You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When using export_tensorrt_engine to export an ONNX model, regardless of the batch_size set in the input_sample, the exported ONNX model's output batch_size remains fixed at 1 when inserted with EfficientNMS_TRT.
Steps to Reproduce
Use export_tensorrt_engine to export an ONNX model.
Set different batch_size values in the input_sample.
Observe the output batch_size of the exported ONNX model.
Expected Behavior
The output ONNX model should dynamically adjust its batch_size based on the input_sample's batch_size, instead of being fixed at 1.
Actual Behavior
The output ONNX model always has a fixed batch_size of 1.
Additional Information
Versions
PyTorch version: 2.0.1+cu117
Is debug build: False
CUDA used to build PyTorch: 11.7
ROCM used to build PyTorch: N/A
OS: Microsoft Windows 10 专业版
GCC version: (MinGW-W64 x86_64-ucrt-posix-seh, built by Brecht Sanders) 13.2.0
Clang version: 17.0.5
CMake version: version 3.27.8
Libc version: N/A
Python version: 3.10.13 | packaged by Anaconda, Inc. | (main, Sep 11 2023, 13:24:38) [MSC v.1916 64 bit (AMD64)] (64-bit runtime)
Python platform: Windows-10-10.0.19045-SP0
Is CUDA available: True
CUDA runtime version: 11.7.99
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA GeForce RTX 3060 Ti
Nvidia driver version: 546.33
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
🐛 Describe the bug
Issue Overview
When using
export_tensorrt_engine
to export an ONNX model, regardless of the batch_size set in the input_sample, the exported ONNX model's output batch_size remains fixed at 1 when inserted with EfficientNMS_TRT.Steps to Reproduce
export_tensorrt_engine
to export an ONNX model.Expected Behavior
The output ONNX model should dynamically adjust its batch_size based on the input_sample's batch_size, instead of being fixed at 1.
Actual Behavior
The output ONNX model always has a fixed batch_size of 1.
Additional Information
Versions
PyTorch version: 2.0.1+cu117
Is debug build: False
CUDA used to build PyTorch: 11.7
ROCM used to build PyTorch: N/A
OS: Microsoft Windows 10 专业版
GCC version: (MinGW-W64 x86_64-ucrt-posix-seh, built by Brecht Sanders) 13.2.0
Clang version: 17.0.5
CMake version: version 3.27.8
Libc version: N/A
Python version: 3.10.13 | packaged by Anaconda, Inc. | (main, Sep 11 2023, 13:24:38) [MSC v.1916 64 bit (AMD64)] (64-bit runtime)
Python platform: Windows-10-10.0.19045-SP0
Is CUDA available: True
CUDA runtime version: 11.7.99
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA GeForce RTX 3060 Ti
Nvidia driver version: 546.33
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture=9
CurrentClockSpeed=2100
DeviceID=CPU0
Family=198
L2CacheSize=2048
L2CacheSpeed=
Manufacturer=GenuineIntel
MaxClockSpeed=2100
Name=12th Gen Intel(R) Core(TM) i7-12700
ProcessorType=3
Revision=
Versions of relevant libraries:
[pip3] numpy==1.23.0
[pip3] onnx==1.14.0
[pip3] onnx-graphsurgeon==0.3.12
[pip3] onnxruntime==1.16.3
[pip3] onnxsim==0.4.35
[pip3] paddle2onnx==1.0.6
[pip3] torch==2.0.1+cu117
[pip3] torchaudio==2.0.2+cu117
[pip3] torchvision==0.15.2+cu117
[conda] blas 1.0 mkl defaults
[conda] mkl 2023.1.0 h6b88ed4_46358 defaults
[conda] mkl-service 2.4.0 py310h2bbff1b_1 defaults
[conda] mkl_fft 1.3.8 py310h2bbff1b_0 defaults
[conda] mkl_random 1.2.4 py310h59b6b97_0 defaults
[conda] numpy 1.23.0 pypi_0 pypi
[conda] pytorch-cuda 11.7 h16d0643_5 pytorch
[conda] pytorch-mutex 1.0 cuda pytorch
[conda] torch 2.0.1+cu117 pypi_0 pypi
[conda] torchaudio 2.0.2+cu117 pypi_0 pypi
[conda] torchvision 0.15.2+cu117 pypi_0 pypi
The text was updated successfully, but these errors were encountered: