.bin

...100%, 6443 KB, 1251 KB/s, 5 seconds passed ========= pedestrian-and-vehicle-detector-adas-0001.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/pedestrian-and-vehicle/mobilenet-reduced-ssd/dldt/pedestrian-and-vehicle-detector-adas-0001.bin

...100%, 3221 KB, 1239 KB/s, 2 seconds passed ========= pedestrian-and-vehicle-detector-adas-0001-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/pedestrian-and-vehicle/mobilenet-reduced-ssd/dldt/pedestrian-and-vehicle-detector-adas-0001-fp16.bin

...100%, 4550 KB, 1227 KB/s, 3 seconds passed ========= pedestrian-detection-adas-0002.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/pedestrian/mobilenet-reduced-ssd/dldt/pedestrian-detection-adas-0002.bin

...100%, 2275 KB, 1281 KB/s, 1 seconds passed ========= pedestrian-detection-adas-0002-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/pedestrian/mobilenet-reduced-ssd/dldt/pedestrian-detection-adas-0002-fp16.bin

...100%, 4303 KB, 3926 KB/s, 1 seconds passed ========= person-attributes-recognition-crossroad-0031.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_attributes/pedestrian/person-attributes-recognition-crossroad-0031/dldt/person-attributes-recognition-crossroad-0031.bin

...100%, 2151 KB, 3269 KB/s, 0 seconds passed ========= person-attributes-recognition-crossroad-0031-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_attributes/pedestrian/person-attributes-recognition-crossroad-0031/dldt/person-attributes-recognition-crossroad-0031-fp16.bin

...100%, 4574 KB, 3781 KB/s, 1 seconds passed ========= person-detection-action-recognition-0001.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/action_detection/pedestrian/rmnet_ssd/0023/dldt/person-detection-action-recognition-0001.bin

...100%, 2287 KB, 3100 KB/s, 0 seconds passed ========= person-detection-action-recognition-0001-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/action_detection/pedestrian/rmnet_ssd/0023/dldt/person-detection-action-recognition-0001-fp16.bin

...100%, 12671 KB, 3274 KB/s, 3 seconds passed ========= person-detection-retail-0001.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/pedestrian/hypernet-rfcn/0026/dldt/person-detection-retail-0001.bin

...100%, 6335 KB, 1188 KB/s, 5 seconds passed ========= person-detection-retail-0001-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/pedestrian/hypernet-rfcn/0026/dldt/person-detection-retail-0001-fp16.bin

...100%, 2823 KB, 3294 KB/s, 0 seconds passed ========= person-detection-retail-0013.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/pedestrian/rmnet_ssd/0013/dldt/person-detection-retail-0013.bin

...100%, 1411 KB, 930 KB/s, 1 seconds passed ========= person-detection-retail-0013-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_detection/pedestrian/rmnet_ssd/0013/dldt/person-detection-retail-0013-fp16.bin

...100%, 1093 KB, 1309 KB/s, 0 seconds passed ========= person-reidentification-retail-0031.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/pedestrian/rmnet_based/0031/dldt/person-reidentification-retail-0031.bin

...100%, 546 KB, 1321 KB/s, 0 seconds passed ========= person-reidentification-retail-0031-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/pedestrian/rmnet_based/0031/dldt/person-reidentification-retail-0031-fp16.bin

...100%, 3202 KB, 1328 KB/s, 2 seconds passed ========= person-reidentification-retail-0076.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/pedestrian/rmnet_based/0076/dldt/person-reidentification-retail-0076.bin

...100%, 1601 KB, 1444 KB/s, 1 seconds passed ========= person-reidentification-retail-0076-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/pedestrian/rmnet_based/0076/dldt/person-reidentification-retail-0076-fp16.bin

...100%, 3202 KB, 1223 KB/s, 2 seconds passed ========= person-reidentification-retail-0079.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/pedestrian/rmnet_based/0079/dldt/person-reidentification-retail-0079.bin

...100%, 1601 KB, 1141 KB/s, 1 seconds passed ========= person-reidentification-retail-0079-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Retail/object_reidentification/pedestrian/rmnet_based/0079/dldt/person-reidentification-retail-0079-fp16.bin

...100%, 4603 KB, 3825 KB/s, 1 seconds passed ========= person-vehicle-bike-detection-crossroad-0078.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_detection/crossroad/0078/dldt/person-vehicle-bike-detection-crossroad-0078.bin

