# human-pose-estimation-0001 Intel Pre-trained Model

###### tags: `POT`

cat /opt/intel/openvino/deployment_tools/open_model_zoo/models/intel/human-pose-estimation-0001/description/human-pose-estimation-0001.md
# human-pose-estimation-0001

## Use Case and High-Level Description

This is a multi-person 2D pose estimation network (based on the OpenPose approach) with tuned MobileNet v1 as a feature extractor.
For every person in an image, the network detects a human pose: a body skeleton consisting of keypoints and connections between them.
The pose may contain up to 18 keypoints: ears, eyes, nose, neck, shoulders, elbows, wrists, hips, knees, and ankles.

## Example


## Specification

| Metric | Value |
|---------------------------------|-------------------------------------------|
| Average Precision (AP) | 42.8% |
| GFlops | 15.435 |
| MParams | 4.099 |
| Source framework | Caffe* |

Average Precision metric described in [COCO Keypoint Evaluation site](https://cocodataset.org/#keypoints-eval).

Tested on a COCO validation subset from the original paper [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://arxiv.org/abs/1611.08050).

## Inputs

Name: `data`, shape: [1x3x256x456]. An input image in the [BxCxHxW] format,
where:
- B - batch size
- C - number of channels
- H - image height
- W - image width
Expected color order is BGR.

## Outputs

The net outputs two blobs with the [1, 38, 32, 57] and [1, 19, 32, 57] shapes. The first blob contains keypoint pairwise relations (part affinity fields), while the second blob contains keypoint heatmaps.

## Legal Information
[*] Other names and brands may be claimed as the property of others.

python3 /opt/intel/openvino_2021.3.394/deployment_tools/tools/model_downloader/downloader.py -o /home/openvino/openvino_models --name human-pose-estimation-0001
################|| Downloading human-pose-estimation-0001 ||################

========== Downloading /home/openvino/openvino_models/intel/human-pose-estimation-0001/FP32/human-pose-estimation-0001.xml
... 100%, 146 KB, 267 KB/s, 0 seconds passed

========== Downloading /home/openvino/openvino_models/intel/human-pose-estimation-0001/FP32/human-pose-estimation-0001.bin
... 100%, 16010 KB, 8691 KB/s, 1 seconds passed

========== Downloading /home/openvino/openvino_models/intel/human-pose-estimation-0001/FP16/human-pose-estimation-0001.xml
... 100%, 146 KB, 358 KB/s, 0 seconds passed

========== Downloading /home/openvino/openvino_models/intel/human-pose-estimation-0001/FP16/human-pose-estimation-0001.bin
... 100%, 8005 KB, 5802 KB/s, 1 seconds passed

========== Downloading /home/openvino/openvino_models/intel/human-pose-estimation-0001/FP16-INT8/human-pose-estimation-0001.xml
... 100%, 418 KB, 755 KB/s, 0 seconds passed

========== Downloading /home/openvino/openvino_models/intel/human-pose-estimation-0001/FP16-INT8/human-pose-estimation-0001.bin
... 100%, 4072 KB, 3687 KB/s, 1 seconds passed

Expected color order is BGR.

## Outputs

1. The net outputs one blobs with shapes [1, 3, 1080, 1920] that contains image after super
resolution.

## Legal Information
[*] Other names and brands may be claimed as the property of others.
openvino@1521a7255089:/opt/intel/openvino/deployment_tools/open_model_zoo/models/intel$ python3 /opt/intel/openvino_2021.3.394/deployment_tools/tools/model_downloader/downloader.py -o /home/openvino/openvino_models --name single-image-super-resolution-1032
################|| Downloading single-image-super-resolution-1032 ||################

========== Downloading /home/openvino/openvino_models/intel/single-image-super-resolution-1032/FP32/single-image-super-resolution-1032.xml
... 100%, 77 KB, 189 KB/s, 0 seconds passed

========== Downloading /home/openvino/openvino_models/intel/single-image-super-resolution-1032/FP32/single-image-super-resolution-1032.bin
... 100%, 116 KB, 283 KB/s, 0 seconds passed

========== Downloading /home/openvino/openvino_models/intel/single-image-super-resolution-1032/FP16/single-image-super-resolution-1032.xml
... 100%, 77 KB, 278 KB/s, 0 seconds passed

========== Downloading /home/openvino/openvino_models/intel/single-image-super-resolution-1032/FP16/single-image-super-resolution-1032.bin
... 100%, 58 KB, 211 KB/s, 0 seconds passed

========== Downloading /home/openvino/openvino_models/intel/single-image-super-resolution-1032/FP16-INT8/single-image-super-resolution-1032.xml
... 100%, 167 KB, 305 KB/s, 0 seconds passed

========== Downloading /home/openvino/openvino_models/intel/single-image-super-resolution-1032/FP16-INT8/single-image-super-resolution-1032.bin
... 100%, 30 KB, 220 KB/s, 0 seconds passed