mirrors/mmdeploy
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmdeploy.git synced 2025-01-14 08:09:43 +08:00
Code Issues Projects Releases Wiki Activity

Update tensorrt install info (#165)

Browse Source
This commit is contained in:
q.yao 2021-11-03 10:55:50 +08:00 committed by GitHub
parent c52b24c67f
commit 4e168ee1c7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 14 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
docs/backends/tensorrt.md
View File

@ -4,7 +4,9 @@
#### Install TensorRT
Please install TensorRT 8 follow [install-guide](https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html).
Please install TensorRT 8 follow [install-guide](https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html#installing).
**Note**: `pip Wheel File Installation` is not supported yet in this repo.
#### Build custom ops
@ -86,6 +88,17 @@ If the calibration dataset is not given, the data will be calibrated with the da
### FAQs
- Error `Cannot found TensorRT headers` or `Cannot found TensorRT libs`
Try cmake with flag `-DTENSORRT_DIR`:
```bash
cmake -DBUILD_TENSORRT_OPS=ON -DTENSORRT_DIR=${TENSORRT_DIR} ..
make -j$(nproc)
```
Please make sure there are libs and headers in `${TENSORRT_DIR}`.
- Error `error: parameter check failed at: engine.cpp::setBindingDimensions::1046, condition: profileMinDims.d[i] <= dimensions.d[i]`
There is an input shape limit in deployment config: