Segmentation vgg16 fcn - cityscapes

Overview

VGGSegmentation

Segmentation vgg16 fcn - cityscapes Priprema skupa

skripta prepare_dataset_downsampled.py

Iz slika cityscapesa izrezuje haubu automobila, i smanjuje sliku na željenu rezoluciju, to zapisuje u tfrecords formatu. Treba zadati putanju do cityscapesa, izlazni direktorij gdje će se spremati tfrecordsi i zadati željenu rezoluciju.

Priprema težina vgg-a

Da bi se model mogao fine-tuneati treba na disku imati spremljene težine mreže (prethodno naučene na nekom drugom skupu). One se mogu skinuti s interneta u raznim formatima.

Ja sam ih imala spremljene u sljedećim datotekama: conv1_1_biases.bin conv1_1_weights.bin conv1_2_biases.bin conv1_2_weights.bin conv2_1_biases.bin conv2_1_weights.bin conv2_2_biases.bin conv2_2_weights.bin conv3_1_biases.bin conv3_1_weights.bin conv3_2_biases.bin conv3_2_weights.bin conv3_3_biases.bin conv3_3_weights.bin conv4_1_biases.bin conv4_1_weights.bin conv4_2_biases.bin conv4_2_weights.bin conv4_3_biases.bin conv4_3_weights.bin conv5_1_biases.bin conv5_1_weights.bin conv5_2_biases.bin conv5_2_weights.bin conv5_3_biases.bin conv5_3_weights.bin fc6_biases.bin fc6_weights.bin fc7_biases.bin fc7_weights.bin fc8_biases.bin fc8_weights.bin

Ako će se težine učitavati iz ckpt. datoteke npr vgg_16.ckpt, onda će i u kodu trebati mjenjati metodu create_init_op unutar model.py

Konfiguracija

config/cityscapes.py - primjer fajla s konfiguracijom za treniranje

Treba promjeniti putanje

model_path da pokazuje do py fajla s definicijom modela (primjer za takve dvije defincije su model.py i model2.py)

dataset_dir - da pokazuje do foldera s prethodno pripremljenim tfrecordsima (koji sadrzi subdirektorije train i val)

treba paziti pri razlicitim rezolucijama da se promjene zastavice img_width i height

ostale zastavice se većinom odnose na treniranje modela to mjenjati prema potrebi.

subsample_factor zastavica bi označavala faktor za koji se rezolucija mape smanji na kraju mreže. Taj faktor će ovisiti o samome modelu koji se trenira, ako model ima tri pooling sloja 2*2 svaki taj sloj će sliku smanjiti za dva puta pa će ukupno smanjnjenje biti za faktor osam

train.py - skripta koja pokreće skriptu treniranja, nakon svake epohe model se evaluira na skupu za validaciju.

Split your patch similarly to `git add -p` but supporting multiple buckets

split-patch.py This is git add -p on steroids for patches. Given a my.patch you can run ./split-patch.py my.patch You can choose in which bucket to p

102 Oct 06, 2022
MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks

MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks Introduction This repo contains the pytorch impl

Meta Research 38 Oct 10, 2022
Open-CyKG: An Open Cyber Threat Intelligence Knowledge Graph

Open-CyKG: An Open Cyber Threat Intelligence Knowledge Graph Model Description Open-CyKG is a framework that is constructed using an attenti

Injy Sarhan 34 Jan 05, 2023
A sketch extractor for anime/illustration.

Anime2Sketch Anime2Sketch: A sketch extractor for illustration, anime art, manga By Xiaoyu Xiang Updates 2021.5.2: Upload more example results of anim

Xiaoyu Xiang 1.6k Jan 01, 2023
A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.

Visdom A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Python. Overview Concepts Setup Usage API To

FOSSASIA 9.4k Jan 07, 2023
tsai is an open-source deep learning package built on top of Pytorch & fastai focused on state-of-the-art techniques for time series classification, regression and forecasting.

