Leveraging Two Types of Global Graph for Sequential Fashion Recommendation, ICMR 2021

Related tags

Deep LearningDGSR
Overview

This is the repo for the paper: Leveraging Two Types of Global Graph for Sequential Fashion Recommendation

Requirements

  1. OS: Ubuntu 16.04 or higher version
  2. python3.7
  3. Supported (tested) CUDA Versions: V10.2
  4. python modules: refer to the modules in requirements.txt

Code Structure

  1. The entry script for training and evaluation is: train.py
  2. The config file is: config.yaml
  3. The script for data preprocess and dataloader: utility.py
  4. The model folder: ./model/.
  5. The experimental logs in tensorboard-format are saved in ./logs.
  6. The experimental logs in txt-format are saved in ./performance.
  7. The best model for each experimental setting is saved in ./model_saves.
  8. The recommendation results in the evaluation are recorded in ./results.
  9. The ./logs, ./performance, ./model_saves, ./results files will be generated automatically when first time runing the codes.
  10. The script get_all_the_res.py is used to print the performance of all the trained and tested models on the screen.

How to Run

  1. Download the dataset, decompress it and put it in the top directory with the following command. Note that the downloaded files include two datasets ulilized in the paper: iFashion and amazon_fashion.

    tar zxvf dgsr_dataset.tar.gz. 
    
  2. Settings in the configure file config.yaml are basic experimental settings, which are usually fixed in the experiments. To tune other hyper-parameters, you can use command line to pass the parameters. The command line supported hyper-parameters including: the dataset (-d), sequence length (-l) and embedding size (-e). You can also specify which gpu device (-g) to use in the experiments.

  3. Run the training and evaluation with the specified hyper-parameters by the command:

    python train.py -d=ifashion -l=5 -e=50 -g=0. 
    
  4. During the training, you can monitor the training loss and the evaluation performance by Tensorboard. You can get into ./logs to track the curves of your training and evaluation with the following command:

    tensorboard --host="your host ip" --logdir=./
    
  5. The performance of the model is saved in ./performance. You can get into the folder and check the detailed training process of any finished experiments (Compared with the tensorboard log save in ./logs, it is just the txt-version human-readable training log). To quickly check the results for all implemented experiments, you can also print the results of all experiments in a table format on the terminal screen by running:

    python get_all_the_res.py
    
  6. The best model will be saved in ./model_saves.

Owner
Yujuan Ding
Yujuan Ding
Visual Adversarial Imitation Learning using Variational Models (VMAIL)

Visual Adversarial Imitation Learning using Variational Models (VMAIL) This is the official implementation of the NeurIPS 2021 paper. Project website

14 Nov 18, 2022
💡 Type hints for Numpy

Type hints with dynamic checks for Numpy! (❒) Installation pip install nptyping (❒) Usage (❒) NDArray nptyping.NDArray lets you define the shape and

Ramon Hagenaars 377 Dec 28, 2022
A package for music online and offline rhythmic information analysis including music Beat, downbeat, tempo and meter tracking.

BeatNet A package for music online and offline rhythmic information analysis including music Beat, downbeat, tempo and meter tracking. This repository

Mojtaba Heydari 157 Dec 27, 2022
Hcpy - Interface with Home Connect appliances in Python

Interface with Home Connect appliances in Python This is a very, very beta inter

Trammell Hudson 116 Dec 27, 2022
Control-Robot-Arm-using-PS4-Controller - A Robotic Arm based on Raspberry Pi and Arduino that controlled by PS4 Controller

Control-Robot-Arm-using-PS4-Controller You can see all details about this Robot

MohammadReza Sharifi 5 Jan 01, 2022
Film review classification

Film review classification Решение задачи классификации отзывов на фильмы на положительные и отрицательные с помощью рекуррентных нейронных сетей 1. З

Nikita Dukin 3 Jan 21, 2022
nn_builder lets you build neural networks with less boilerplate code

nn_builder lets you build neural networks with less boilerplate code. You specify the type of network you want and it builds it. Install pip install n

Petros Christodoulou 157 Nov 20, 2022
A working implementation of the Categorical DQN (Distributional RL).

Categorical DQN. Implementation of the Categorical DQN as described in A distributional Perspective on Reinforcement Learning. Thanks to @tudor-berari

Florin Gogianu 98 Sep 20, 2022
Bayesian Deep Learning and Deep Reinforcement Learning for Object Shape Error Response and Correction of Manufacturing Systems

Bayesian Deep Learning for Manufacturing 2.0 (dlmfg) Object Shape Error Response (OSER) Digital Lifecycle Management - In Process Quality Improvement

Sumit Sinha 30 Oct 31, 2022
2D Human Pose estimation using transformers. Implementation in Pytorch

PE-former: Pose Estimation Transformer Vision transformer architectures perform very well for image classification tasks. Efforts to solve more challe

Panteleris Paschalis 23 Oct 17, 2022
VisionKG: Vision Knowledge Graph

VisionKG: Vision Knowledge Graph Official Repository of VisionKG by Anh Le-Tuan, Trung-Kien Tran, Manh Nguyen-Duc, Jicheng Yuan, Manfred Hauswirth and

Continuous Query Evaluation over Linked Stream (CQELS) 9 Jun 23, 2022
Using VideoBERT to tackle video prediction

VideoBERT This repo reproduces the results of VideoBERT (https://arxiv.org/pdf/1904.01766.pdf). Inspiration was taken from https://github.com/MDSKUL/M

75 Dec 14, 2022
Lenia - Mathematical Life Forms

For full version list, see Timeline in Lenia portal [2020-10-13] Update Python version with multi-kernel and multi-channel extensions (v3.4 LeniaNDK.p

Bert Chan 3.1k Dec 28, 2022
Using contrastive learning and OpenAI's CLIP to find good embeddings for images with lossy transformations

Creating Robust Representations from Pre-Trained Image Encoders using Contrastive Learning Sriram Ravula, Georgios Smyrnis This is the code for our pr

Sriram Ravula 26 Dec 10, 2022
My freqtrade strategies

My freqtrade-strategies Hi there! This is repo for my freqtrade-strategies. My name is Ilya Zelenchuk, I'm a lecturer at the SPbU university (https://

171 Dec 05, 2022
Place holder for HOPE: a human-centric and task-oriented MT evaluation framework using professional post-editing

HOPE: A Task-Oriented and Human-Centric Evaluation Framework Using Professional Post-Editing Towards More Effective MT Evaluation Place holder for dat

Lifeng Han 1 Apr 25, 2022
Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm

Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetu

3 Dec 05, 2022
Notebook and code to synthesize complex and highly dimensional datasets using Gretel APIs.

Gretel Trainer This code is designed to help users successfully train synthetic models on complex datasets with high row and column counts. The code w

Gretel.ai 24 Nov 03, 2022
GeneralOCR is open source Optical Character Recognition based on PyTorch.

Introduction GeneralOCR is open source Optical Character Recognition based on PyTorch. It makes a fidelity and useful tool to implement SOTA models on

57 Dec 29, 2022
Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using coresets and data selection.

COResets and Data Subset selection Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order

decile-team 244 Jan 09, 2023