...100%, 2301 KB, 1050 KB/s, 2 seconds passed ========= person-vehicle-bike-detection-crossroad-0078-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_detection/crossroad/0078/dldt/person-vehicle-bike-detection-crossroad-0078-fp16.bin

...100%, 719 KB, 1587 KB/s, 0 seconds passed ========= road-segmentation-adas-0001.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/segmentation/curbs/dldt/road-segmentation-adas-0001.bin

...100%, 359 KB, 2602 KB/s, 0 seconds passed ========= road-segmentation-adas-0001-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/segmentation/curbs/dldt/road-segmentation-adas-0001-fp16.bin

...100%, 26116 KB, 3244 KB/s, 8 seconds passed ========= semantic-segmentation-adas-0001.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/segmentation/semantic_segmentation/icnet_icv/dldt/semantic-segmentation-adas-0001.bin

...100%, 13058 KB, 2816 KB/s, 4 seconds passed ========= semantic-segmentation-adas-0001-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/segmentation/semantic_segmentation/icnet_icv/dldt/semantic-segmentation-adas-0001-fp16.bin

...100%, 2445 KB, 2709 KB/s, 0 seconds passed ========= vehicle-attributes-recognition-barrier-0039.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_attributes/vehicle/resnet10_update_1/dldt/vehicle-attributes-recognition-barrier-0039.bin

...100%, 1222 KB, 2707 KB/s, 0 seconds passed ========= vehicle-attributes-recognition-barrier-0039-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_attributes/vehicle/resnet10_update_1/dldt/vehicle-attributes-recognition-barrier-0039-fp16.bin

...100%, 4213 KB, 3444 KB/s, 1 seconds passed ========= vehicle-detection-adas-0002.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/vehicle/mobilenet-reduced-ssd/dldt/vehicle-detection-adas-0002.bin

...100%, 2106 KB, 1045 KB/s, 2 seconds passed ========= vehicle-detection-adas-0002-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Transportation/object_detection/vehicle/mobilenet-reduced-ssd/dldt/vehicle-detection-adas-0002-fp16.bin

...100%, 2512 KB, 3377 KB/s, 0 seconds passed ========= vehicle-license-plate-detection-barrier-0106.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_detection/barrier/0106/dldt/vehicle-license-plate-detection-barrier-0106.bin

...100%, 1256 KB, 3544 KB/s, 0 seconds passed ========= vehicle-license-plate-detection-barrier-0106-fp16.bin ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/Security/object_detection/barrier/0106/dldt/vehicle-license-plate-detection-barrier-0106-fp16.bin

###############|| Start downloading topologies in tarballs ||###############

...100%, 98624 KB, 3383 KB/s, 29 seconds passed ========= ssd512.tar.gz ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/object_detection/common/ssd/512/caffe/ssd512.tar.gz

...100%, 95497 KB, 3460 KB/s, 27 seconds passed ========= ssd300.tar.gz ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/object_detection/common/ssd/300/caffe/ssd300.tar.gz

...100%, 183521 KB, 3615 KB/s, 50 seconds passed ========= ssd_mobilenet_v2_coco.tar.gz ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/object_detection/common/ssd_mobilenet_v2_coco/tf/ssd_mobilenet_v2_coco.tar.gz

...100%, 86590 KB, 3430 KB/s, 25 seconds passed ========= googlenet-v3.tar.gz ====> /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/googlenet/v3/tf/googlenet-v3.tar.gz


