-
### Describe the issue
Observe that ONNX model (FP32) executed in C++ runs slower than Python. it's much much worse with TensorRT execution provider.
I've tried exporting a F16 model with `keep…
-
Dear Developers,
I am very new to Tensorrt and quantization. Previously I only use the basic example of Tensorrt to generate engines in FP16 because I thought INT8 will compromise accuracy signific…
-
tensorflow-gpu1.14
CUDA10.1
GPU gtx1080
my_test.json
{
"model_config": {
"model_name": "ssd_resnet_50_fpn_coco",
"input_dir": "/home/liujt/software/tensorrt/data",
"batch_size…
-
### Describe the issue
Inference results are outputting abnormally when using YOLOv7 models with TensorRT EP.
We have confirmed that the results are normal when using CPU and CUDA.
The issue wa…
-
Hi, I'm trying to convert to tensorRT int8 Model using onnx made by keras2Onnx.
My environment is as below:
python=3.7, keras2onnx=1.7, tensorflow=2.2.0, onnx=1.7, onnxconverter_common=1.7
My s…
-
By using [pytorch-quantization](https://docs.nvidia.com/deeplearning/tensorrt/pytorch-quantization-toolkit/docs/index.html) i was able to create TensorRT engine models that are (almost) fully int8 and…
-
Firstly, thanks for this project that is of high quality.
I converte my model with torch2trt in code:
...
model_trt_float32 = torch2trt( my_model,[ims],max_batch_size=32);
model_trt…
-
### System Info
4*A800 80G
### Who can help?
@Tracin
### Information
- [X] The official example scripts
- [ ] My own modified scripts
### Tasks
- [X] An officially supported tas…
-
## Description
what is the right way to calibrate a hybrid quantization model ？
i built my tensorrt engine from ONNX model by the sub code, i selected the ``` class Calibrator(trt.IInt8EntropyCa…
-
## Description
When I use TensorRT for int8 quantization, I always encounter the accuracy fallback to fp32. The trt.BuilderFlag.OBEY_PRECISION_CONSTRAINTS parameter does not solve the issue. W…