Day: October 13, 2021

App

An alternative site to emplea.do due to inconsistent service of the app

a agile and fast alternative to emplea.do Settings Moved to settings. Basic Commands Setting Up Your Users To create a normal user account, just go to Sign Up and fill out the form. Once you submit it, you’ll see a “Verify Your E-mail Address” page. Go to your console to see a simulated email verification message. Copy the link into your browser. Now the user’s email should be verified and ready to go. To create an superuser account, use this […]

Read more
Simulation

Network Dynaimcs Simulation For Python

A Final Year Project in CUHK, Autumn 2021 Files param.h edit all the variables & settings here simulate.c the main program to run the network dynaimcs How to use edit variables in param.h place param.h and simulate.c in the same folder compile simulate.c wait for results Output export up to 4 files OUT_SPIK stores all the spiking data column 1: index of nodes, starting from 1 column 2: number of spikes of the corresponding node remining columns: time-stamps of each […]

Read more
Generator

A benchmark for concept generalization

Code repository for the ImageNet-CoG Benchmark introduced in the paper “Concept Generalization in Visual Representation Learning” (ICCV 2021). It contains code for reproducing all the experiments reported in the paper, as well as instructions on how to evaluate any custom model on the ImageNet-CoG Benchmark. @InProceedings{sariyildiz2021conceptgeneralization, title={Concept Generalization in Visual Representation Learning}, author={Sariyildiz, Mert Bulent and Kalantidis, Yannis and Larlus, Diane and Alahari, Karteek}, booktitle={International Conference on Computer Vision}, year={2021} } Contents of the Readme file: Installation We developed the […]

Read more
Research

The Easy-to-use Dialogue Response Selection Toolkit for Researchers

Our released data can be found at this link. Make sure the following steps are adopted to use our codes. How to Use Init the repo Before using the repo, please run the following command to init: # create the necessay folders python init.py # prepare the environment # if some package cannot be installed, just google and install it from other ways pip install -r requirements.txt train the model

Read more
Command-line Tools

Straight-forward command line interfacing with GPT-3

Straight-forward command line interfacing with GPT-3. Finding yourself stuck at a conceptual stage? Spinning your wheels needlessly on a segment of text and staring into a cyclic void? Alter the prompt within interact.py and run the code as many times as you wish. Generate interesting permutations and harvest ideas. Get unblocked. . . . OpenAI API key required Demo Vid: GV_v.mov GitHub View Github    

Read more
Segmentation

Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation

The implementation of Reducing Infromation Bottleneck for Weakly Supervised Semantic Segmentation, Jungbeom Lee, Jooyoung Choi, Jisoo Mok, and Sungroh Yoon, NeurIPS 2021. [[paper]] Abstract Weakly supervised semantic segmentation produces pixel-level localization from class labels; however, a classifier trained on such labels is likely to focus on a small discriminative region of the target object. We interpret this phenomenon using the information bottleneck principle: the final layer of a deep neural network, activated by the sigmoid or softmax activation functions, causes […]

Read more
1 2