PaddleOCR icon indicating copy to clipboard operation
PaddleOCR copied to clipboard

paddleocr4 onnx模型转engine出现错误咋解决啊

Open yxl23 opened this issue 1 year ago • 2 comments

🔎 Search before asking

  • [X] I have searched the PaddleOCR Docs and found no similar bug report.
  • [X] I have searched the PaddleOCR Issues and found no similar bug report.
  • [X] I have searched the PaddleOCR Discussions and found no similar bug report.

🐛 Bug (问题描述)

image

🏃‍♂️ Environment (运行环境)

win10 tensorrt 8.5 cuda 11.8

🌰 Minimal Reproducible Example (最小可复现问题的Demo)

trtexec --onnx=rec.onnx --saveEngine=rec.engine

yxl23 avatar Sep 04 '24 05:09 yxl23

错误信息显示:

  1. Dynamic dimensions:输入的维度没有被指定,导致解析失败。
  2. Engine 生成失败:由于输入维度不明确,导致无法正确构建网络引擎。

为了解决这些问题,可以尝试以下几种方法:

  1. 指定输入维度:可能需要在构建 TensorRT 引擎时,明确地设置输入的形状。
  2. 重新检查输入数据:确保输入的形状在推理时是有效的,并且输入与模型结构一致。

GreatV avatar Sep 06 '24 01:09 GreatV

那我应该指定的维度是多少啊

yxl23 avatar Sep 06 '24 02:09 yxl23

This issue is stale because it has been open for 90 days with no activity.

github-actions[bot] avatar Dec 06 '24 02:12 github-actions[bot]