-
## Description
I believe it is because that onnx cannot load the model which is large then 2GB.
For example, https://github.com/onnx/onnx-tensorrt/issues/818 have the similar issues with me
…
-
Hi,
1. Exporting .pt to .onnx works:
```
python export.py --weights yolov7-tiny.pt --grid --simplify
Import onnx_graphsurgeon failure: No module named 'onnx_graphsurgeon'
Namespace(batc…
-
## Bug Description
After trained a Q/DQ-inserted fake-quantized resnet, we did `model.half()` and then `torch.jit.trace()` to generate [this torchscript model](https://drive.google.com/file/d/1SeY…
-
## Description
I encountered the following error when building the bert-base model with trt 8.5.3 use ```builder.py``` on T4 GPU. Is this a bug for 8.5.3 on T4 ?
The errors in FP16:
```
…
-
Unfortunately I dont get any video input from my usb camera since OpenGL fails:
I…
-
### 问题描述 Issue Description
[yanjiaxing@in-dev-docker:/apollo/data/Paddle/build]$ make -j8
Scanning dependencies of target extern_eigen3
Scanning dependencies of target copy_kernels_command
Scannin…
-
### Checklist
- [X] I have searched related issues but cannot get the expected help.
- [X] 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/faq.md) bu…
-
### Why TorchBench?
1. A benchmark maintained by the PyTorch community officially
2. `torchbenchmark/models` contains copies of popular or exemplary workloads
3. `torch.utils.benchmark.Timer` has …
-
[10/17/2022-21:53:09] [I] TensorRT version: 8.4.1
[10/17/2022-21:53:10] [I] [TRT] [MemUsageChange] Init CUDA: CPU +330, GPU +0, now: CPU 338, GPU 443 (MiB)
[10/17/2022-21:53:20] [I] [TRT] [MemUsageC…
-
## Description
Hi, I have a quantized Yolov5s ONNX model;
When I use ONNX runtime to infer this model, I got the mAP of 36.8;
But when I use C++ TRT backend, enable with INT8 inference, the mAP…