-
### 问题确认 Search before asking
- [X] 我已经查询[历史issue](https://github.com/PaddlePaddle/PaddleDetection/issues),没有报过同样bug。I have searched the [issues](https://github.com/PaddlePaddle/PaddleDetection/iss…
-
## Description
Hi, I'm trying to build my centerNet model with INT8 engine. I read the guide and samples and followed it. [(link)](https://github.com/NVIDIA/TensorRT/tree/main/samples/python/effici…
-
## Description
Cannot build a "yolov4-tiny" TensorRT engine for DLA core on Jetson Xavier NX due to the following error. (I have previously reported this issue on [NVIDIA Developer Forum](https://…
-
Network: yolov3
Config file: configs/yolo/yolov3_d53_mstrain-416_273e_coco.py
We use "configs/mmdet/detection/detection_tensorrt-int8_dynamic-64x64-608x608.py" within mmdeploy for TRT int8 model q…
-
I try to deploy c++ under win10,but i got the error.I have two cuda 10.0 and 11.6 on my computer, and I trained with 10.0.
my conversion command:
`python ./tools/deploy.py configs/mmdet/instance-…
-
TensorRT Version: 8.2.0.6
GPU Type: RTX2080
Nvidia Driver Version: 470.86
CUDA Version: 11.4
CUDNN Version: 8.2.4
Operating System + Version: Ubuntu 18.04
Python Version (if applicable): 3.7.11
…
-
## Description
My network has two inputs and an error occurred during int8 calibration
`[TensorRT] ERROR: 2: [graph.cpp::getDefinition::336] Error Code 2: Internal Error (Assertion mIndex >= 0 faile…
-
**Describe the bug**
使用for-torch 优化模型时出错,以resnest50d为例:
代码如下:
`
origion_model = timm.create_model('resnest50d', pretrained=True)
infer_mode = 'float16' # float32 / float16 / int8_calib / …
-
## Description
I'm currently using Xavier AGX and AGX Orin platforms with 7.1.3 and 8.4.0 versions respectively. Many of the samples can't run because they throw missing data errors. Here are some …
-
**Describe the bug**
```
hf_output [{'generated_text': 'Try without sampling the data.\n\nA:\n\nYou can use the following code to get the data from the database.\n$sql = "SELECT * FROM `table`";\n$r…