Model Training - Imagery Analysis

Instructions for use

The purpose of Model Training is to conduct neural network Model Training using the generated training data, and iteratively evaluate the model according to Set Parameters to obtain the available neural network model.

SuperMap has built-in open source frameworks such as TensorFlow and Pytorch, and trains Machine Learning or Deep Learning models with different Dataset categories. The overall Training Procedure obtains the network model with better Training Result through multiple epochs, and uses the pre-training model based on large-scale basic training data in the training model to reduce the training time. Improve Model Training efficiency and accuracy through hyperparameter tuning (learning rate, Batchsize, etc.). The desktop-side training tool is suitable for short-cycle Model Training.

Parameter Description

Parameter name Default Parameter description Parameter Type
Train the data path   Specify the generated training data path String
Purpose of the training model Object Detection A purpose of that train data is specified, Provide Object Detection, Binary Classification, Multiple Classification, Scene Classification, Object Extraction, Detect Common Change six uses. Object
Model Algorithm Customize Specify the Model Algorithm String
Train the Config File   Specify the training configuration and ask for that path. String
Training Times 10 Number of times all training data participated in Model Training Integer
Amount of single step operation 1 The number of pictures of single step operation in one training Integer
Learning rate   Magnitude of update of model parameters Double
Training log path   Specify the Save path for the training low String
Load Pretrained Model
(Optional)
false Check to add a pre-trained model path Boolean
Processor type GPU Specifies the processor type String
GPU number 0 Enter the GPU number String
Model storage path   Specify the Result Data storage path String
Model name saved_model Specify the generation data Folder Name String

Output Result

Data folder generated by Model Training.