Comments (2)
Implement an Inferencer
class similar to Trainer
class.
Two ways to go about it:
- Each project has separate script for inference where it uses the
Inferencer
but also defines how to load data and save generated output or; - Each project has a test-time dataloader defined which could be taken by the
Inferencer
as it is done inTrainer
andtrain.py
. The test-time dataloader will load the data for inference without the extras that are used during the training (no need for two domains, no need for patch sampling etc.) and will have to have a method for storing the outputs.
from ganslate.
Went for the option 2, implemented as of dab669
, some details left to be done, e.g. the sliding window inference's arguments should be passed in the inference conf
from ganslate.
Related Issues (20)
- Windowed images not displayed correctly in tensorboard
- Switch to monai's `decollate_batch`
- Functionality documentation: Is the core functionality of the software documented to a satisfactory level (e.g., API method documentation)? HOT 1
- Add more functionality tests: HOT 1
- make default imagedataset have different behavior for train vs val/test modes HOT 4
- metrics calculation not working for batch_size > 1
- Better logging names for losses, metric, G and D, and visuals
- metrics all over the place in GAN implementations HOT 1
- Val-Test metrics need to work accurately across batches and across data points HOT 4
- Add warning for when dataset size is smaller than number of processes in DDP * batch size HOT 1
- PatchGAN output channels set equal to in_channels? Change it to 1 HOT 10
- Figure out logging for multimodal images
- Make CycleGAN's separate channel config cleaner and more readable
- Document + support framework for fine-tuning on a different dataset HOT 2
- Out channels missing in PatchGAN 3D HOT 1
- Volumetric probability map based PatchSampler HOT 5
- Add structure-constrained GANs to the list of available GANs
- separate out medical utils
- CLI tab autocompletion not working
- Restructure docs to separate package overview from tutorials
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 ganslate.