Comments (6)
Hi @HuAndrew , same question here.
I am playing with this code recently and was also wondering about how did you generate the detection part.
To be more specific, I am detecting humans from the COCO val 2017 keypoints images (5000 images) from the person_keypoints_val2017.json
. I try to use Yolo v3 detector and keep only the bounding boxes regarding humans. Then I dump the JSON file which is similar to this repo's.
However, the size of the generated JSON is quite small compared with theirs (~1.3MB vs 16.4MB). Also, when I run cocoEval
and use person_keypoints_val2017.json
as groundtruth, I can only get about 40 AP.
Any suggestions? Thank you in advance :)
from human-pose-estimation.pytorch.
I have the same question. Can you please share your detector or give a link to a similar one?
from human-pose-estimation.pytorch.
👍 . Related papers keep mentioning of the "person detector used in Simple Baseline..." but it's nowhere to be found
from human-pose-estimation.pytorch.
Hi @HuAndrew , same question here.
I am playing with this code recently and was also wondering about how did you generate the detection part.
To be more specific, I am detecting humans from the COCO val 2017 keypoints images (5000 images) from the
person_keypoints_val2017.json
. I try to use Yolo v3 detector and keep only the bounding boxes regarding humans. Then I dump the JSON file which is similar to this repo's.However, the size of the generated JSON is quite small compared with theirs (~1.3MB vs 16.4MB). Also, when I run
cocoEval
and useperson_keypoints_val2017.json
as groundtruth, I can only get about 40 AP.Any suggestions? Thank you in advance :)
Well the author said 56.4 AP on person category. I have used Detectron's model . In End-to-End Faster & Mask R-CNN Baselines, the entry X-101-64x4d-FPN with 42.4 box AP can get 55.7 AP on person cat. I think this is competitive.
from human-pose-estimation.pytorch.
@bearpaw @Odaimoko Hello, I test multi detector, like mask, cascade_RCNN , and the detector vis and other preds' results are as follows:
vis samples
preds samples
256x192_pose_resnet_50_d256d256d256 | total person | detect AP | keypoint |
---|---|---|---|
ground truth | 11004 | XXXXX | 72.4 |
faster author | 104125 | 56.4 | 70.5 |
mask rcnn_0.7 | 13167 | 48.6 | 68.1 |
mask rcnn_0.5 | 15530 | 49.5 | 68.6 |
mask rcnn_0.3 | 15796 | 49.6 | 68.7 |
Cascade_RCNN | 73597 | 53.0 | 70.0 |
Then
From the test results, something can be found:
- In order to achieve the purpose of rescore tricks, the author let detector gives multiple detection boxes for every person instance(rescore operation refer to COCO17-Keypoints-TeamOKS). And rescore could amend pred results.
- Then if we want to get multi bboxs, we can adjust NMS postprocess.
- As long as the detector position is very correct like gt bbox, the prediction results are also very good.
- Top-down methods, the detector is very import to improve preds results.
- But I use multi bbox, preds results are worse. So I guess the author used the byte bboxs and the NMS operation together amend the detectors performance.
- Other detectors: maskrcnn-benchmark, yolov3.
Welcome to Join pose forum www.ilovepose.com
from human-pose-estimation.pytorch.
Evaluated using the Detectron2 repo:
- Faster R-CNN with ResNeXt-101 FPN backbone gets 56.6 AP for the person category on COCO val2017.
- Faster R-CNN with ResNet-101 FPN backbone gets 55.7 AP for the person category on COCO val2017.
https://github.com/facebookresearch/detectron2/blob/main/MODEL_ZOO.md
from human-pose-estimation.pytorch.
Related Issues (20)
- 关于数据增强的疑惑。
- Help with Transfer Learning
- 模型的速度问题
- 关于数据处理,请大神解惑。 HOT 1
- 检测部分的代码 HOT 1
- 训练结果低于作者给的结果 HOT 3
- I have an error when I load image file in data/coco/images/val2017 HOT 2
- About the rotation of test_set in MPII
- cpu_nms HOT 1
- TypeError: _update_dict() missing 1 required positional argument: 'code' HOT 2
- experiments and core.config
- 只能实现单人姿态估计?
- TypeError: unhashable type: 'slice'
- flip_pairs?
- Which part of this code that explains joint propagation using optical flow?
- This repo is missing important files HOT 1
- lib make error HOT 1
- Support inference in C++
- Pretrained 2d pose estimation with resnet50 backbone
- How to I run demo in video.
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from human-pose-estimation.pytorch.