TensorRTX反序列fp32模型量化失败,原因是因为numclasses数量不对。当前为v8s_seg分割模型,但是报错,生成的engine文件为0kb故为错误的。

先附上解决方案:参考修改config.h文件

[Convolution]:kernel weights has count 3840 but 32640 was expected,yolov5s生成engine模型失败_yolov5s.engine-优快云博客icon-default.png?t=N7T8https://blog.youkuaiyun.com/pvmsmfchcs/article/details/131388796修改这个config.h文件,然后继续修改

当前分割背景的类别不要算进去,训练的时候,是几个类别,这里就是几个,不要额外加一 

遇见警告如下:

[04/10/2024-15:51:05] [W] [TRT] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[04/10/2024-15:51:06] [W] [TRT] Weights [name=(Unnamed Layer* 346) [Deconvolution].weight] had the following issues when converted to FP16:
[04/10/2024-15:51:06] [W] [TRT]  - Subnormal FP16 values detected.
[04/10/2024-15:51:06] [W] [TRT] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[04/10/2024-15:51:06] [W] [TRT] Weights [name=(Unnamed Layer* 346) [Deconvolution].weight] had the following issues when converted to FP16:
[04/10/2024-15:51:06] [W] [TRT]  - Subnormal FP16 values detected.
[04/10/2024-15:51:06] [W] [TRT] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[04/10/2024-15:51:06] [W] [TRT] Weights [name=(Unnamed Layer* 346) [Deconvolution].weight] had the following issues when converted to FP16:
[04/10/2024-15:51:06] [W] [TRT]  - Subnormal FP16 values detected.
[04/10/2024-15:51:06] [W] [TRT] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[04/10/2024-15:51:06] [W] [TRT] Weights [name=(Unnamed Layer* 346) [Deconvolution].weight] had the following issues when converted to FP16:
[04/10/2024-15:51:06] [W] [TRT]  - Subnormal FP16 values detected.
[04/10/2024-15:51:06] [W] [TRT] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[04/10/2024-15:51:06] [W] [TRT] Weights [name=(Unnamed Layer* 346) [Deconvolution].weight] had the following issues when converted to FP16:
[04/10/2024-15:51:06] [W] [TRT]  - Subnormal FP16 values detected.
[04/10/2024-15:51:06] [W] [TRT] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[04/10/2024-15:51:06] [W] [TRT] Weights [name=(Unnamed Layer* 346) [Deconvolution].weight] had the following issues when converted to FP16:
[04/10/2024-15:51:06] [W] [TRT]  - Subnormal FP16 values detected.
[04/10/2024-15:51:06] [W] [TRT] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[04/10/2024-15:51:06] [W] [TRT] Weights [name=(Unnamed Layer* 346) [Deconvolution].weight] had the following issues when converted to FP16:
[04/10/2024-15:51:06] [W] [TRT]  - Subnormal FP16 values detected.
[04/10/2024-15:51:06] [W] [TRT] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.

onnx->trt F16:Subnormal FP16 value detected_if this is not the desired behavior, please modify-优快云博客icon-default.png?t=N7T8https://blog.youkuaiyun.com/Zhou_yongzhe/article/details/127289947成功之后的

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

光芒再现dev

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值