Comments (7)
@GranMin besides, if you use script convert_train_binary_tfrecord.py for data preprocessing, you must enforce all dir names of your N classes are strictly within interval [0,...,N-1], because dir names will be further used as labels in Softmax loss.
from arcface-tf2.
Hey..The same problem was with me then i realized that my input image size was not 112x112. when i have re-scaled them to 112x112 then Nan Values have been gone..
from arcface-tf2.
hello,My image size is 96x96, and I changed the input of the model, just as shown blow. But my loss is still nan. Do you have any idea about it?
from arcface-tf2.
@GranMin
Hi!
In a dataset.py size of input image is hardcoded in function _transform_images
. Maybe this is the reason of nans.
from arcface-tf2.
@Androsimus thankyou, I find my problem that I labeled my dataset by [1,...,N] rather than [0,...,N-1]. So I got nan. I correct it and then it runs well.
By the way, when I changed optimizer to Adam, model resnet50 sometimes achieve accuracy of 0.9, but sometimes sticks in 0.3, do you have any idea about it?
from arcface-tf2.
@GranMin if you use identical hyperparameters and datasets, then I can hardly imagine appropriate reasons.
But if you use different learning rates for example or something else, then I can try to explain this.
from arcface-tf2.
@Androsimus thanks.I had some problem with the understanding of tf.optimizers, I changed the hyperparameters as somebody said, and it works. Best wishes!
from arcface-tf2.
Related Issues (20)
- Can anyone explain why model loading fails when I try 'archead' while it works with 'normhead' during custom training with16 classes HOT 2
- How to get the classification result?
- get nan result for a whole batch HOT 1
- How can i apply augmentation
- How can I still get loss=nan
- 您好,我想請教一下tfrecord中輸入是image的資訊,那label是原始的image的id嗎?
- Accuracy difference from insightface mxnet implementation
- Fine-tunning ArcFace
- Asking test.py
- [BUG] lost GlobalAveragePooling
- I can't achieve the accuracy in bench mark, could somebody help? HOT 18
- Issues with perform_val HOT 2
- Colab notebook does not work HOT 1
- Colab notebook does not work(for downloading arc_res50.zip file) HOT 1
- good performance is not obtained HOT 1
- Asian-celeb dataset download link
- Cosine Similarity, Best Threshold
- my desktop use two gpu. occurred error that 'Memory growth cannot differ between GPU devices' HOT 1
- Load arc_res50 pretained model with tensorflow keras load_model HOT 1
- Cannot find ckpt from None HOT 1
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 arcface-tf2.