Comments (2)
I've not done this myself so I cannot say for sure, but these are a few things that come to my mind:
- Make sure to use the same patch size as the pretrained checkpoint so you can load the entire pretrained model.
- Interpolate the pretrained position embeddings if your data is of a different resolution. In the global forecasting module we also provide a function for doing this.
- Input your latitude vector when finetuning the model since it'll be different from pretraning.
Besides this, finetuning ClimaX on your cropped data should be similar to global forecasting.
from climax.
Thank you for your kind response.
from climax.
Related Issues (20)
- Cannot access pretrained weight HOT 5
- Possible bug in lr scheduler HOT 4
- Training ClimaX without pre-training HOT 3
- Questions regarding pre-training HOT 5
- Pretrain dataset prepare and Out-of-memory problem HOT 1
- Would it be possible to kindly share the downscaling data? HOT 3
- How can I check for early stopping conditions in this code? HOT 1
- The replication issues with the downscaling task. HOT 7
- How to download the IFS data? HOT 1
- How to use trained ClimaX model for predictions? HOT 1
- What is the point of the hrs_each_step variable? HOT 1
- Required training time HOT 3
- If use Docker to build the image as introductions,the name should obey dns rules,and so the name of image must be lowercase? HOT 7
- Predict Range and hrs_each_step
- How to handle Nan values in training data? HOT 1
- How to view log files in tensorboard format? HOT 1
- acc and rmse in metrics.py might contain some errors. HOT 2
- How can I measure the performance of a fine-tuned model for a specific region? HOT 2
- About num_workers > 1 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 climax.