###############|| Post processing ||###############

========= Changing input dimensions in squeezenet1.0.prototxt =========
========= Changing input dimensions in squeezenet1.1.prototxt =========
========= Changing input dimensions in mtcnn-p.prototxt =========
========= Changing input dimensions in vgg19.prototxt =========
========= Changing input dimensions in vgg16.prototxt =========
========= Extracting files from ssd512.tar.gz
========= Moving ssd512.prototxt and ssd512.caffemodel to /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/object_detection/common/ssd/512/caffe after untarring the archive =========
========= Deleting "save_output_param" from ssd512.prototxt =========
========= Extracting files from ssd300.tar.gz
========= Moving ssd300.prototxt and ssd300.caffemodel to /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/object_detection/common/ssd/300/caffe after untarring the archive =========
========= Deleting "save_output_param" from ssd300.prototxt =========
========= Changing input dimensions in googlenet-v1.prototxt =========
========= Changing input dimensions in googlenet-v2.prototxt =========
========= Moving to new Caffe layer presentation googlenet-v2.prototxt =========
========= Changing input dimensions in alexnet.prototxt =========
========= Extracting files from ssd_mobilenet_v2_coco.tar.gz
========= Moving ssd_mobilenet_v2_coco.frozen.pb to /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/object_detection/common/ssd_mobilenet_v2_coco/tf after untarring the archive =========
========= Extracting files from googlenet-v3.tar.gz
========= Moving googlenet-v3.frozen.pb to /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/googlenet/v3/tf/ after untarring the archive =========
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader$ ll
total 140
drwxrwxrwx  8 root   root    4096 11月 28 11:59 ./
drwxrwxrwx 10 root   root    4096 11月 20 09:17 ../
drwxrwxr-x  9 strong strong  4096 11月 28 11:29 classification/
-rwxrwxrwx  1 root   root   10200 11月 20 09:17 downloader.py*
-rwxrwxrwx  1 root   root   21338 11月 20 09:17 license.txt*
-rwxrwxrwx  1 root   root   62585 11月 20 09:17 list_topologies.yml*
drwxrwxr-x  3 strong strong  4096 11月 28 11:29 object_detection/
-rwxrwxrwx  1 root   root    4463 11月 20 09:17 README.md*
drwxrwxr-x  6 strong strong  4096 11月 28 11:29 Retail/
drwxrwxr-x  5 strong strong  4096 11月 28 11:30 Security/
drwxrwxr-x  3 strong strong  4096 11月 28 11:29 semantic_segmentation/
drwxrwxr-x  5 strong strong  4096 11月 28 11:30 Transportation/
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader$ 

Step 2: Convert the downloaded pre-trained model into IR files

cd ~/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe

# Ensure that the OpenVINO environment is initialized
source ~/intel/computer_vision_sdk/bin/setupvars.sh

# Use model optimizer to convert googlenet.caffemodel to IR
mo.py --data_type FP16 --input_model googlenet-v2.caffemodel --input_proto googlenet-v2.prototxt

If the script ran fine, you should see googlenet-v2.bin, googlenet-v2.mapping and googlenet-v2.xml in model_downloader/classification/googlenet/v2/caffe folder.

strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader$ cd classification/googlenet/v2/caffe/
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe$ source /opt/intel/computer_vision_sdk/bin/setupvars.sh
[setupvars.sh] OpenVINO environment initialized
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe$ 
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe$ mo.py --data_type FP16 --input_model googlenet-v2.caffemodel --input_proto googlenet-v2.prototxt
Model Optimizer arguments:
Common parameters:
	- Path to the Input Model: 	/opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/googlenet/v2/caffe/googlenet-v2.caffemodel
	- Path for generated IR: 	/opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/googlenet/v2/caffe/.
	- IR output name: 	googlenet-v2
	- Log level: 	ERROR
	- Batch: 	Not specified, inherited from the model
	- Input layers: 	Not specified, inherited from the model
	- Output layers: 	Not specified, inherited from the model
	- Input shapes: 	Not specified, inherited from the model
	- Mean values: 	Not specified
	- Scale values: 	Not specified
	- Scale factor: 	Not specified
	- Precision of IR: 	FP16
	- Enable fusing: 	True
	- Enable grouped convolutions fusing: 	True
	- Move mean values to preprocess section: 	False
	- Reverse input channels: 	False
Caffe specific parameters:
	- Enable resnet optimization: 	True
	- Path to the Input prototxt: 	/opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/googlenet/v2/caffe/googlenet-v2.prototxt
	- Path to CustomLayersMapping.xml: 	Default
	- Path to a mean file: 	Not specified
	- Offsets for a mean file: 	Not specified
Model Optimizer version: 	1.4.292.6ef7232d

[ SUCCESS ] Generated IR model.
[ SUCCESS ] XML file: /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/googlenet/v2/caffe/./googlenet-v2.xml
[ SUCCESS ] BIN file: /opt/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_downloader/classification/googlenet/v2/caffe/./googlenet-v2.bin
[ SUCCESS ] Total execution time: 4.05 seconds. 
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe$ 
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe$ 
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe$ ll
total 84976
drwxrwxr-x 2 strong strong     4096 11月 28 16:38 ./
drwxrwxr-x 3 strong strong     4096 11月 28 11:29 ../
-rw-rw-r-- 1 strong strong 22370064 11月 28 16:38 googlenet-v2.bin
-rw-rw-r-- 1 strong strong 64445495 11月 28 11:49 googlenet-v2.caffemodel
-rw-rw-r-- 1 strong strong    28372 11月 28 16:38 googlenet-v2.mapping
-rw-rw-r-- 1 strong strong    60272 11月 28 11:59 googlenet-v2.prototxt
-rw-rw-r-- 1 strong strong    94600 11月 28 16:38 googlenet-v2.xml
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe$

