vlomonaco / ar1-pytorch Goto Github PK
View Code? Open in Web Editor NEWAR1* with Latent Replay, implemented in PyTorch
Home Page: https://arxiv.org/abs/1912.01100
License: Other
AR1* with Latent Replay, implemented in PyTorch
Home Page: https://arxiv.org/abs/1912.01100
License: Other
Hi @vlomonaco,
Thanks for the great algorithm and codebase!
I was about the reproduce the results of NICv2_391 by following the readme instruction.
I'd like to also run experiments of NI and NC scenarios as shown in this paper. I attempted to modify line 87 directly in ar1star_lat_replay.py
but the results (~30 to 40%) I got was worse than NICv2_391 (which I expected to be a harder case).
Could you kindly show us where else needs to be adjusted (lr or other hyperparameters) in order to make it work properly? I think I am missing something. Thanks in advance!
Fu-Jen
Dear Mr. Lomonaco,
Thank you for making the code of AR1* publicly available and re-implement it in pytorch.
I'm trying to recreate the result of Figure 4 of the paper https://arxiv.org/pdf/1912.01100.
The setting is NICv2-391 with replay buffer size 500.
I have kept all the parameter of params.cfg the same and only changed rm_rz from 1500 to 500, the result is an accuracy of 63.62%, specifically: Accuracy: 0.6362827923521566.
This is far from the reported ~70% as shown below.
Is there some parameter I should change to recreate the results from the paper?
Thank you in advance,
Best regards,
Wei
Hello,
Thanks for the code. When I tried to run it, I got this error:
"Traceback (most recent call last):
File "ar1star_lat_replay.py", line 87, in
dataset = CORE50(root='/home/admin/ssd_data/core50', scenario="nicv2_391")
File "/content/ar1-pytorch/data_loader.py", line 94, in init
with open(os.path.join(root, 'paths.pkl'), 'rb') as f:
FileNotFoundError: [Errno 2] No such file or directory: '/home/admin/ssd_data/core50/paths.pkl'
Thanks for helping me solve this issue
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.