Main Content

Visualize Deep Neural Networks

Plot training progress, assess accuracy, explain predictions, and visualize features learned by an image network

Monitor training progress using built-in plots of network accuracy and loss. Investigate trained networks using visualization techniques such as Grad-CAM, occlusion sensitivity, LIME, and deep dream.


Deep Network DesignerProgetta, visualizza e addestra le reti di Deep Learning


espandi tutto

analyzeNetworkAnalyze deep learning network architecture
trainingProgressMonitorMonitor and plot training progress for deep learning custom training loops (Da R2022b)
updateInfoUpdate information values for custom training loops (Da R2022b)
recordMetricsRecord metric values for custom training loops (Da R2022b)
groupSubPlotGroup metrics in training plot (Da R2022b)
plotPlot neural network architecture
predictCompute deep learning network output for inference (Da R2019b)
minibatchpredictMini-batched neural network prediction (Da R2024a)
scores2labelConvert prediction scores to labels (Da R2024a)
deepDreamImageVisualize network features using deep dream
occlusionSensitivityExplain network predictions by occluding the inputs (Da R2019b)
imageLIMEExplain network predictions using LIME (Da R2020b)
gradCAMExplain network predictions using Grad-CAM (Da R2021a)
confusionchartCreate confusion matrix chart for classification problem
sortClassesSort classes of confusion matrix chart
rocmetricsReceiver operating characteristic (ROC) curve and performance metrics for binary and multiclass classifiers (Da R2022b)
addMetricsCompute additional classification performance metrics (Da R2022b)
averageCompute performance metrics for average receiver operating characteristic (ROC) curve in multiclass problem (Da R2022b)


ConfusionMatrixChart PropertiesConfusion matrix chart appearance and behavior
ROCCurve PropertiesReceiver operating characteristic (ROC) curve appearance and behavior (Da R2022b)



Training Progress and Performance