Comments (10)
ok, cool! Please do not merge pull request directly into the master! Let me do that to make sure everything is in order! :-)
from avalanche.
will do it this weekend
from avalanche.
@ffeng1996 you can start by adding openloris as a pytorch dataset in avalanche/benchmarks/datasets
.
You can take a look at how core50 is implemented there to have an idea.
from avalanche.
WIP PR #223 merged. It seems the validation.zip file is downloaded instead of the train. A this point it is better to let the user download it manually to remove any confusion.
@ffeng1996 can you please start creating the "continual" data loader? You can take inspiration from the CORe50 one here: avalanche\benchmarks\classic\core50.py. Thanks!
from avalanche.
WIP PR #223 merged. It seems the validation.zip file is download instead of the train. A this point it is better to let the user download it manually to remove any confusion.
@ffeng1996 can you please start creating the "continual" data loader? You can take inspiration from the CORe50 one here: avalanche\benchmarks\classic\core50.py. Thanks!
OK. I will write down some comments to let the user download the datasets manually and finish the continual setting. Thanks for taking the time.
from avalanche.
Hi @ffeng1996, I've already fixed it here: vlomonaco@a07ae71
You can implement directly the new module for the two continual learning benchmarks based on openloris (IROS & ICRA versions)!
from avalanche.
Hi @ffeng1996, I've already fixed it here: a07ae71
You can implement directly the new module for the two continual learning benchmarks based on openloris (IROS & ICRA versions)!
Got it. Many thanks for your help!
from avalanche.
I have submitted the continual data generator for openloris (https://github.com/vlomonaco/avalanche/pull/229). Many thanks for the continuous support and help.
from avalanche.
Thanks @ffeng1996 I've merged it in vlomonaco@67c68f6.
This looks good but we should support both the IROS and ICRA version I believe! Can you adapt the OpenLoris
and OPENLORIS_DATA
classes so that the user is able to choose which version to use? Thanks!
from avalanche.
Thanks @ffeng1996 I've merged it in 67c68f6.
This looks good but we should support both the IROS and ICRA version I believe! Can you adapt the
OpenLoris
andOPENLORIS_DATA
classes so that the user is able to choose which version to use? Thanks!
Sure. I added the IROS benchmark together with the updated bacth_fileliss
in #230. Thanks a lot!
from avalanche.
Related Issues (20)
- Can I use my own dataset? HOT 1
- test dataset path broken HOT 2
- Checkpoint error in AGEM
- tutorial missing docs HOT 2
- Cannot catch last subexp (Affects Online settings with access to task boundaries) HOT 5
- Issue with cpu_usage metric HOT 2
- ConcatDatasets HOT 1
- forgetting_metrics is 0 with filelist_benchmark
- I can use the CPU version of the torch normally, but after installing the gpu version of the torch, I get this error: TypeError: BaseSGDTemplate.__init__() missing 2 required positional arguments: 'model' and 'optimizer'
- Avalanche unable to use cuda device. HOT 3
- make_train_dataloader discards custom collate function passed as kwarg HOT 4
- Split Cub200 into more the five experiences.
- Question about Multi-Class Classification Continual Learning in Avalanche
- Help to handle with miniImageNet HOT 1
- support python 3.11 HOT 1
- Trouble with ni_benchmark
- Trouble with `dataset_benchmark` and `tensors_benchmark`. Continual Learning plugins do not work.
- How to use Packnet model
- Multi task fails on existing module wrappers HOT 2
- Code from Avalanche Tutorial doesn't work 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 avalanche.