DeepLearningExamples/PyTorch/Classification/ConvNets/triton/scripts
Piotr Marcinkiewicz 5c33a8289b
[ResNet50/PyT] Triton perf fix
* ResNet50/PyT Triton ONNXruntime fix with env flag

Scripts were modified to fix missing ORT_TENSORRT_FP16_ENABLE flag for
Triton Inference Server with ONNXRuntime and TensorRT execution provider.

* ResNet50/PyT TensorRT FP16 support fixed

ONNX to TensorRT converter was fixed to force FP16 precision for
TensorRT networks.
2021-06-16 16:04:22 +02:00
..
docker [ResNet50/PyT] Triton perf fix 2021-06-16 16:04:22 +02:00
benchmark.sh [COnvNets/Pyt] Triton Deployment 2020-10-14 20:43:50 +02:00
download_data.sh [ConvNets/PyT] Triton and performance numbers updated 2021-04-20 12:54:18 +02:00
get_metrics_static.sh [COnvNets/Pyt] Triton Deployment 2020-10-14 20:43:50 +02:00
process_dataset.sh [ConvNets/PyT] Triton and performance numbers updated 2021-04-20 12:54:18 +02:00
process_output.sh [COnvNets/Pyt] Triton Deployment 2020-10-14 20:43:50 +02:00
setup_environment.sh [ConvNets/PyT] Triton and performance numbers updated 2021-04-20 12:54:18 +02:00
setup_parameters.sh [ResNet50/PyT] Triton perf fix 2021-06-16 16:04:22 +02:00