Comments (2)
Thanks for your attention. Please refer to the paper for the settings in the speed test. With the advanced GPUs and PyTorch framework, ViTPose is faster than HRNet. Besides, the inference speed using tensorRT is not only related to the model but also the configurations. e.g., the maximum memory allowed or the optimal searched calculation manner.
from vitpose.
Hi, thank you for answering.
I had run a test in native Pytorch as well. ViTPose was indeed faster or similar when the batch size was equal to 1.
I tested the yolov5 hrnet and vitpose pipeline with the webcam for single person infrerence and the VitPose method had indeed higher fps.
When i increased the batch size to 10 ,HRNet for some reason was 2-3 times faster both in the inference test and with a video. If I understood correctly these results could be related to my GPU (GTX 1650)?
In the following pictures I have attached the inference tests in Pytorch. The first row in each picture is with batch 1 while the second with batch size equal to 10.
from vitpose.
Related Issues (20)
- APT-36k train valid(test) split
- Support for Selective Person Tracking in Multi-Person Videos
- which config file can train COCO+AIC+MPII dataset?
- Questions about table5 in the paper
- Issue about the padding when building the PatchEmbedding layer HOT 1
- the config about ViTPose small_simple
- where is smpl_mean_params.npz
- Question about parameter "max_num_joints" HOT 1
- Inconsistency in Reported Experimental Results for ViTPose and ViTPose++ Across Papers HOT 2
- Assertion Error During Testing HOT 1
- How to identify occluded hands?
- Duplicate code in topdown_heatmap_simple_head.py
- What is the details of public-data/ViTPose on huggingface? HOT 1
- about input size
- Output keypoints from Huggingface demo?
- the code for the visualization results of Figure 8 in the vitpose++ paper
- what is backbone.cls_token weights, where it is used?
- Loss is zero while training ViTPose Base with custom dataset
- how to run inference with pretrained model? HOT 1
- Breakpoint Resume Transmission
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 vitpose.