Step 3: Deploy the converted IR model onto Intel NCS 2 using the toolkit’s IE API

/opt/intel/computer_vision_sdk/deployment_tools/inference_engine/samples/python_samples

cd ~/intel/computer_vision_sdk/deployment_tools/inference_engine/samples/python_samples

# Download a test image from the internet
wget -N https://upload.wikimedia.org/wikipedia/commons/b/b6/Felis_catus-cat_on_snow.jpg

# Ensure that the OpenVINO environment is initialized
source ~/intel/computer_vision_sdk/bin/setupvars.sh

# Run an inference on this image using a built-in sample code
python3 classification_sample.py -m ~/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe/googlenet-v2.xml -i Felis_catus-cat_on_snow.jpg -d MYRIAD

If everything ran fine, you should see the below message in the terminal window. Class #173 corresponds to the ‘tabby cat’ class/category. Try downloading other images of tabby cat and rerunning the example.

Image Felis_catus-cat_on_snow.jpg

0.3881836 label #173
0.3193359 label #54
0.2410889 label #7
0.0361328 label #200
0.0037460 label #84
0.0025158 label #66
0.0021381 label #10
0.0016766 label #473
0.0013685 label #198
0.0007257 label #152

Congratulations! You have successfully installed and configured Intel Distribution of OpenVINO Toolkit to develop smart apps for Intel® Neural Compute Stick 2.

strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe$ cd ../../../../../
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools$ ll
total 40
drwxrwxrwx 10 root root 4096 11月 20 09:17 ./
drwxr-xr-x 11 root root 4096 11月 20 09:17 ../
drwxrwxrwx  6 root root 4096 11月 20 09:17 computer_vision_algorithms/
drwxrwxrwx  2 root root 4096 11月 20 09:17 demo/
drwxrwxrwx  3 root root 4096 11月 20 09:17 documentation/
drwxrwxrwx  4 root root 4096 11月 20 09:17 extension_generator/
drwxrwxrwx  9 root root 4096 11月 20 09:17 inference_engine/
drwxrwxrwx 29 root root 4096 11月 20 09:17 intel_models/
drwxrwxrwx  8 root root 4096 11月 28 11:59 model_downloader/
drwxrwxrwx  6 root root 4096 11月 20 09:17 model_optimizer/
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools$ cd inference_engine/samples/python_samples/
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/inference_engine/samples/python_samples$ ll
total 128
drwxrwxrwx  5 root root  4096 11月 23 21:57 ./
drwxrwxrwx 31 root root  4096 11月 20 09:17 ../
drwxrwxrwx  8 root root  4096 11月 20 09:17 accuracy_checker/
-rwxrwxrwx  1 root root  5079 11月 20 09:17 affinity_setting_demo.py*
-rwxrwxrwx  1 root root  6294 11月 20 09:17 classification_sample_async.py*
-rwxrwxrwx  1 root root  6199 11月 20 09:17 classification_sample.py*
drwxrwxrwx  2 root root  4096 11月 20 09:17 cross_check_tool/
drwxrwxrwx  2 root root  4096 11月 20 09:17 greengrass_samples/
-rwxrwxrwx  1 root root 31675 11月 20 09:17 image_net_synset.txt*
-rwxrwxrwx  1 root root  8318 11月 23 21:57 object_detection_demo_ssd_async.py*
-rwxrwxrwx  1 root root 12897 11月 20 09:17 object_detection_demo_yolov3.py*
-rwxrwxrwx  1 root root    19 11月 20 09:17 requirements.txt*
-rwxrwxrwx  1 root root  6555 11月 20 09:17 segmentation_sample.py*
-rwxrwxrwx  1 root root  6687 11月 20 09:17 style_transfer_sample.py*
-rwxrwxrwx  1 root root   145 11月 20 09:17 voc_labels.txt*
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/inference_engine/samples/python_samples$ wget -N https://upload.wikimedia.org/wikipedia/commons/b/b6/Felis_catus-cat_on_snow.jpg
--2018-11-28 16:41:50--  https://upload.wikimedia.org/wikipedia/commons/b/b6/Felis_catus-cat_on_snow.jpg
Resolving upload.wikimedia.org (upload.wikimedia.org)... 198.35.26.112, 2620:0:863:ed1a::2:b
Connecting to upload.wikimedia.org (upload.wikimedia.org)|198.35.26.112|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 2125399 (2.0M) [image/jpeg]
Saving to: ‘Felis_catus-cat_on_snow.jpg’

