Comments (7)
Hey @MarkAlive
Can I confirm you used dna_r9.4.1.toml, not quartznet5x5.toml?
from bonito.
@iiSeymour I used quartznet5x5.toml. Will the new model be faster or higer acc?
from bonito.
Actually, lr set as 2e-3 can get a better result in 8GPUs situation. But when I extend to 64GPUs. It is easy to fall into divergence problem, while lower lr can't reach the baseline acc.
from bonito.
Yes, the newer model will coverage faster and reach higher accuracies.
from bonito.
Thanks for the quick reply.
I coverted the hdf5 file to npy format with the defaut args in config.toml and finally got 851972 chunks of data. Does the model trained with this size of data?
from bonito.
Yes you will want to train will all the chunks, one of the filters --min-run
has a default of 5, setting this to 1 will results in more chunks being generated.
from bonito.
Thanks, I will try it.
from bonito.
Related Issues (20)
- Bonito Train missing dataset.py HOT 5
- RNA002 model
- RNA004 Does not output any CTC data HOT 3
- bonito basecaller max_reads HOT 1
- Bonito export for dorado error HOT 6
- Feature request: export the list of reads used to train a model
- bonito WASM
- Training data for R10.4, 4 and 5kHz? HOT 3
- Chunks.npy and Dataset.py not being generated HOT 2
- how to best fine tune a model with different references HOT 12
- Applying INT8 quantization, just like in Dorado HOT 2
- How can I set the `gpu_memory_utilization` ?
- bonito duplex runs out of memory HOT 1
- [Errno 2] No such file or directory: '/data/training/ctc-data/dataset.py' HOT 2
- how to choose the model? HOT 1
- Exporting a model - which weights does it use? HOT 2
- Is it possible to use a Bonito trained or fine-tuned model with dorado duplex basecalling.
- Training Data Used for Pre-made models
- Retrieving every paths examined in beam search module
- undefined symbol: cublasGemmEx
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 bonito.