Comments (7)
Hey @ExcellentHH thanks for flagging this :) will get on it asap. Is there a particular upsampling mode you need ? (Default is "nearest").
Thank you for your prompt response. In fact, this issue arose when I was trying to validate the upsampling operation in the U-Net structure. As mentioned in the URL, "In transposed convolutions we have weights that we learn through back-propagation. In papers I’ve come across all of these upsampling methods for various cases and also in practice you may change your architecture and try all of them to see which works best for your own problem. I personally prefer transposed convolutions since we have more control over it but you may go for bilinear interpolation or nearest neighbor for simplicity as well."
I understand that there are different ways to implement upsampling operation, and I would be grateful if EZKL could support torch.nn.ConvTranspose2d and as many modes (bilinear, nearest, etc.) as possible for torch.nn.Upsample. I believe that this will greatly expand EZKL's application range, and thanks for the hard work.
Please let me know if there is anything I can do to assist with this feature, and I look forward to hearing back from you soon.
from ezkl.
Hey @ExcellentHH rolling out ConvTranspose2D in #263 . Also added your example above as a unit test :)
Thank you for your hard work on developing the new feature. I am eagerly looking forward to testing it as soon as possible!
Once again, I would like to express my sincere thanks for your response and support. Please let me know if there is anything I can do to assist with testing or providing feedback on the new feature. Furthermore, I hope that the EZKL project will continue to flourish and grow.
from ezkl.
Hey @ExcellentHH thanks for flagging this :) will get on it asap. Is there a particular upsampling mode you need ? (Default is "nearest").
from ezkl.
@ExcellentHH I've kicked off work for ConvTranspose2D / Deconv op :) stay tuned
from ezkl.
Hey @ExcellentHH rolling out ConvTranspose2D in #263 . Also added your example above as a unit test :)
from ezkl.
Hey @ExcellentHH #264 implements nearest neighbours upsampling ! hope that helps
from ezkl.
Hey @ExcellentHH #264 implements nearest neighbours upsampling ! hope that helps
Thanks a lot, I'll update my local version to use the new features. Thank you very much for your hard work again!
from ezkl.
Related Issues (20)
- GPTNeoXForCausalLM models shape issue HOT 3
- Install from source fails HOT 2
- `--srs-path` argument missing from docs HOT 3
- Model table fails to print / failure parsing the model HOT 4
- `DimError` when generating the circuit settings HOT 4
- `ezkl` python bindings do not provide `__version__` attribute
- Numerical accuracy report table not being shown in Jupyter environments after calibration HOT 2
- Setup fails with invalid value HOT 6
- do you have benchmark tutorial for with EZKL and without EZKL? HOT 2
- PanicException: the value of ``extended_k`` is bigger than the size of the field ``S`` after calibrating settings HOT 4
- How to use nanoGPT? HOT 1
- Error on integration of ezkl with huggingface pretrained models HOT 1
- deploy evm verifier error HOT 1
- error with 'create-evm-verifier' HOT 2
- Can't generate witness in the `mnist_classifier.ipynb` HOT 1
- Excessive RAM Usage during setup step HOT 1
- Can't setup gen_settings for NCF model HOT 2
- Splitting proof error
- ARM support HOT 6
- Failed to generate settings when using ONNX converted from keras 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 ezkl.