Felis_catus-cat_on_snow.jpg             100%[==============================================================================>]   2.03M  50.1KB/s    in 30s     

2018-11-28 16:42:22 (68.7 KB/s) - ‘Felis_catus-cat_on_snow.jpg’ saved [2125399/2125399]

strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/inference_engine/samples/python_samples$ source /opt/intel/computer_vision_sdk/bin/setupvars.sh
[setupvars.sh] OpenVINO environment initialized
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/inference_engine/samples/python_samples$ 
strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/inference_engine/samples/python_samples$ python3 classification_sample.py -m /opt/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe/googlenet-v2.xml -i Felis_catus-cat_on_snow.jpg -d MYRIAD
[ INFO ] Loading network files:
	/opt/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe/googlenet-v2.xml
	/opt/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe/googlenet-v2.bin
[ INFO ] Preparing input blobs
[ WARNING ] Image Felis_catus-cat_on_snow.jpg is resized from (2000, 3000) to (224, 224)
[ INFO ] Batch size is 1
[ INFO ] Loading model to the plugin
[ INFO ] Starting inference (1 iterations)
[ INFO ] Average running time of one iteration: 25.846004486083984 ms
[ INFO ] Processing output blob
[ INFO ] Top 10 results: 
Image Felis_catus-cat_on_snow.jpg

0.3801270 label #173
0.2961426 label #54
0.2783203 label #7
0.0329590 label #200
0.0032921 label #84
0.0021286 label #66
0.0018044 label #10
0.0016289 label #473
0.0009890 label #198
0.0006843 label #152


strong@foreverstrong:/opt/intel/computer_vision_sdk/deployment_tools/inference_engine/samples/python_samples$ 

Further Experiments

  • Okay, you just ran what I call ‘the blinky code’ (or ‘Hello World!’) example, now what? How about a ‘my-first-openvino-app’? Try writing your own application using the Inference Engine API.
  • At the time of writing this blog, the toolkit did not ship with a labels file which could be used to display a sensible inference result as against a class ID like #173. Try using the --labels flag with classification_sample.py to print out actual names of the inference results.
    Reference: See “BEST REPLY” in this community forum post.
    https://software.intel.com/en-us/forums/computer-vision/topic/796906

the --labels option
OpenVINO doesn’t [yet] ship with labels file for all supported models, so I pulled the ILSVRC2012 sysnset_words.txt from http://dl.caffe.berkeleyvision.org/caffe_ilsvrc12.tar.gz and renamed it as googlenet-v1.labels. Note that the ILSVRC2012 synset_words.txt won’t work for GoogLeNet V2 since V2 was trained on ILSVRC2015, you’d have to fetch the 2015 labels file when running GoogLeNet V2.
http://dl.caffe.berkeleyvision.org/caffe_ilsvrc12.tar.gz

python3 classification_sample.py -m /opt/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe/googlenet-v2.xml -i Felis_catus-cat_on_snow.jpg -d MYRIAD --labels /opt/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe/googlenet-v2.labels

Further Reading

  • If you like to migrate your Intel Neural Compute SDK apps to Intel Distribution of OpenVINO Toolkit, check out this migration document.
  • The Intel NCS 2 is powered by Intel Movidius MyriadX VPU which has an on-chip neural network accelerator. This hardware neural network accelerator significantly improves performance by running certain layers directly on the hardware as against splitting them into operations that run on the SHAVE DSPs. This article shows you how to optimize your Neural Networks to efficiently run on MyriadX’s Neural Compute Engine.
    https://software.intel.com/en-us/articles/neural-compute-stick-2-optimizing-networks

Related links

1Intel® Distribution of OpenVINO™ Toolkit
https://software.intel.com/en-us/openvino-toolkit

2New Intel Vision Accelerator Solutions Speed Deep Learning and Artificial Intelligence on Edge Devices
https://newsroom.intel.com/news/new-intel-vision-accelerator-solutions-speed-deep-learning-artificial-intelligence-edge-devices/

