An Ensemble of CNN (Python 3.5.1 Tensorflow 1.3 numpy 1.13)

Overview

An Ensemble of CNN

Machine Learning project 2017

Read me

NOTE: All commands should be run inside the tensorflow environment

Dependencies

Python 3.5.1 Tensorflow 1.3 numpy 1.13

Although the model might work with previous version of above libraries, these version are what were used in development. Link to dataset: https://www.kaggle.com/xainano/handwrittenmathsymbols

Preparation

Do the following steps only if the folders MathExprJpeg/train_data and MathExprJpeg/train_data and files x_data.npy, y_data.npy and labels.npy are none existent, otherwise go directly to Running Main section.

In order to run the model the training and testing folders must be created. If test_data folder and train_data folder does not exist in the MathExprJpeg folder, these must be created. Create them by running the script create_train_test_data.py like this:

python create_train_test_data.py

Then the datafiles for the training data must be created in order to speed up training. Called x_data.npy, y_data.npy and labels.npy. If non existent create by running the script create_datafiles.py like this:

python create_datafiles.py
Running main

After the preparation steps are done, set the preferred modes in cnn_math_main.py file. This is done by changing the parameters at the top of the file:

# set if data shold be read in advance
fileread = True
ensemble_mode = False 

fileread = True means that the data will be read from the previously created x_data.npy and y_data.npy files. Setting this to True is highly recommended. The ensemble_mode = False means that the model will not be run in ensemble mode. This is recommended as the ensemble mode is performance heavy and can not be guaranteed to work in the latest releases.

It is recommended to change the name of the logging file for each run:

writer = tf.summary.FileWriter('./logs/cnn_math_logs_true_2ep_r1')
writer.add_graph(sess.graph)

Also set the preferred value to the epoch and batch_size:

training_epochs = 40
batch_size = 20

When all of the above has been done, the model can be run with the command:

python cnn_math_main.py

The model has been known to sometimes get errors while reading files. The source of which is unknown. If such an error is to occur, run the following commands:

rm -r MatchExprJpeg/train_data
rm -r MatchExprJpeg/test_data
rm x_data.npy
rm y_data.npy
rm labels.npy

python create_train_test_data.py
python create_datafiles.py

And then try to run the cnn_math_main.py again. start tensorboard with:

tensorboard --logdir=./logs

to see the graphs for the scalars, the image being processed etc.

The model is implemented in the cnn_model.py class. If this file is tempered with it is possible that the model breaks.

Happy predicting

MachineLearningProjectCNN

A light weight data augmentation tool for training CNNs and Viola Jones detectors

hey-daug A light weight data augmentation tool for training CNNs and Viola Jones detectors (Haar Cascades). This tool inflates your data by up to six

Jaiyam Sharma 2 Nov 23, 2019
PyTorch IPFS Dataset

PyTorch IPFS Dataset IPFSDataset(Dataset) See the jupyter notepad to see how it works and how it interacts with a standard pytorch DataLoader You need

Jake Kalstad 2 Apr 13, 2022
[CVPR2021 Oral] FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation.

FFB6D This is the official source code for the CVPR2021 Oral work, FFB6D: A Full Flow Biderectional Fusion Network for 6D Pose Estimation. (Arxiv) Tab

Yisheng (Ethan) He 201 Dec 28, 2022
PyTorch-centric library for evaluating and enhancing the robustness of AI technologies

Responsible AI Toolbox A library that provides high-quality, PyTorch-centric tools for evaluating and enhancing both the robustness and the explainabi

24 Dec 22, 2022
SE-MSCNN: A Lightweight Multi-scaled Fusion Network for Sleep Apnea Detection Using Single-Lead ECG Signals

SE-MSCNN: A Lightweight Multi-scaled Fusion Network for Sleep Apnea Detection Using Single-Lead ECG Signals Abstract Sleep apnea (SA) is a common slee

9 Dec 21, 2022
Code for the ECIR'22 paper "Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators"

Query Variation Generators This repository contains the code and annotation data for the ECIR'22 paper "Evaluating the Robustness of Retrieval Pipelin

Gustavo Penha 12 Nov 20, 2022
Explicable Reward Design for Reinforcement Learning Agents [NeurIPS'21]

Explicable Reward Design for Reinforcement Learning Agents [NeurIPS'21]

3 May 12, 2022
Official code implementation for "Personalized Federated Learning using Hypernetworks"

Personalized Federated Learning using Hypernetworks This is an official implementation of Personalized Federated Learning using Hypernetworks paper. [

Aviv Shamsian 121 Dec 25, 2022
This dlib-based facial login system

Facial-Login-System This dlib-based facial login system is a technology capable of matching a human face from a digital webcam frame capture against a

Mushahid Ali 3 Apr 23, 2022
A decent AI that solves daily Wordle puzzles. Works with different websites with similar wordlists,.

Wordle-AI A decent AI that solves daily "Wordle" puzzles. Works with different websites with similar wordlists. When prompted with "Word:" enter the w

Ethan 1 Feb 10, 2022
Rainbow DQN implementation that outperforms the paper's results on 40% of games using 20x less data 🌈

Rainbow 🌈 An implementation of Rainbow DQN which reaches a median HNS of 205.7 after only 10M frames (the original Rainbow from Hessel et al. 2017 re

Dominik Schmidt 31 Dec 21, 2022
MODNet: Trimap-Free Portrait Matting in Real Time

MODNet is a model for real-time portrait matting with only RGB image input.

Zhanghan Ke 2.8k Dec 30, 2022
This repo contains the source code and a benchmark for predicting user's utilities with Machine Learning techniques for Computational Persuasion

Machine Learning for Argument-Based Computational Persuasion This repo contains the source code and a benchmark for predicting user's utilities with M

Ivan Donadello 4 Nov 07, 2022
PyTorch Implementation of Region Similarity Representation Learning (ReSim)

ReSim This repository provides the PyTorch implementation of Region Similarity Representation Learning (ReSim) described in this paper: @Article{xiao2

Tete Xiao 74 Jan 03, 2023
Public repository created to store my custom-made tools for Just Dance (UbiArt Engine)

Woody's Just Dance Tools Public repository created to store my custom-made tools for Just Dance (UbiArt Engine) Development and updates Almost all of

Wodson de Andrade 8 Dec 24, 2022
PRTR: Pose Recognition with Cascade Transformers

PRTR: Pose Recognition with Cascade Transformers Introduction This repository is the official implementation for Pose Recognition with Cascade Transfo

mlpc-ucsd 133 Dec 30, 2022
A framework that allows people to write their own Rocket League bots.

YOU PROBABLY SHOULDN'T PULL THIS REPO Bot Makers Read This! If you just want to make a bot, you don't need to be here. Instead, start with one of thes

543 Dec 20, 2022
PyTorch implementation DRO: Deep Recurrent Optimizer for Structure-from-Motion

DRO: Deep Recurrent Optimizer for Structure-from-Motion This is the official PyTorch implementation code for DRO-sfm. For technical details, please re

Alibaba Cloud 56 Dec 12, 2022
A JAX-based research framework for writing differentiable numerical simulators with arbitrary discretizations

jaxdf - JAX-based Discretization Framework Overview | Example | Installation | Documentation ⚠️ This library is still in development. Breaking changes

UCL Biomedical Ultrasound Group 65 Dec 23, 2022
Face recognition system using MTCNN, FACENET, SVM and FAST API to track participants of Big Brother Brasil in real time.

BBB Face Recognizer Face recognition system using MTCNN, FACENET, SVM and FAST API to track participants of Big Brother Brasil in real time. Instalati

Rafael Azevedo 232 Dec 24, 2022