Inference Results
Once an initial inference has been run with a model sample dataset and target, you can view performance results on the project dashboard.
The components specified below provide visual representation of a model performance on a selected dataset and help find potential bottlenecks and areas for improvement:
- The Execution Time by Layer pie chart represents information on execution time of each layer group . A tooltip with information on execution time in milliseconds appears when you hover your mouse over the chart.
- The Mean Inference Time bar chart represents mean time of inference on a selected dataset. For example, if you specify 10 runs on each image of a 100-images dataset and the total execution time is 10000 ms, the mean inference time is 10000 ms : 100 images: 10 runs = 10 ms. Detailed information about throughput, latency, total execution time, number of parallel requests, and batch appears when you hover your mouse over the bar chart.
- The Layers Table data table shows each layer of a model. Expand rows representing fused layers to see layers parameters. For details, go to Visualize Model.
- The Visualize original IR and Visualize runtime graph are visualization tools. Go to Visualize Model for details.
Model Analyzer
The Model Analyzer is used for generating estimated performance information on neural networks. The tool analyzes of the following characteristics:
| Characteristic | Unit of Measurement | Explanation |
|---|---|---|
| Computational Complexity | GFLOPs | Represents a number of floating point operations required to infer a model. |
| Number of Parameters | Millions | Represents a total number of weights in a model. |
| Minimum Memory Consumption, Maximum Memory Consumption | Millions of units | A unit depends on the precision of model weights. For example, for FP32 model these parameters must be multiplied by 4 bytes. |
Model analysis data is collected when the model is imported. All parameters depend on the size of a batch. Currently, information is gathered on the default model batch.
To view model analysis data, click the plus button next to a model name on the Configurations page.
A table with characteristics of a model appears:
