Comments (2)
You have a function called '_build_transform' in class common, and inside the function there is only one line which is return 'build_transform'. After I jump tp that page, there are only one function in this file, and I can see you only call this function once, so why you just put the code inside the '_build_transform '.
from vedaseg.
Why make the code so complicated? I just want to see how you use transforms to augment the image. From the dataset file, I jumped 6 pages and haven't seen the final code so far. . . . .
Hi,
Thanks for your interest in our Vedaseg.
Our design makes it easier to develop and use in our sense.
You should look at transformes instead of dataset
.
FYI, we are building transforms based on albumentations
For the '_build_transform' part you mentioned, you are trapped in our mechanism design
. Those designs makes it easier for customization
based on your own needs. With those 'extra codes', you can define your experiments by only change the config file instead of changing actual code. You will see it when you see the whole picture.
from vedaseg.
Related Issues (20)
- ImportError: cannot import name 'weak_module' HOT 4
- Add COCO format support HOT 1
- Example to output predict result HOT 2
- multi gpu training HOT 1
- Implementation Error of ResNet BasicBlock HOT 1
- Bad mIoU when using many GPUs HOT 2
- Any support for Resnet50 backbone? HOT 2
- How to save prediction label as binary mask one by one? HOT 4
- AssertionError: Default process group is not initialized HOT 2
- Benchmark on COCO Dataset HOT 3
- AssertionError: Default process group is not initialized HOT 2
- Windows HOT 1
- Validating Problem HOT 1
- AttributeError: 'SyncBatchNorm' object has no attribute '_specify_ddp_gpu_num' HOT 3
- How to train with custom dataset?
- AttributeError: module 'albumentations.augmentations.functional' has no attribute 'scale' HOT 3
- RuntimeError: Default process group has not been initialized, please make sure to call init_process_group. HOT 1
- Suggest to loosen the dependency on albumentations
- can't download the backbone checkpoints in macOS 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 vedaseg.