Comments (3)
hi,
-
The task
Keypoint Estimation Subnet with person segmentation mask
is still in to-do list, I have not added it in keypoints subnet yet. -
The batch-size of dataloader is linearly related to the number of GPUs. Specifically, batch-size will be multiplied by the number of GPUs you enabled in
CUDA_VISIBLES_DEVICES
. Related code is in multipose_keypoint_train.py#L61.
That is more GPUs means more pre-processing such as data agumentation, GT generation and so on. All of these pre-processing are on CPUs. So, I think the training speed maybe limited by not only the GPU but the CPUs' computational ability.
from multiposenet.pytorch.
@LiMeng95 thanks very much~
Another question, I trained a resnet50 as backbone, but compared to ckpt_baseline_resnet101.h5 in your project, the inference FPS went up by only 2 frames.
Do you have training with resnet50? How fast is the result compared with resnet101?Can you provide one resnet50?
thanks
from multiposenet.pytorch.
Sorry, I didn't train with resnet50. Maybe the backbone is not the main limitation of inference FPS, other parts like person detection will also take some time.
from multiposenet.pytorch.
Related Issues (20)
- I want to know the best result of this work? HOT 4
- Questions about key point network training HOT 12
- Missing license HOT 1
- Questions about training and evaluate HOT 1
- Improvements detail HOT 2
- this the numpy==1.14.3 and pycocotools==2.0.0 is ok? i have this error! HOT 3
- multipose_environment.yaml file HOT 4
- PRN when using tester HOT 2
- Question about the baseline model HOT 20
- ImportError: lib/nms/_ext/nms/_nms.so: undefined symbol: __cudaPopCallConfiguration HOT 3
- Build the NMS extension HOT 7
- No such file or directory: '/data/COCO/COCO.json' HOT 1
- 有关intermediate supervision的问题 HOT 2
- different input size of the two subnet when training HOT 10
- why weight_decay = 0? HOT 2
- detection subnet training HOT 9
- Maybe some bugs in network?
- Original image and heatmap alignment
- Details of Baseline model
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 multiposenet.pytorch.