Hi all, I have modifying the sample.py code from the directory
/usr/src/tensorrt/samples/python/network_api_pytorch_mnist/
to accommodate for INT8 calibration.
Though it ran successfully, I got few warning messages related to the layers in the network created.
Here is the output below, please refer to the WARNING messages. I am unable to understand, why it has come? is it acceptable?. If not acceptable then what could be the solution to avoid these warning messages. Please help me in this regard.
Entered read_calibration_cache
Entered read_calibration_cache
[TensorRT] WARNING: Missing scale and zero-point for tensor (Unnamed Layer* 0) [Convolution]_output, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
[TensorRT] WARNING: Missing scale and zero-point for tensor (Unnamed Layer* 1) [Pooling]_output, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
[TensorRT] WARNING: Missing scale and zero-point for tensor (Unnamed Layer* 2) [Convolution]_output, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
[TensorRT] WARNING: Missing scale and zero-point for tensor (Unnamed Layer* 3) [Pooling]_output, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
[TensorRT] WARNING: Missing scale and zero-point for tensor (Unnamed Layer* 5) [Activation]_output, expect fall back to non-int8 implementation for any layer consuming or producing given tensor
[TensorRT] WARNING: Detected invalid timing cache, setup a local cache instead
Calling deserialize_cuda_engine
Calling create_execution_context()
inputs[0].host len 78400
Start time 1697722782.2533145
End time 1697722803.5443306
Number of inference 10000
Total inference time 21.291016101837158
Total time took to fetch the random test cases 20.22803807258606
Predicted 9723 / 10000 correctly
Thanks and Regards
N.M.Trivedi