Forward Compatible Few-Shot Class-Incremental Learning

The code repository for “Forward Compatible Few-Shot Class-Incremental Learning” [paper] (CVPR22) in PyTorch. If you use any content of this repo for your work, please cite the following bib entry: @inproceedings{zhou2022forward, title={Forward Compatible Few-Shot Class-Incremental Learning}, author={Zhou, Da-Wei and Wang, Fu-Yun and Ye, Han-Jia and Ma, Liang and Pu, Shiliang and Zhan, De-Chuan}, booktitle={CVPR}, year={2022} } Forward Compatible Few-Shot Class-Incremental Learning Novel classes frequently arise in our dynamically changing world, e.g., new users in the authentication system, and a machine […]

Read more

PyTorch/HuggingFace Implementation of URLTran: Improving Phishing URL Detection Using Transformers

PyTorch implementation of Improving Phishing URL Detection via Transformers Paper Data The paper used ~1.8M URLs (90/10 split on benign vs. malicious). There are few places to gather malicious URLs. My recommendation is to do the following: Malicious URLs OpenPhish will provide 500 malicious URLs for free in TXT form. You can access that data here. Likewise, PhishTank is an excellent resource that provides a daily feed of malicious URLs in CSV or JSON format. You can gather ~5K through […]

Read more

A basic and simple training framework for pytorch. Easy to expand for multi network interaction

[TOC] Introduction A basic and simple training framework for pytorch, easy for extension. Dependence torch==1.7.0+cu110 torchvision==0.8.0 easydict==1.9 tensorboard==2.7 tensorboardX==2.4 PyYAML==5.3.1 Features Any module can be easily customized Not abstract, easy to learn, develop and debug With a lot of repetitive work reduction, it can be more easily control the training process in development and research Friendly to multi-network interactive training, such as GAN, transfer learning, knowledge distillation, etc. Train python main.py –model resnet18 –save_dir cifar100_resnet18 –config_path ./configs/cifar100.yml Results CIFAR100 All […]

Read more

A Python bot which can compare and assist in predicting future crypto prices

A cryptocurrency bot which can assist you in predicting future crypto prices through comparing previous crypto prices with actual prices. The bot uses the method of Death Cross vs Golden Cross, a reliable method for solid predictions of prices, to make a plot based on previously predicted data. Image: Preview of the graph Table of Contents Features Interactive graph Allows user to input to customize the following in the chart – currency, cryptocurrency, time period and time interval Various built-in […]

Read more

Invariant and Equivariant Graph Networks

A PyTorch implementation of The ICLR 2019 paper “Invariant and Equivariant Graph Networks” by Haggai Maron, Heli Ben-Hamu, Nadav Shamir and Yaron Lipmanhttps://openreview.net/forum?id=Syx72jC9tm. The official TensorFlow implementation is at https://github.com/Haggaim/InvariantGraphNetworks Data Data should be downloaded from: https://www.dropbox.com/s/vjd6wy5nemg2gh6/benchmark_graphs.zip?dl=0.Run the following commands in order to unzip the data and put its proper path. mkdir data unzip benchmark_graphs.zip -d data Prerequisites Python3 PyTorch 1.5.0 Additional modules: numpy, pandas, matplotlib TensorFlow is not neccessary except if you want to run the tests (comparisons) between […]

Read more

MTReclib provides a PyTorch implementation of multi-task recommendation models and common datasets

Introduction MTReclib provides a PyTorch implementation of multi-task recommendation models and common datasets. Currently, we implmented 7 multi-task recommendation models to enable fair comparison and boost the development of multi-task recommendation algorithms. The currently supported algorithms include: Datasets For the processed dataset, you should directly put the dataset in ‘./data/’ and unpack it. For the original dataset, you should put it in ‘./data/’ and run ‘python preprocess.py –dataset_name NL’. Requirements Python 3.6 PyTorch > 1.10 pandas numpy tqdm Run Parameter […]

Read more

A PyTorch landmarks-only library with 100+ data augmentations, training and inference

English | 中文文档 🤗 Introduction torchlm is a PyTorch landmarks-only library with 100+ data augmentations, support training and inference. torchlm is aims at only focus on any landmark detection, such as face landmarks, hand keypoints and body keypoints, etc. It provides 30+ native data augmentations and can bind with 80+ transforms from torchvision and albumentations, no matter the input is a np.ndarray or a torch Tensor, torchlm will automatically be compatible with different data types and then wrap it back […]

Read more

Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels

Official PyTorch implementation of Semi-Supervised Semantic Segmentation Using Unreliable Pseudo Labels, CVPR 2022. Please refer to our project page for qualitative results. Abstract.The crux of semi-supervised semantic segmentation is to assign adequate pseudo-labels to the pixels of unlabeled images.A common practice is to select the highly confident predictions as the pseudo ground-truth, but it leads to a problem that most pixels may be left unused due to their unreliability.We argue that every pixel matters to the model training, even its […]

Read more

Custom PyTorch ML block example for Edge Impulse

This repository is an example on how to bring a custom transfer learning model into Edge Impulse. This repository contains a small fully-connected model built in PyTorch. If you want to see a more complex PyTorch example, see edgeimpulse/yolov5. Or if you’re looking for the Keras version of this repository, see edgeimpulse/example-custom-ml-block-keras. As a primer, read the Adding custom transfer learning models page in the Edge Impulse docs. To test this locally: Create a new Edge Impulse project, and add […]

Read more
1 2 3 4 14