Comments (4)
tanjimin
commented on August 30, 2024
1
Hi @wawpaopao , did you use the processed ATAC-seq CTCF ChIP and Hi-C provided from Zenodo https://zenodo.org/record/7226561? If that is correct, you can check your loss curve, it should converge at around 0.15. The original model is trained for about a day on 4 V100s with batch size of 8. You can check your machine setup and make sure you leave sufficient time for training.
from c.origami.
wawpaopao
commented on August 30, 2024
1
I adjusted the batch_size to 32, and on a single 3090 GPU, I was able to replicate the results fairly well within about 10 epochs. Thank you.However, we can also observe that the batch size has a significant impact on the results.
from c.origami.
wawpaopao
commented on August 30, 2024
I might have some differences in training time. I trained for 60 epochs, so the total batch size would be 8 * 4, right?
from c.origami.
wawpaopao
commented on August 30, 2024
So, the total number of samples is approximately 5000. Using 4 NVIDIA RTX 3090 GPUs, it takes about 5 minutes per epoch.
from c.origami.
Related Issues (20)
- How to merge the predicted matrix and convert it back to valid pairs ？ HOT 2
- `examples/prediction.sh` generates blank Hi-C image for chromosome 15 HOT 2
- Request for evaluation code HOT 2
- Questions about performance comparison with deepC HOT 2
- About comparison with Original HiC matrix HOT 3
- The pre-trained models of other cell types HOT 1
- What method was used in the paper to convert the predictions into valid pairs? HOT 1
- Single-cell ATACseq adaptability HOT 1
- How to balance mcool files. HOT 1
- Using CTCF chip-exo without input HOT 5
- insulation score HOT 5
- How to makr trans interaction contacts prediction? HOT 5
- Adding different ChIP-seq during the training phase ？ HOT 1
- A problem in the PositionalEncoding model code HOT 3
- Independant chance of returning sequence complement HOT 4
- Training and prediction at 5kb resolution HOT 2
- Issues with Training the C.Origami Model Using Only Sequence Data and Integrating Multi-Species Data
- Issues with Training the C.Origami Model Using Only Sequence Data and Integrating Multi-Species Data HOT 4
- GRAM importance score 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 c.origami.