Git Product home page Git Product logo

pblite-dl's Introduction

For Phase 1- PB Lite Edge Detection:

To find edges on image number 7,

python3 Wrapper.py --ImageName 7.jpg

For Phase 2- DeepLearning Architectures,

For the Simple First Neural network, run:

Training:

    python3 Train.py --BasePath ../CIFAR10/Train/ --CheckPointPath ../Checkpoints/BasicModel/ --NumEpochs 25 --DivTrain 1 --MiniBatchSize 64 --LoadCheckPoint 0 --LogsPath Logs/BasicModel/ --ModelName BasicModel

Testing:

    python3 Test.py --ModelName BasicModel --ModelPath ../Checkpoints/BasicModel/24model.ckpt --BasePath ../CIFAR10/Test/ --LabelsPath ./TxtFiles/LabelsTest.txt

For the Modified network, run:

Training:

python3 Train.py --BasePath ../CIFAR10/Train/ --CheckPointPath ../Checkpoints/BasicModel2/ --NumEpochs 50 --DivTrain 1 --MiniBatchSize 64 --LoadCheckPoint 0 --LogsPath Logs/BasicModel2/ --ModelName BasicModel2

Testing:

python3 Test.py --ModelName BasicModel2 --ModelPath ../Checkpoints/BasicModel2/49model.ckpt --BasePath ../CIFAR10/Test/ --LabelsPath ./TxtFiles/LabelsTest.txt

For Simple ResNet, run:

Training:

    python3 Train.py --BasePath ../CIFAR10/Train/ --CheckPointPath ../Checkpoints/ResNet2/ --NumEpochs 50 --DivTrain 1 --MiniBatchSize 64 --LoadCheckPoint 0 --LogsPath Logs/ResNet2/ --ModelName ResNet2

Testing:

    python3 Test.py --ModelName ResNet2  --ModelPath ../Checkpoints/ResNet2/49model.ckpt --BasePath ../CIFAR10/Test/ --LabelsPath ./TxtFiles/LabelsTest.txt

For ResNet pooling version, run:

Training:

   python3 Train.py --BasePath ../CIFAR10/Train/ --CheckPointPath ../Checkpoints/ResNet/ --NumEpochs 50 --DivTrain 1 --MiniBatchSize 64 --LoadCheckPoint 0 --LogsPath Logs/ResNet/ --ModelName ResNet

Testing:

python3 Test.py --ModelName ResNet --ModelPath ../Checkpoints/ResNet/49model.ckpt --BasePath ../CIFAR10/Test/ --LabelsPath ./TxtFiles/LabelsTest.txt

For DenseNet, run:

Training:

python3 Train.py --BasePath ../CIFAR10/Train/ --CheckPointPath ../Checkpoints/DenseNet/ --NumEpochs 50 --DivTrain 1 --MiniBatchSize 64 --LoadCheckPoint 0 --LogsPath Logs/DenseNet/ --ModelName DenseNet

Testing:

python3 Test.py --ModelName DenseNet --ModelPath ../Checkpoints/DenseNet/49model.ckpt --BasePath ../CIFAR10/Test/ --LabelsPath ./TxtFiles/LabelsTest.txt

For Resnext, run:

Training:

python3 Train.py --BasePath ../CIFAR10/Train/ --CheckPointPath ../Checkpoints/ResNext/ --NumEpochs 25 --DivTrain 1 --MiniBatchSize 64 --LoadCheckPoint 0 --LogsPath Logs/ResNext/ --ModelName ResNext

Testing:

python3 Test.py --ModelName ResNext --ModelPath ../Checkpoints/ResNext/24model.ckpt --BasePath ../CIFAR10/Test/ --LabelsPath ./TxtFiles/LabelsTest.txt

pblite-dl's People

Contributors

h-gokul avatar

Watchers

James Cloos avatar avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.