Comments (10)
@michaelgsharp my best guess is there's overflow when calculating focal loss?
from machinelearning.
Is there a solution or suggestion? please
from machinelearning.
@Cilouche which coco dataset are you using, could you share a link?
from machinelearning.
data : https://drive.google.com/drive/folders/1-dQPRdQ-MRp6mrPhnpng5pcgJsTZMg23 ,
I used this site https://drive.google.com/drive/folders/1-dQPRdQ-MRp6mrPhnpng5pcgJsTZMg23 to convert them to coco format
from machinelearning.
@Cilouche which site? The site link seems to be the same with the data you share
from machinelearning.
Yes sorry the site :
https://roboflow.com/convert/pascal-voc-xml-to-coco-json?ref=blog.roboflow.com
I've also noticed that once the database is large, there's a loss Nan
example:
data = 100, epoch=8; all is well except for the precesion is low ~ 0.69
but from data ~= 1200 images, epoch= 5, 8 , 11 ; losses converge rapidly towards Nan
from machinelearning.
Update
I got it reproduced on my second training, thanks
Origianl post
Hey @Cilouche some updates here: I can't reproduce the NaN loss error using your dataset in the latest model builder main branch. Maybe it's already been fixed.
We haven't released model builder yet, but you can verify the latest bit in mlnet cli > 16.18.2 by installing mlnet-win-x64
and try object detection there. mlnet cli and model builder shares the same AutoML service so if you didn't see NaN error from mlnet cli, then you probably also won't see NaN error from model builder
steps to verify
- install the latest mlnet-win-x64 (https://www.nuget.org/packages/mlnet-win-x64)
- start object detection there
mlnet object-detection --dataset /path/to/coco.json --device cuda --epoch 1
from machinelearning.
Any suggestion or solution to bypass this problem, please ?
Thanks
from machinelearning.
Try a smaller batch size, Maybe 1?
And GPU training doesn't produce NaN loss, is that also an option for you(training on GPU)
from machinelearning.
It's works on GPU thanks.
from machinelearning.
Related Issues (20)
- ML.NET can't add Evaluate logic into pipeline HOT 1
- How to predict text type based on input text? HOT 1
- Accessing data by column after adding columns to a DataFrame returns error data
- Specify Categorical Features in LightGBM
- Get Loss During Training for Visualization (Learning Curve Graph)
- Allow developers to supply their own function to infer column data types from data while loading CSVs
- [Tokenizers] Question regarding performance
- Tokenizers Library Design HOT 7
- Dll version of Microsoft.ML.OnnxRuntime.dll is 0.0.0.0
- Modify IDataView in AutoML Experiment After Transform and Before Evaluate
- Is it possible to use ML.NET for image processing (such as remove background)?
- DataFrame.LoadCsv() Could not load file or assembly 'System.Runtime.CompilerServices.Unsafe, Version=4.0.4.1'
- Schema mismatch for label column ': expected Boolean, got Single
- Still no o200k_base support HOT 4
- Support special tokens in sentence piece bpe
- Special Tokens handling seems to be incorrect (at least in my scenario where I'm creating Command R+ tiktoken file from specification)
- Running AI inference of phi3 and other llms from c# using NPU + GPU in comming processors? HOT 2
- Loading a LSTM Model Created in Torchsharp in ML.Net
- Model builder training appears to leak data somehow into the training set HOT 1
- When training with AutoML, I encounter a Win32Exception: The wait operation timed out after 30 seconds. HOT 2
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 machinelearning.