cure-lab / deep-active-learning Goto Github PK
View Code? Open in Web Editor NEWAn implementation of the state-of-the-art Deep Active Learning algorithms
License: BSD 2-Clause "Simplified" License
An implementation of the state-of-the-art Deep Active Learning algorithms
License: BSD 2-Clause "Simplified" License
According to the original paper:
If we can predict the loss of a data point, it becomes possible to select data points that are expected to have high losses. The selected data points would be more informative to the current model.
This implies we should be taking the maximum values from the uncertainties arg[-n:]
. Your current implementation returns the minimum arg[:n]
and so is returning the least informative points.
When we try to use pretrained model to extract features, such as "python main.py --model ResNet18 --dataset cifar10 --strategy LeastConfidence --pretrained", it returns an error: AttributeError: 'ResNet' object has no attribute 'fe'.
The reason is related to line 303 in https://github.com/cure-lab/deep-active-learning/blob/main/query_strategies/strategy.py:
e1 = self.clf.fe.encode_image(x)
Could I ask how to 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.