Time series Timeseries Deep Learning Pytorch fastai - State-of-the-art Deep Learning with Time Series and Sequences in Pytorch / fastai

timeseriesAI 2.8k Jan 08, 2023
Zalo AI challenge 2021 task hum to song

Zalo AI challenge 2021 task Hum to Song pipeline: Chuẩn bị dữ liệu cho quá trình train: Sửa các file đường dẫn trong config/preprocess.yaml raw_path:

Vo Van Phuc 105 Dec 16, 2022
A library for Deep Learning Implementations and utils

deeply A Deep Learning library Table of Contents Features Quick Start Usage License Features Python 2.7+ and Python 3.4+ compatible. Quick Start $ pip

Achilles Rasquinha 1 Dec 12, 2022
An ML & Correlation platform for transforming disparate data points of interest into usable intelligence.

SSIDprobeCollector An ML & Correlation platform for transforming disparate data points of interest into usable intelligence. At a High level the platf

Bill Reyor 1 Jan 30, 2022
A Lightweight Hyperparameter Optimization Tool 🚀

Lightweight Hyperparameter Optimization 🚀 The mle-hyperopt package provides a simple and intuitive API for hyperparameter optimization of your Machin

136 Jan 08, 2023
Official repository of "Investigating Tradeoffs in Real-World Video Super-Resolution"

RealBasicVSR [Paper] This is the official repository of "Investigating Tradeoffs in Real-World Video Super-Resolution, arXiv". This repository contain

Kelvin C.K. Chan 566 Dec 28, 2022
Lightweight Cuda Renderer with Python Wrapper.

pyRender Lightweight Cuda Renderer with Python Wrapper. Compile Change compile.sh line 5 to the glm library include path. This library can be download

Jingwei Huang 53 Dec 02, 2022
Check out the StyleGAN repo and place it in the same directory hierarchy as the present repo

Variational Model Inversion Attacks Kuan-Chieh Wang, Yan Fu, Ke Li, Ashish Khisti, Richard Zemel, Alireza Makhzani Most commands are in run_scripts. W

Jackson Wang 15 Dec 26, 2022
[CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

TransFuser This repository contains the code for the CVPR 2021 paper Multi-Modal Fusion Transformer for End-to-End Autonomous Driving. If you find our

695 Jan 05, 2023
Learning infinite-resolution image processing with GAN and RL from unpaired image datasets, using a differentiable photo editing model.

Exposure: A White-Box Photo Post-Processing Framework ACM Transactions on Graphics (presented at SIGGRAPH 2018) Yuanming Hu1,2, Hao He1,2, Chenxi Xu1,

Yuanming Hu 719 Dec 29, 2022
Storage-optimizer - Identify potintial optimizations on the cloud storage accounts

Storage Optimizer Identify potintial optimizations on the cloud storage accounts

Zaher Mousa 1 Feb 13, 2022
PyTorch implementation of ENet

PyTorch-ENet PyTorch (v1.1.0) implementation of ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation, ported from the lua-torc

David Silva 333 Dec 29, 2022
In this project we predict the forest cover type using the cartographic variables in the training/test datasets.

Kaggle Competition: Forest Cover Type Prediction In this project we predict the forest cover type (the predominant kind of tree cover) using the carto

Marianne Joy Leano 1 Mar 15, 2022
GndNet: Fast ground plane estimation and point cloud segmentation for autonomous vehicles using deep neural networks.

GndNet: Fast Ground plane Estimation and Point Cloud Segmentation for Autonomous Vehicles. Authors: Anshul Paigwar, Ozgur Erkent, David Sierra Gonzale

Anshul Paigwar 114 Dec 29, 2022
A note taker for NVDA. Allows the user to create, edit, view, manage and export notes to different formats.

Quick Notetaker add-on for NVDA The Quick Notetaker add-on is a wonderful tool which allows writing notes quickly and easily anytime and from any app

5 Dec 06, 2022