Introduction to ExeML

ExeML

ModelArts ExeML is a customized code-free model development tool that helps you start codeless AI application development with high flexibility. ExeML automates model design, parameter tuning and training, and model compression and deployment based on the labeled data. With ExeML, you only need to upload data and perform simple operations as prompted on the ExeML GUI to train and deploy models.

You can use ExeML to quickly build models for sound classification, text classification, image classification, predictive analytics, and object detection. ExeML is widely used in industrial, retail, and security sectors.

Image classification: identifies a class of objects in images.
Object detection: identifies the position and class of each object in an image.
Predictive analytics: classifies or predicts structured data.
Sound classification: classifies and identifies different sounds.
Text classification: identifies the category of a piece of text. Currently, only Chinese is supported.

ExeML of the old version supports only the dataset function of the old version.

ExeML Process

Figure 1 shows the ExeML process.

Figure 1 ExeML process

ExeML Projects

Image Classification
An image classification project aims to classify images. You only need to add images and label them. Then, an image classification model can be quickly generated for automatically classifying offerings, vehicle types, and defective goods. For example, in the quality check scenario, you can upload a product image, label the image as qualified or unqualified, and train and deploy a model to inspect product quality.

Object Detection
An object detection project aims to identify the class and location of objects in images. You only need to add images and label objects in the images with proper bounding boxes. The labeled images will be used as a training set for building a model to identify multiple objects or provide the number of objects in a single image. Object detection can also be used to inspect employees' dress code and perform unattended inspection of article placement.
Predictive Analytics
A predictive analytics project is an automated model training application for structured data, which can classify or predict structured data. Predictive analytics can be used for user profile analysis and targeted marketing, as well as predictive maintenance of manufacturing equipment based on real-time data to identify equipment faults.
Sound Classification
A sound classification project identifies whether a certain sound is contained in an audio file. Sound classification can be used to monitor abnormal sounds in production or security scenarios.
Text Classification
A text classification project identifies the class of a piece of text.

Model Deployment Specifications

Different types of ExeML projects support different specifications for model deployment. For details, see Table 1.

**Table 1** Available deployment specifications for different types of projects
Project Type	Available Model Deployment Specifications
Image Classification	Free (CPU) Compute-intensive 3 instance (CPU) Compute-intensive 2 instance (GPU)
Object Detection	Free (CPU) Compute-intensive 3 instance (CPU) Compute-intensive 2 instance (GPU)
Predictive Analytics	Free (CPU) Compute-intensive 3 instance (CPU)
Sound Classification	Free (CPU) Compute-intensive 3 instance (CPU) Compute-intensive 2 instance (GPU)
Text Classification	Free (CPU) Compute-intensive 3 instance (CPU) Compute-intensive 2 instance (GPU)