Comments (13)
Hi, @HsuTzuJen
Any progress on implementation mobile-facenet on TF? I am doing the same thing, however got bad result so far. There is some referneces on this repo, hope that will help you.
from insightface_tf.
@ruobop
I just used the same settings as the paper, but I got this:
C:\ProgramData\Anaconda3\lib\site-packages\numpy\core_methods.py:70: RuntimeWarning: overflow encountered in reduce
ret = umr_sum(arr, axis, dtype, out, keepdims)
total_step 1520, total loss gpu 1 is nan , inference loss gpu 1 is nan, weight deacy loss gpu 1 is nan, total loss gpu 2 is nan , inference loss gpu 2 is nan, weight deacy loss gpu 2 is nan, training accuracy is 0.000000, time 368.072 samples/sec
But it is working when I use small batch size(64) and small lr(0.0005), I do not know why.
from insightface_tf.
I also encounter this problem about when lr>0.05,after a moment the total loss is nan,so i use the learning rate start at 0.02,i don't know why?can you solve it?
At the moment, the best accuracy i can achieve is Accuracy-Flip: 0.98150+-0.00545.
my batch size is 128
from insightface_tf.
@billtiger The best acc I achieved is 0.9875 with batch size 64 at step 348000.
I think that maybe we should change the lr step.
from insightface_tf.
@HsuTzuJen thank you for your reply!
but I think the learning rate can't be set at 0.1 is abnormal,and this will result low accuracy!
from insightface_tf.
@HsuTzuJen how about the prelu and leaky_relu influence the accuracy?
i find the the original paper authors are use PReLU,and you and me are all used leaky_relu,
and i don't find PReLU api in tensorflow tf.nn module.so i use the tf.nn.leaky_relu,
the insightface author are use PReLU in the mobilefacenet.py:
body = mx.sym.LeakyReLU(data = data, act_type='prelu', name = name)
have you ever try PReLU?hope you reply!thanks!
from insightface_tf.
@billtiger As I know, prelu is leaky relu.
from insightface_tf.
@billtiger You can try:
bn = tl.layers.InputLayer(bn)
act = tl.layers.PReluLayer(bn, name='%s%s_Prelu' %(name, suffix))
return act.outputs
Leaky_relu is a Prelu with a stable alpha(not trainable), but the alpha is trainable in Prelu.
from insightface_tf.
why learning rate is so small as train.py set 0.01, something wrong?
from insightface_tf.
Hello,
Any progress? Do you know where I can find the pretrained model for mobilefacenet?
Thanks!
from insightface_tf.
Could you tell me about your model's learning rate and How much steps you can arrival the 99+ accuracy for your model? please! @HsuTzuJen
from insightface_tf.
@HsuTzuJen do you use weight decay for mobilenet? and what lr step did you use ,thx
from insightface_tf.
@406747925 Please check on "https://github.com/HsuTzuJen/Face_Recognition_Practice_with_TF"
I have uploaded the codes that I am using.
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.