Training and Inference
Last updated
Last updated
Computer vision models can be used to classify images, detect objects and segment classes in imagery and videos. The Rendered.ai platform gives users the ability to train computer vision models using datasets from their Datasets Library, and use these models to make predictions against other Datasets. This tutorial will show you how to train and use a Detectron2 computer vision model on the Platform.
To train a computer vision model, first navigate to the Datasets Library and select the Dataset to be used for training the model. In this example we will be training the model using a synthetic dataset.
Click on the + icon next to Models in the right-side panel. Fill in the form then click the Create button to start training the model. Some parameters are specific to the model Architecture.
Name
The name to give the computer vision model.
Description
The description to give the computer vision model.
Dataset
The dataset split into train and validation sets, used during training the computer vision model.
Class Mapping
Maps dataset classes to a new set of classes.
Architecture
The model architecture used for training the model.
Hyperparameters
A list of basic parameters that are specific to the model architecture, the list below are specific to Detectron2 - Object Detection: Training Weights - The starting weights for the model, this can be set to random weights, ImageNet or a model previously trained on the platform. Train/Validation Split - Percentage of the dataset used for training and validation. Alternatively, you can specify a validation dataset. Epochs - The number of training epochs to run. Base Learning Rate - The base learning rate used by the learning rate scheduler. Seed - The random seed setting for training. Extra Args - Additional arguments passed to the Detectron2 configuration.
After the training parameters have been configured, click the Create button to create the training job. Training will begin once compute has been provisioned, and any preprocessing on the dataset is complete. Once the model training has begun, we can track the training status using the right-hand panel on the Models Library.
Once training is complete, the model is ready to be used for inference jobs, where we can make predictions against another dataset.
To run inference against the computer vision model, click the + icon next to Inferences in the right-hand panel on the Models Library.
Select the Dataset to run through the model and a class mapping if necessary. The class mapping will be used to map dataset classes to a new set of classes (ideally the same set of classes used by the model). Click the Create button to start the Inference job.
Once complete, we can view the results of the inferences in the Inference Library. If ground truth data existed in the input dataset, additional metrics are generated that can be seen in the right-hand panel of the Inference job, this includes:
Overall metrics and Class-specific metrics for Precision, Recall, F1 and mAP.
Plots for Confusion Matrix, PR Curve and ROC Curve.
To view the predictions from Inference, navigate to the Dataset Image Viewer by clicking the Go-To icon at the top of the right-side panel. This will navigate you to the Dataset Image Viewer.
You can toggle on/off the ground truth and inference layers as desired, turn on/off labels including prediction confidence.