3Pretrained Models
https://software.intel.com/en-us/openvino-toolkit/documentation/pretrained-models

4Intel’s OpenVX Developer Guide
https://software.intel.com/en-us/openvino-ovx-guide-heterogeneous-computing-with-openvino-toolkit

5Release Notes for Intel® Distribution of OpenVINO™ toolkit
https://software.intel.com/en-us/articles/OpenVINO-RelNotes

6Pretrained Models
https://software.intel.com/en-us/openvino-toolkit/documentation/pretrained-models

7 8 9Inference Engine Samples
https://software.intel.com/en-us/articles/OpenVINO-IE-Samples

+Testing by Intel as of October 12, 2018
+由英特尔于 2018 年 10 月 12 日测试

Deep Learning Workload Configuration. Comparing Intel® Movidius™ Neural Compute Stick based on Intel® Movidius™ Myriad™ 2 VPU vs. Intel® Neural Compute Stick 2 based on the Intel® Movidius™ Myriad™ X VPU with Asynchronous Plug-in enabled for (2xNCE engines). As measured by images per second across GoogleNetV1 and YoloTiny v1. Base System Configuration: Intel® Core™ I7-8700K 95W TDP (6C12T at 3.7GHz base freq and 4.7GHz max turbo freq), Graphics: Intel® UHD Graphics 630 Total Memory 65830088 kB Storage: INTEL SSDSC2BB24 (240GB), Ubuntu 16.04.5 Linux- 4.15.0-36-generic-x86_64-with - Ubuntu -16.04-xenial, deeplearning_deploymenttoolkit_2018.0.14348.0, API version 1.2, Build 14348, myriadPlugin, FP16, Batch Size = 1
深度学习工作负载配置:对基于英特尔® Movidius™ Myriad™ 2 视觉处理器 (VPU) 的英特尔® Movidius™ 神经计算棒及基于英特尔® Movidius™ Myriad™ X 视觉处理器 (VPU) 的英特尔® 神经计算棒 2 进行比较,两种神经计算引擎均启用了异步插件。 按每秒钟跨越 GoogLeNet V1 和 Tiny YOLO* V1 的图像数测定。
基础系统配置:英特尔® 酷睿™ i7 处理器 8700K,95 W TDP(6C12T 于 3.7 GHz 基础频率和 4.7 GHz 最大超频)。 显卡:英特尔® 超高清显卡 630,总内存 65830088 kB,存储:英特尔® 固态盘 SC2BB24(240 GB),Ubuntu* 16.04.5 Linux* 4.15.0-36-generic-x86_64-with-Ubuntu-16.04-xenial, deeplearning_deploymenttoolkit_2018.0.14348.0, API version 1.2, Build 14348, myriadPlugin API, FP16, Batch Size = 1

Software and workloads used in performance tests may have been optimized for performance only on Intel® microprocessors.
性能测试中使用的软件和工作负载可能仅在英特尔® 微处理器上进行了性能优化。

Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products. For more complete information visit www.intel.com/benchmarks.
性能测试 (如 SYSmark* 和 MobileMark*) 使用特定的计算机系统、组件、软件、操作系统和功能进行测量。 对这些因素的任何更改可能导致不同的结果。 您应该查询其它信息和性能测试以帮助您对正在考虑的购买作出全面的评估,包括该产品在与其它产品结合使用时的性能。 有关更多完整信息,请访问基准。

Performance results are based on testing as of October 12, 2018 and may not reflect all publicly available security updates. See configuration disclosure for details. No product can be absolutely secure.
性能结果根据至 2018 年 10 月 12 日止的测试,不一定反映所有可公开获得的安全更新。 有关详细信息,请参阅配置 没有产品是绝对安全的。

*Other names and brands may be claimed as the property of others.

For more complete information about compiler optimizations, see our Optimization Notice.
https://software.intel.com/en-us/articles/optimization-notice

Wordbook

Intel® Deep Learning Deployment Toolkit,Intel® DLDT
Intermediate Representation,IR
form factor:形状因数,形状系数
mantra ['mæntrə]:n. 咒语,颂歌
elegance ['elɪg(ə)ns]:n. 典雅,高雅

已标记关键词 清除标记
相关推荐
©️2020 CSDN 皮肤主题: 成长之路 设计师:Amelia_0503 返回首页