h3lio5 / episodic-lifelong-learning Goto Github PK
View Code? Open in Web Editor NEWImplementation of "Episodic Memory in Lifelong Language Learning"(NeurIPS 2019) in Pytorch
License: MIT License
Implementation of "Episodic Memory in Lifelong Language Learning"(NeurIPS 2019) in Pytorch
License: MIT License
Hi,
I am running this work and I found a couple of minor mistakes (that was taken care of) and a major issue with the sampling process. While sampling the dictionary data structure, what should be the output?
Line 93 of the main.py
content, attn_masks, labels = memory.sample(sample_size=64)
I sampled from the dictionary items and I am getting 4 tuples as output while expected output should be: content, attn_mask, label.
Let me know if my sampling procedure matches the desired one. I am neglecting the fourth tuple altogether.
Thanks!
Hi,
I am trying to run this model. While at the Training stage, I received the following error:
usage: main.py [-h] [--batch_size BATCH_SIZE] [--mode MODE] [--order ORDER] [--epochs EPOCHS] [--model_path MODEL_PATH] [--memory_path MEMORY_PATH] main.py: error: argument --epochs: invalid int value: 'any_number'
I am wondering if anyone has the same issue like this. Or, any thoughts?
Thank you!
Hi,
I am trying to run this model. While at the inference stage, I received the following AttributeError:
Traceback (most recent call last):
File "main.py", line 273, in <module>
model = MbPAplusplus(model_state=model_state)
File "/home/sandstone/code/continual_learning/replay_baselines/episodic-lifelong-learning-master/models/MbPAplusplus.py", line 118, in __init__
self.base_weights = self.classifier.parameters().clone().detach().to("cuda" if torch.cuda.is_available() else "cpu")
AttributeError: 'generator' object has no attribute 'clone'
I am wondering if anyone has the same issue like this. Or, any thoughts?
Thank you!
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.