Description:

tinyms 0.3.2

TinyMS










English | 查看中文
TinyMS is an Easy-to-Use deep learning framework development toolkit based on MindSpore, designed to provide quick-start guidelines for machine learning beginners.

Installation



Distribution
Version
Command




PyPI
x.y.z
pip install tinyms==x.y.z



latest
pip install git+https://github.com/tinyms-ai/tinyms.git


Docker
x.y.z
docker pull tinyms==x.y.z



latest
-




NOTICE: The x.y.z version shown above should be replaced with the real version number.

Please checkout the install document to quickly install or upgrade TinyMS project.
Quick start
Have no idea what to do with TinyMS❓ See the Quick Start to implement the image classification application in one minutes❗
Besides, here are some use cases listed to demonstrate how TinyMS simplifies the code flow for users.
Data loading and preprocess



from tinyms.data import MnistDataset, download_dataset
from tinyms.vision import mnist_transform

data_path = download_dataset('mnist')
mnist_ds = MnistDataset(data_path, shuffle=True)
mnist_ds = mnist_transform.apply_ds(mnist_ds)




Network construction



from tinyms.model import lenet5

net = lenet5(class_num=10)




Model train/evaluation



from tinyms.model import Model

model = Model(net)
model.compile(loss_fn=net_loss, optimizer=net_opt, metrics=net_metrics)
model.train(epoch_size, train_dataset)
model.save_checkpoint('./checkpoint_lenet.ckpt')
···
model.load_checkpoint('./checkpoint_lenet.ckpt')
model.eval(eval_dataset)




Model prediction



from PIL import Image
import tinyms as ts
from tinyms.model import Model, lenet5
from tinyms.vision import mnist_transform

img = Image.open(img_path)
img = mnist_transform(img)

net = lenet5(class_num=10)
model = Model(net)
model.load_checkpoint('./checkpoint_lenet.ckpt')

input = ts.expand_dims(ts.array(img), 0)
res = model.predict(input).asnumpy()
print("The label is:", mnist_transform.postprocess(res))




API documentation
If you are interested in learning TinyMS API, please find TinyMS Python API in API Documentation.
Tutorial
For a more detailed step-by-step video tutorial, please refer to the following website.



Episode
Title
Content
Docs
Status
Update Time




EP01
How to learn Deep Learning? The Most Efficient Way For Beginners!
Teacher's profile+DeepLearning Course Introduction
-
Published
2021.3.30


EP02
How we teach computers to understand pictures? Three Ways to Install TinyMS
It uncovers the magic of computer vision + three ways to install TinyMS (Ubuntu, Win10, Docker)
TinyMS Installation For Beginners
Published
2020.3.31


EP03
Learn Shell Script in 30 Minutes
It covers the essential concepts such as using variables, basic operators, loops & functions and so on. It also gives you an insight by scaling down some real-time scenarios and demonstrating them using the docker container.
Learn Shell Script in 30 Minutes (doc)
Published
2020.4.1


EP04
Learn Python in 30 Minutes(Part I.)
Python installation, basic syntax, primitive data types and operators
Learn Python in 30 Minutes
Published
2021.4.23


EP05
Learn Python in 30 Minutes(Part II.)
Python conditional statements, loop statements, iterators, generators, functions, class, module, advanced usages, and several most commonly used Python libraries in deep learning
Learn Python in 30 Minutes
Published
2022.1.10



Community
For any developers who are not familiar with how TinyMS community works, please find the Contributing Guidelines to get started.
Release Notes
The release notes, see our RELEASE.
License
Apache License 2.0

License

For personal and professional use. You cannot resell or redistribute these repositories in their original state.

Share

• Share on Facebook
• Share on Twitter