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.

A testcase generation tool for Persistent Memory Programs.

PMFuzz PMFuzz is a testcase generation tool to generate high-value tests cases for PM testing tools (XFDetector, PMDebugger, PMTest and Pmemcheck) If

Systems Research at ShiftLab 14 Jul 24, 2022
Fast algorithms to compute an approximation of the minimal volume oriented bounding box of a point cloud in 3D.

ApproxMVBB Status Build UnitTests Homepage Fast algorithms to compute an approximation of the minimal volume oriented bounding box of a point cloud in

Gabriel Nützi 390 Dec 31, 2022
Single object tracking and segmentation.

Single/Multiple Object Tracking and Segmentation Codes and comparison of recent single/multiple object tracking and segmentation. News 💥 AutoMatch is

ZP ZHANG 385 Jan 02, 2023
Ranger deep learning optimizer rewrite to use newest components

Ranger21 - integrating the latest deep learning components into a single optimizer Ranger deep learning optimizer rewrite to use newest components Ran

Less Wright 266 Dec 28, 2022
A PyTorch implementation for PyramidNets (Deep Pyramidal Residual Networks)

A PyTorch implementation for PyramidNets (Deep Pyramidal Residual Networks) This repository contains a PyTorch implementation for the paper: Deep Pyra

Greg Dongyoon Han 262 Jan 03, 2023
A curated list of long-tailed recognition resources.

Awesome Long-tailed Recognition A curated list of long-tailed recognition and related resources. Please feel free to pull requests or open an issue to

Zhiwei ZHANG 542 Jan 01, 2023
RealTime Emotion Recognizer for Machine Learning Study Jam's demo

Emotion recognizer Table of contents Clone project Dataset Install dependencies Main program Demo 1. Clone project git clone https://github.com/GDSC20

Google Developer Student Club - UIT 1 Oct 05, 2021
Automatic meme generation model using Tensorflow Keras.

Memefly You can find the project at MemeflyAI. Contributors Nick Buukhalter Harsh Desai Han Lee Project Overview Trello Board Product Canvas Automatic

BloomTech Labs 2 Jan 13, 2022
A Closer Look at Invalid Action Masking in Policy Gradient Algorithms

A Closer Look at Invalid Action Masking in Policy Gradient Algorithms This repo contains the source code to reproduce the results in the paper A Close

Costa Huang 73 Dec 24, 2022
Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt

Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt. This is done by

Mehdi Cherti 135 Dec 30, 2022
Discovering Dynamic Salient Regions with Spatio-Temporal Graph Neural Networks

Discovering Dynamic Salient Regions with Spatio-Temporal Graph Neural Networks This is the official code for DyReg model inroduced in Discovering Dyna

Bitdefender Machine Learning 11 Nov 08, 2022
Implementation of Kalman Filter in Python

Kalman Filter in Python This is a basic example of how Kalman filter works in Python. I do plan on refactoring and expanding this repo in the future.

Enoch Kan 35 Sep 11, 2022
Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation

Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation Paper Multi-Target Adversarial Frameworks for Domain Adaptation in

Valeo.ai 20 Jun 21, 2022
Course on computational design, non-linear optimization, and dynamics of soft systems at UIUC.

Computational Design and Dynamics of Soft Systems · This is a repository that contains the source code for generating the lecture notes, handouts, exe

Tejaswin Parthasarathy 4 Jul 21, 2022
Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models.

Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models

AdvBox 1.3k Dec 25, 2022
Learning Spatio-Temporal Transformer for Visual Tracking

STARK The official implementation of the paper Learning Spatio-Temporal Transformer for Visual Tracking Hiring research interns for visual transformer

Multimedia Research 484 Dec 29, 2022
A trashy useless Latin programming language written in python.

Codigum! The first programming langage in latin! (please keep your eyes closed when if you read the source code) It is pretty useless though. Document

Bic 2 Oct 25, 2021
Implementation of 'X-Linear Attention Networks for Image Captioning' [CVPR 2020]

Introduction This repository is for X-Linear Attention Networks for Image Captioning (CVPR 2020). The original paper can be found here. Please cite wi

JDAI-CV 240 Dec 17, 2022
[CVPR 2021] MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition

MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition (CVPR 2021) arXiv Prerequisite PyTorch = 1.2.0 Python3 torchvision PIL argpar

51 Nov 11, 2022
Official PyTorch implementation for "Low Precision Decentralized Distributed Training with Heterogenous Data"

Low Precision Decentralized Training with Heterogenous Data Official PyTorch implementation for "Low Precision Decentralized Distributed Training with

Aparna Aketi 0 Nov 23, 2021