TensorRT
TensorRT copied to clipboard
NVIDIA
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
## Description ## Environment **TensorRT Version**: 8.4.1.5 **NVIDIA GPU**: 1080ti **NVIDIA Driver Version**: 450 **CUDA Version**: 11.0 **CUDNN Version**: 8.1.0 **Operating System**: **Python Version (if applicable)**: **Tensorflow Version (if applicable)**:...
## Description When I run `polygraphy run --onnxrt ./my_onnx.onnx --save-inputs onnx_inputs.json` to save the inputs data of my onnx model, I am very puzzled by this onnx_inputs.json The content of...
onnx model : [link](https://drive.google.com/file/d/1xJyU7CnVqzc8tBU0_ruewTD1fgxrz1EA/view?usp=sharing) used trtexec to generate the engine: trtexec --onnx=test_quant_sim.onnx --saveEngine=test_quant_sim.engine --workspace=4096 --int8 --fp16 --noTF32 --verbose --noDataTransfers --separateProfileRun --dumpProfile --useCudaGraph > test_quant_sim.log When generating the engine for this...
## Description Hi, I am working on deploying MobileNetv2 on Jetson Nano and am having trouble converting these networks from TensorflowV2.5.0 Object_detection_api to TensorRT. I tried to convert the .onnx...
## Description The same steps can be generated engine(int8) when using RTX4000(tensorrt 8.0, cuda11.3), but when using Jeston AGX orin(tensorrt 8.4, cuda11.4) reports an error(an illegal memory access was encountered)....
When using TRT8.4 to generate a model with FP16 precision, following warning occurred: [07/27/2022-23:16:56] [W] [TRT] Weights [name=Conv_13703 + Add_13709 + onnx::Mul_4732_clone_3 + (Unnamed Layer* 7047) [Shuffle] + Mul_13729.weight] had...
## Description failed to serialize the network for NVDLA standalone mode, it gives the crash log ```cpp DLA Cores: 2 4: [standardEngineBuilder.cpp::engineValidationForSafeDLAMode::1519] Error Code 4: Internal Error (Safe DLA is...
## Description The inference results of the model converted from ONNX with trtexec are clearly different from the inference results of the original ONNX. ## Environment **TensorRT Version**: 8.0.1 **NVIDIA...
Hi everyone, I have an input of size [1, 64, 6, 15, 20], and when I apply torch's ConvTranspose3d on it with the following arguments ConvTranspose3d(64, 32, kernel_size=(3, 3, 3),...
