Comments (13)
@twmht I randomly crop image(0.3~1) and scale image to the fixed scale which has the similar effect with multiscale training.
from pytorch_retinaface.
@TIAN-Xiao did you try to use group norm instead batchnorm or freezing batchnorm after pretrain on ImageNet? It's common practice
from pytorch_retinaface.
Network is easy to shake due to small batch size.
from pytorch_retinaface.
Network is easy to shake due to small batch size.
So, if I wanna reproduce the same AP, I have to have GPUs with large memories so that big batch_size can be used. is it right?
from pytorch_retinaface.
Yes......
from pytorch_retinaface.
@biubug6 Could you share the traning log of mobilenet0.25? When i use this repo to reproduce the result, the batch_size in my config is 512, but i get a lower result:
Easy Val AP: 0.74
Medium Val AP: 0.60
Hard Val AP: 0.29
from pytorch_retinaface.
Original batch_size is 32. You increased it 16 times but number of iteration was decreased 16 times. It's bad. If you increase batch size 16 times you should increase learning rate 16 times for fix this problem.
from pytorch_retinaface.
@rydenisbak yeah, i also increased the learning rate to 0.015(~16 times), but the performance is bad.
from pytorch_retinaface.
Why don't you use multiscale training?
from pytorch_retinaface.
@felixfuu anyway final learning rate maybe too high, try cosine lr schedule
https://pytorch.org/docs/stable/optim.html#torch.optim.lr_scheduler.CosineAnnealingLR
from pytorch_retinaface.
@biubug6 After training for 50 times, the learning rate remains the same. What's the matter?
from pytorch_retinaface.
@twmht我随机裁剪图像(0.3~1)并将图像缩放到与多尺度训练具有相似效果的固定尺度。
The wider validation set enables the input to be fixed with the same shape of the input and the mAP is not low. Because the wider validation set of true labels makes pictures of different sizes
from pytorch_retinaface.
The batch_size is important, and it will influence the learning rate. when you increase batch_size, lr should also increase, reverse is same.
from pytorch_retinaface.
Related Issues (20)
- Is it ok if we upload your models to Zenodo and distribute them?
- Fine-tuning Resnet 50 model
- Unable to find a compatible Visual Studio installation
- How to fit non-squared input?
- The form of bboxes is wrong!!!
- Mesh decoder HOT 1
- About the ratioHard Example Mining HOT 3
- Why can't we evaluate during the training? HOT 1
- Pretrained Model HOT 1
- [Refactor] Acclerate training based on MMEngine :rocket:
- How to train with custom dataset by using the pretrained model?
- Dataset
- Evaluation 评估失败,在widerface的三个子集上map值都为0 HOT 1
- What maximum FPS have you achieved?
- Why does the forward pass time become shorter with iterations?
- Why loop 100 times while testing begin in detect.py?
- 用celeba数据集训练的模型,摄像头测试时小脸的框会变大框不准 HOT 1
- How can I train using pth pretrained file? (For transfer learning)
- 用预训练的权重直接训练,为什么loss会这么高
- C++ and TensorRT implementation of yolov5face yolov7face yolov8face
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 pytorch_retinaface.