arantxacasanova / ralis Goto Github PK
View Code? Open in Web Editor NEWCode for the paper "Reinforced Active Learning for Image Segmentation"
Code for the paper "Reinforced Active Learning for Image Segmentation"
I have installed all the dependencies and also downloaded the pretrained model but now I am not able to run code.Could you please let me know in what order files should be executed?Like what should be flow of file executions?
Could you give a ballpark on how long the training took and what kind of hardware you used? I ran the baseline shell script for CAMVID only with 2 GPUs and timed out after 24 hours, and I was curious how long to try running it.
in the run.py
there is no code for the entropy condition
Hi! I am currently working in a similar field and I'm really excited to find this project.
I find I cannot run the code probably due to these two variables:
ralis/scripts/launch_train_ralis.sh
Lines 3 to 4 in 83325f3
I have tried replacing the following code into the path of the model you provided in google drive, it seems not working.
ckpt_path='/home/casanova/scratch/ckpt_seg'
Also, could you briefly introduce how data_path
works in the project? It seems that the python file does not use this argument.
hello could you tell the details of unzipping the file from the gui on my linux vm cause i still couldnot get the pth files by gunzip command on my linux machine (ubuntu os)
To download the trained RALIS models for Camvid and Cityscapes (as well as the pretrained segmentation model on GTA and D_T subsets): https://drive.google.com/file/d/13C4e0bWw6SEjTAD7JdAfLGVz7p7Veeb9/view?usp=sharing
Hello! I'm having trouble extracting the files for the pretrained models. I can download the ralis_models.gz file, but when I unzip it, there is only a file called ralis_models with no extensions. Are you able to download it, gunzip ralis_models.gz, and get the correct folder out?
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.