Monk is a low code Deep Learning tool and a unified wrapper for Computer Vision.
Issue: Want to begin learning computer vision
Issue: Multiple libraries hence multiple syntaxes to learn
Issue: Tough to keep track of all the trial projects while participating in a deep learning competition
Issue: Tough to set hyper-parameters while training a classifier
Issue: Looking for a library to build quick solutions for your customer
Medical Domain | Fashion Domain | Autonomous Vehicles Domain |
Agriculture Domain | Wildlife Domain | Retail Domain |
Satellite Domain | Healthcare Domain | Activity Analysis Domain |
#Create an experiment
ptf.Prototype("sample-project-1", "sample-experiment-1")
#Load Data
ptf.Default(dataset_path="sample_dataset/",
model_name="resnet18",
num_epochs=2)
# Train
ptf.Train()
predictions = ptf.Infer(img_name="sample.png", return_raw=True);
#Create comparison project
ctf.Comparison("Sample-Comparison-1");
#Add all your experiments
ctf.Add_Experiment("sample-project-1", "sample-experiment-1");
ctf.Add_Experiment("sample-project-1", "sample-experiment-2");
# Generate statistics
ctf.Generate_Statistics();
pip install -U monk-cuda90
pip install -U monk-cuda92
pip install -U monk-cuda100
pip install -U monk-cuda101
pip install -U monk-cuda102
pip install -U monk-cpu
pip install -U monk-colab
pip install -U monk-kaggle
For More Installation instructions visit: Link
Functional Documentation (Will be merged with Latest docs soon)
Features and Functions (In development):
Complete Latest Docs (In Progress)
Copyright 2019 onwards, Tessellate Imaging Private Limited Licensed under the Apache License, Version 2.0 (the "License"); you may not use this project's files except in compliance with the License. A copy of the License is provided in the LICENSE file in this repository.