class tensorrt.Profiler(self: tensorrt.tensorrt.Profiler) → None

When this class is added to an IExecutionContext, the profiler will be called once per layer for each invocation of IExecutionContext.execute() . Note that IExecutionContext.execute_async() does not currently support profiling.

The profiler will only be called after execution is complete. It has a small impact on execution time.

report_layer_time(self: tensorrt.tensorrt.Profiler, layer_name: str, ms: float) → None

Reports time in milliseconds for each layer. This function should be overloaded by classes derived from IProfiler.

  • layer_name – The name of the layer, set when constructing the INetworkDefinition .
  • ms – The time in milliseconds to execute the layer.