All Projects → yiling-chen → View Finding Network

yiling-chen / View Finding Network

Licence: gpl-3.0
A deep ranking network that learns to find good compositions in a photograph.

Programming Languages

139335 projects - #7 most used programming language

Projects that are alternatives of or similar to View Finding Network

Semantic Kitti Api
SemanticKITTI API for visualizing dataset, processing data, and evaluating results.
Stars: ✭ 272 (+377.19%)
Mutual labels:  dataset, evaluation
Vidvrd Helper
To keep updates with VRU Grand Challenge, please use
Stars: ✭ 81 (+42.11%)
Mutual labels:  dataset, evaluation
Text2sql Data
A collection of datasets that pair questions with SQL queries.
Stars: ✭ 287 (+403.51%)
Mutual labels:  dataset, evaluation
Hpatches Benchmark
Python & Matlab code for local feature descriptor evaluation with the HPatches dataset.
Stars: ✭ 129 (+126.32%)
Mutual labels:  dataset, evaluation
Dukemtmc Reid evaluation
ICCV2017 The Person re-ID Evaluation Code for DukeMTMC-reID Dataset (Including Dataset Download)
Stars: ✭ 344 (+503.51%)
Mutual labels:  dataset, evaluation
💧 In memory dataset filtering, inspired by snikch/aggro
Stars: ✭ 49 (-14.04%)
Mutual labels:  dataset
Corpus of Annual Reports in Japan
Stars: ✭ 55 (-3.51%)
Mutual labels:  dataset
Code for the collection and analysis of the MTNT dataset
Stars: ✭ 48 (-15.79%)
Mutual labels:  dataset
A library & tools to evaluate predictive language models.
Stars: ✭ 47 (-17.54%)
Mutual labels:  evaluation
Stars: ✭ 57 (+0%)
Mutual labels:  dataset
Fifa Fut Data
Web-scraping script that writes the data of all players from FutHead and FutBin to a CSV file or a DB
Stars: ✭ 55 (-3.51%)
Mutual labels:  dataset
✅ CODAR is a Framework built using PyTorch to analyze post (Text+Media) and predict Cyber Bullying and offensive content. 💬📷
Stars: ✭ 52 (-8.77%)
Mutual labels:  dataset
Awesome Semantic Segmentation
🤘 awesome-semantic-segmentation
Stars: ✭ 8,831 (+15392.98%)
Mutual labels:  evaluation
Multi-class confusion matrix library in Python
Stars: ✭ 1,076 (+1787.72%)
Mutual labels:  evaluation
Detects Chinese traffic police commanding poses 检测中国交警指挥手势
Stars: ✭ 49 (-14.04%)
Mutual labels:  dataset
☁️ 🚀 📊 📈 Evaluating state of the art in AI
Stars: ✭ 1,087 (+1807.02%)
Mutual labels:  evaluation
Combine multiple MNIST digits to create datasets with 100/1000 classes for few-shot learning/meta-learning
Stars: ✭ 48 (-15.79%)
Mutual labels:  dataset
Covid 19
Novel Coronavirus 2019 time series data on cases
Stars: ✭ 1,060 (+1759.65%)
Mutual labels:  dataset
Clothing Detection Dataset
Clothing detection dataset
Stars: ✭ 55 (-3.51%)
Mutual labels:  dataset
Images Web Crawler
This package is a complete tool for creating a large dataset of images (specially designed -but not only- for machine learning enthusiasts). It can crawl the web, download images, rename / resize / covert the images and merge folders..
Stars: ✭ 51 (-10.53%)
Mutual labels:  dataset

View Finding Network

This repository contains the dataset and scripts used in the following article:

Yi-Ling Chen, Jan Klopp, Min Sun, Shao-Yi Chien, Kwan-Liu Ma, "Learning to Compose with Professional Photographs on the Web", in Proc. of ACM Multimedia 2017. (Supplemetnal)

News We are reimplementing this method in PyTorch. Check back often if you are interested.


You will need to have tensorflow (version > 1.0), skimage, tabulate, pillow installed on your system to run the scripts.

Download the dataset

  • Clone the repository to your local disk.
  • Under a command line window, run the following command to get the training images from Flickr:
$ python -w 4

The above command will launch 4 worker threads to download the images to a default folder (./images).


  • Run to generate the TFRecords files used by Tensorflow.
  • Run to start training.
$ python --spp 0

The above example starts training with SPP disabled. Or you may want to enable SPP with either max or avg options.

$ python --pooling max

Note that if you changed the output filenames when running, you will need to provide the new filenames to Take a look at the script to check out other available parameters or run the following command.

$ python -h


We provide the evaluation script to reproduce our evaluation results on Flickr cropping dataset. For example,

$ python --spp false --snapshot snapshots/model-wo-spp

You will need to get sliding_window.json and the test images from the Flickr cropping dataset and specify the path of your model when running You can also try our pre-trained model, which can be downloaded from here.

If you want to get an aesthetic score of a patch, please take a look at the example featured by ModelDepot


If you have questions/suggestions, feel free to send an email to (yiling dot chen dot ntu at gmail dot com).

If this work helps your research, please cite the following article:

  title={Learning to Compose with Professional Photographs on the Web},
  author={Yi-Ling Chen and Jan Klopp and Min Sun and Shao-Yi Chien and Kwan-Liu Ma},
  booktitle={ACM Multimedia 2017},
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].