Comments (6)
Might have figured it out myself, dimension should be multiples of 32.
from segmentation_models.pytorch.
@psinger I have also noticed that when training Unet ... Do you know why ? Is it specific to Unet or is it the same with other architecture ?
from segmentation_models.pytorch.
@qubvel this question comes over an over, any idea if a better error message could be thrown? Or could we pad them to avoid this?
@julienguegan images needs to be a multiple of 2^depth because they will go through subsampling depth
times (with rounding), before being up-sampled and concatenated in the skip connections.
In the example above :
525 ---------------> 544
\ /
263 -----------> 272
\ /
132 -------> 136
\ /
66 -----> 68
\ /
33 -> 34 !
\ /
17
You can see the concatenation will fail Sizes of tensors must match except in dimension 1. Got 33 and 34 in dimension 3
from segmentation_models.pytorch.
It is possible to add abstract _check_input
method for SegmentationModel and implement it for different models
from segmentation_models.pytorch.
Or change unet upsampling, instead of factor specify shape for interpolation
from segmentation_models.pytorch.
Such kind of upsamplig have been chosen to simplify conversion between different frameworks, not sure that all of them support shape upsampling
from segmentation_models.pytorch.
Related Issues (20)
- Adding FeatUp HOT 1
- get_preprocessing_fn HOT 2
- SSL: CERTIFICATE_VERIFY_FAILED error HOT 1
- 'DeepLabV3Plus' object has no attribute 'save_pretrained' HOT 12
- How to specify class weights for loss function? HOT 1
- the method of adding new networks HOT 4
- No problems with all losses, except JaccardLoss HOT 8
- I can't run "cars segmentation (camvid).ipynb" example HOT 2
- DiceLoss when multiclass mode throwing an assertion error HOT 6
- How to implement model parallelism using PyTorch on an HPC environment? HOT 16
- multiple object task HOT 1
- Can't load saved model after training HOT 3
- Dice Loss resulting in unexpected logit outputs HOT 2
- How can I get the final evaluation metrics HOT 1
- how to calculate the number of parameters and computational complexity for each model HOT 1
- Using multi GPUs HOT 1
- Segmentation fault (core dumped) HOT 3
- add other new models HOT 3
- add UperNet model HOT 7
- Guidance required to add CBAM Module 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 segmentation_models.pytorch.