We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
onnx部署没问题,tensorrt部署有问题 tensorrt是图像侧没有问题,文本侧的向量不对,导致计算相似不对,有没有解法
The text was updated successfully, but these errors were encountered:
你好,想请教一下配环境的问题。我开在了cuDNN版本不对。(8.3.2而不是8.6.0)
Sorry, something went wrong.
我也遇到一样问题,使用tensorrt 10.6.0,库api有些调整,基本上是把binding相关的接口改到io_tensor,还有使用context.execute_async_v3接口启动,为此调整了tensorrt_utils.py中的内容,改完之后测试,将onnx出来的feature和trt出来的feature做内积,发现图像模型99+,基本一致,但是文本模型出来分别是68、79、78、74,不管fp16还是fp32都这样,直接用trtexec转换也一样,导致图文内积偏差较大,怀疑是由于api更新但是tensorrt_util.py里有哪个环节还没匹配上导致的
No branches or pull requests
onnx部署没问题,tensorrt部署有问题
tensorrt是图像侧没有问题,文本侧的向量不对,导致计算相似不对,有没有解法
The text was updated successfully, but these errors were encountered: