Comments (1)
Hi @FranciscoPark ,
I realize it's not completley obvious (especially since we support **kwargs
), but these model builders functions like models.swin_b
are meant to implement a very specific architecture and not all parameters are allowed. For swin_b
, stochastic_depth_prob
is hard-coded to 0.5 and it should not be modified.
Since you're not using pre-trained weights anyway, I suggest that you instanciate a model directly from the SwinTransformer
base class instead:
vision/torchvision/models/swin_transformer.py
Line 508 in f96c42f
You might have to hard-code a few of the swin_b parameters yourself, you can look at the code to figure out the values. HTH.
from vision.
Related Issues (20)
- Improve empty import time of torchvision HOT 2
- MD5 checksum of the download file ./data/celeba/img_align_celeba.zip does not match HOT 2
- celebA dataset issue with downloading HOT 1
- `fasterrcnn_resnet50_fpn` edits weights on-the-fly
- Can we add datatype support for examples under references HOT 2
- Add support for recentering for RandomAffine and RandomPerspective transformations
- Typo on documentation example HOT 1
- [Documentation] Improve Clarity on `torchvision.io.write_video` options HOT 1
- Obscure error messages using VideoReader when PyAV version too old/not installed HOT 1
- Add 3-augment from DeiT III HOT 3
- How to write your own v2 transforms example does not work HOT 2
- V2 transforms tests failing due to pickle FutureWarning (coming from torch.load)
- torchvision.ops.focal_loss missing a -1 HOT 2
- transforms.v2.Normalize() does not work as expected for multiple inputs HOT 1
- Feature Request: Support for `Path` objects in `torchvision.datasets.ImageFolder` HOT 1
- Windows unittest jobs fail due to numpy 2 dependency issue
- ONNXRuntimeError for fasterrcnn_mobilenet_v3_large_fpn
- ColorJitter results with OverflowError HOT 5
- scipy.ndimage.find_objects GPU implementation
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 vision.