Comments (13)
Based on my training, it is hard to converge loss to a small number if train with m=0.5. My solution is that train with m =0 at the beginning and then increase m to 0.1, 0.2, 0.4, 0.5. It works well and the loss goes from 6 to 0.3 in my database.
from insightface_tf.
可以先使用softmax进行预训练,之后使用arcface进行fine tune
在原作者的issue中有过相关讨论
https://github.com/deepinsight/insightface/issues/214
from insightface_tf.
@ltcs11 为什么使用arcface训练时一直显示Accuracy为0,
谢谢
from insightface_tf.
@Joll123
你是直接使用softmax预训练之后再接arcface fine tune吗?
如果是,可以在继续训练一段时间,或增大batch_size
from insightface_tf.
不用softmax预训练应该也能收敛,只是效果不好。我那个不收敛是因为minibatch太小只有128,学习率又太大导致。减小学习率就能收敛了
from insightface_tf.
@dl8207531 你取的学习率多大
from insightface_tf.
@dl8207531 老兄用哪个数据集训练的, margin多少?训练的模型在lfw的准确率能达到多少呢?
from insightface_tf.
@Joll123 用softmax预训练可以从0.01开始 如果想测试直接mobilefacenet训练可以试下也从0.01开始,如果不行就0.001肯定能收敛
from insightface_tf.
@jetsmith 就InsightFace提供的那个数据集 margin 0.5 mobilefacenet 准确率99.367% 达不到作者baseline 我猜原因应该是minibatch太小
from insightface_tf.
@dl8207531 那你用softmax预训练训到什么程度转arcface训练呢, 你arcface学习率的schedule是如何设置的呢?
from insightface_tf.
@jetsmith softmax从0.01开始训练到不再收敛保持该学习率改用arc,arc同样训练到不再收敛学习率乘0.1继续训练
from insightface_tf.
@dl8207531 您好,请问 你后面改用arc时是全部参数训练,还是冻结了卷积层呢?
from insightface_tf.
and then increase m to 0.1, 0.2, 0.4, 0.5.
How about the frequent of increasing m?
- Epoch [0-10] m is 0, [10-20] m is 0.1, ... epoch [40-50] m is 0.5. If I do this, my losses will increase after the adjustment.
- or epoch 1 m is 0, epoch 2 m is 0.01, ..., epoch 50 m is 0.5 ?
And lr gradually decay or remain constant at a small value?
from insightface_tf.
Related Issues (20)
- About the accuracy computation(关于计算准确率的问题) HOT 1
- the number of samples is not 5.8M
- resnet_v1_50/block1/unit_1/bottleneck_v1/shortcut_bn/BatchNorm/beta
- stom
- could I get the 512-D face embedding features ?
- pre trained models HOT 2
- How can I directly test the LFW data set with an existing model to get accuracy?Which folder is the model in?
- Embeddings model d
- In what format does the labels should be
- How to download pretrain ?
- Thank you for your code,could you tell why I feed input with shape(n,112,112,3),but just get the embedding with shape(1,512) HOT 1
- Performance issues in your project (by P3) HOT 1
- Performance issues in train_nets.py(P2)
- from models import base_server NOT IMPORTING
- center parallel strategy
- any instruction how to start?
- Share model please,,..
- Did you try a lighter base such as MobileFaceNet?
- compared with facenet HOT 2
- How to solve the problem of "summary" errors during training?
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 insightface_tf.