View training results
View model training results to evaluate your model performance.
The View Training Results page provides detailed insights into the training process and evaluation metrics of your computer vision model. By examining the training configuration, evaluating metrics, and visualizing training graphs, you can assess the model’s performance and make informed decisions regarding its deployment.
Training Details
Upon completion of model training, you can click on the model in the models table to access the details view. Here, you’ll find comprehensive information about the model’s training configuration and evaluation metrics:
Training Configuration
The training configuration section outlines the parameters and settings used during model training. This includes details such as the dataset used, training epochs, batch size, learning rate, and model architecture.
Evaluation Metrics
Classification Accuracy
This metric measures the proportion of correctly classified images in image classification models. It indicates the model’s overall accuracy in predicting the correct class label for input images.
Mean Average Precision (mAP)
mAP is a commonly used metric for object detection models. It evaluates the precision-recall curve across different object categories, providing a comprehensive measure of the model’s detection performance.
Precision
Precision measures the proportion of true positive detections among all positive predictions made by the model. It indicates the model’s ability to minimize false positives.
Recall
Recall measures the proportion of true positive detections among all ground truth positive instances. It indicates the model’s ability to capture all relevant objects while minimizing false negatives.
Training Graphs
The details view also includes training graphs that visualize the runtime metrics of the training process. These graphs provide insights into the model’s performance and convergence over time. Commonly displayed metrics include loss curves, accuracy curves, and learning rate schedules.
Model Evaluation and Deployment
In addition to reviewing training results, you can try out the trained model directly within the page. This allows you to perform inference tasks on sample data and evaluate the model’s predictions in real-time. Furthermore, you’ll find various deployment options available, enabling you to deploy the model for production use or integrate it into your applications seamlessly.
Get Started
Explore the training results of your computer vision model today to gain valuable insights into its performance and capabilities. By examining training configuration, evaluating metrics, and visualizing training graphs, you can make informed decisions regarding model deployment and optimization. Should you have any questions or require assistance interpreting training results, our support team is available to provide guidance and assistance. We’re committed to helping you unlock the full potential of your computer vision models for your applications and projects.
View training results
View model training results to evaluate your model performance.
The View Training Results page provides detailed insights into the training process and evaluation metrics of your computer vision model. By examining the training configuration, evaluating metrics, and visualizing training graphs, you can assess the model’s performance and make informed decisions regarding its deployment.
Training Details
Upon completion of model training, you can click on the model in the models table to access the details view. Here, you’ll find comprehensive information about the model’s training configuration and evaluation metrics:
Training Configuration
The training configuration section outlines the parameters and settings used during model training. This includes details such as the dataset used, training epochs, batch size, learning rate, and model architecture.
Evaluation Metrics
Classification Accuracy
This metric measures the proportion of correctly classified images in image classification models. It indicates the model’s overall accuracy in predicting the correct class label for input images.
Mean Average Precision (mAP)
mAP is a commonly used metric for object detection models. It evaluates the precision-recall curve across different object categories, providing a comprehensive measure of the model’s detection performance.
Precision
Precision measures the proportion of true positive detections among all positive predictions made by the model. It indicates the model’s ability to minimize false positives.
Recall
Recall measures the proportion of true positive detections among all ground truth positive instances. It indicates the model’s ability to capture all relevant objects while minimizing false negatives.
Training Graphs
The details view also includes training graphs that visualize the runtime metrics of the training process. These graphs provide insights into the model’s performance and convergence over time. Commonly displayed metrics include loss curves, accuracy curves, and learning rate schedules.
Model Evaluation and Deployment
In addition to reviewing training results, you can try out the trained model directly within the page. This allows you to perform inference tasks on sample data and evaluate the model’s predictions in real-time. Furthermore, you’ll find various deployment options available, enabling you to deploy the model for production use or integrate it into your applications seamlessly.
Get Started
Explore the training results of your computer vision model today to gain valuable insights into its performance and capabilities. By examining training configuration, evaluating metrics, and visualizing training graphs, you can make informed decisions regarding model deployment and optimization. Should you have any questions or require assistance interpreting training results, our support team is available to provide guidance and assistance. We’re committed to helping you unlock the full potential of your computer vision models for your applications and projects.