Pytorch lightning tutorial using MNIST Youtube stream (Maybe there will be another… still planning!) Pytorch lightning introduction scheduler introduction (Japanese) Python>=3.7, creation using anaconda is recommended. Install libraries by pip install -r requirements.txt. Run (example) python train.py –root_dir “./” It will download the dataset to root_dir and start training. You can monitor the training process by launching tensorboard in another terminal: tensorboard –logdir logs And go to localhost:6006 in your browser. GitHub View Github    

This is an implementation of the cyclemoid activation function for PyTorch. The cyclemoid function achieved state-of-the-art results in a recent benchmark with other popular activation functions as shown below: Note that this is a figure from the paper submitted on April 1st, 2022. An arxiv preprint will be uploaded soon. Installation You can install the cyclemoid-pytorch package via pip install cyclemoid_pytorch Usage This package implements a CycleMoid class and a cyclemoid function. You can use these are drop-in replacements for […]

In Vision-and-Language Navigation (VLN), an agent needs to navigate through the environment based on natural language instructions. Due to limited available data for agent training and finite diversity in navigation environments, it is challenging for the agent to generalize to new, unseen environments. To address this problem, we propose EnvEdit, a data augmentation method that creates new environments by editing existing environments, which are used to train a more generalizable agent. Our augmented environments can differ from the seen environments […]

By Wen Wang, Jing Zhang, Yang Cao, Yongliang Shen, and Dacheng Tao This repository is an official implementation of DE-CondDETR and DELA-CondDETR in the paper Towards Data-Efficient Detection Transformers. For the implementation of DE-DETR and DELA-DETR, please refer to DE-DETRs. Introduction TL; DR. We identify the data-hungry issue of existing detection transformers and alleviate it by simply alternating how key and value sequences are constructed in the cross-attention layer, with minimum modifications to the original models. Besides, we introduce a […]

NER, Sentiment, Classification in Persian text by using prepared Pytorch model Usage First of all you need to download the prepared models. Each task has it’s own model. After downloading them, you should put them into related folders. Use docker-compose to setup Django container by bellow command: Now, Django app is ready to use. Three APIs are available: http://localhost:8040/v1/app/ner/ http://localhost:8040/v1/app/sentiment/ http://localhost:8040/v1/app/classification/ You should send POST request with text field in the body. GitHub View Github    

This project implements a method for faster and more memory-efficient RNN-T loss computation, called pruned rnnt. Note: There is also a fast RNN-T loss implementation in k2 project, which shares the same code here. We make fast_rnnt a stand-alone project in case someone wants only this rnnt loss. How does the pruned-rnnt work ? We first obtain pruning bounds for the RNN-T recursion using a simple joiner network that is just an addition of the encoder and decoder, then we […]

A PyTorch implementation of GraphSAGE This package contains a PyTorch implementation of GraphSAGE. Currently, only supervised versions of GraphSAGE-mean, GraphSAGE-GCN, GraphSAGE-maxpool and GraphSAGE-meanpool are implemented. Authors of this code package: Bin Yu Environment settings python>=3.6.8 pytorch>=1.0.0 Basic Usage Example Usage To run the supervised model on Cuda: GitHub View Github    

This is an official pytorch implementation of our ICML 2021 paper Is Space-Time Attention All You Need for Video Understanding?. In this repository, we provide PyTorch code for training and testing our proposed TimeSformer model. TimeSformer provides an efficient video classification framework that achieves state-of-the-art results on several video action recognition benchmarks such as Kinetics-400. If you find TimeSformer useful in your research, please use the following BibTeX entry for citation. @inproceedings{gberta_2021_ICML, author = {Gedas Bertasius