Comments (1)
Wasnt able to reproduce with Modulus on my machine:
>>> import modulus
>>> modulus.__version__
'0.5.0'
>>> from modulus.models.afno import AFNO
>>> model = AFNO.from_checkpoint("fcn.mdlus")
>>> model
AFNO(
(patch_embed): PatchEmbed(
(proj): Conv2d(26, 768, kernel_size=(8, 8), stride=(8, 8))
)
(pos_drop): Dropout(p=0.0, inplace=False)
(blocks): ModuleList(
(0-11): 12 x Block(
(norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(filter): AFNO2DLayer()
(norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(mlp): AFNOMlp(
(fc1): Linear(in_features=768, out_features=3072, bias=True)
(act): GELU(approximate='none')
(fc2): Linear(in_features=3072, out_features=768, bias=True)
(drop): Dropout(p=0.0, inplace=False)
)
)
)
(head): Linear(in_features=768, out_features=1664, bias=False)
)
>>>
Could it be you have an old AFNO checkpoint in a model registry? I updated to a new version (auto download should pull this one) after a small API change occurred in Modulus. The v0.2 model has the fix for the error you're seeing I believe.
This got updated I think in 0.4.0 of modulus, interesting its just showing up now.
from earth2mip.
Related Issues (20)
- 🐛[BUG]: Graphcast Operational Input/Output Channel Mismatch HOT 5
- Earth-2 MIP Data flow HOT 2
- Cleanup earth2mip/lagged_ensembles/__main__.py HOT 1
- Utilities for distributed management of ensembles HOT 1
- 🚀[FEA]: Improving Diagnostic Implementations
- 🐛[BUG]: Inconsistency in Model Inferences with Modified Initial Conditions and Execution Date in 04_diagnostic_models Example HOT 3
- 🐛[BUG]: Running inference_ensemble with multiple ensemble members per rank causes perturbations to be applied multiple times HOT 1
- 🚀[FEA]: make pure python function for earth2mip.time_collection
- Need to clarify provenance of e2mip models
- 🚀[FEA]: Improve deterministic inference UX HOT 1
- 🐛[BUG]: ensemble perturbation_strategy: "spherical_grf"
- 🐛[BUG]: time averaging loses the time coordinate informations
- 🐛[BUG]: Download API issues HOT 1
- 🐛[BUG]: Not able to load models on CPU HOT 1
- 🐛[BUG]: Chunking feature of open_forecasts is not available HOT 2
- 🐛[BUG][Feature Request]: Perturbing channels that are not included in `earth2mip/_channel_stds.py` HOT 1
- upgrade to pydantic 2.0
- 🐛[BUG]: Using output_grid different than model grid results in an error HOT 2
- 🚀[FEA]: Running on Multi GPU A100 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 earth2mip.