-
Notifications
You must be signed in to change notification settings - Fork 24
New issue
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
使用acuitylite 转yolov5模型包含swish算子,看源码目前只支持hswish #160
Comments
@zjd1988 , 你的问题是用AcuityLite 转 YoloV5 到 tflite格式碰到swish算子不支持吗? Thanks |
@sunshinemyson 暂时没有用tflite-vx-delegate测试转换后的模型,在分析量化后模型的算子种类,然后对照tflite-vx-delegate来看,发现tflite-vx-delegate/op_map.cc源码没有算子,不过看到HardSwish算子,下图是AcuityLite转出的yolov5模型图, 看tflite 的 scheme.fbs没有swish这个算子,swish应该是个自定义op, 目前在想办法解析AcuityLite量化后的tflite模型,然后用python来构造网络,lenet网络验证了下问题不大,想找个yolov5验证下,所以遇到这个问题 |
了解,你有没有原始输入模型?我请同事看看 |
收到 |
@sunshinemyson 你好,还有个疑问,tf-lite的cpu推理结果可以跟tflite-vx-delegate完全对应起来吗? |
@zjd1988 , 我们和CPU之间会有一点精度差异,例如asymmU8的convolution我们会跟CPU有一个量化精度的差异。 |
@zjd1988 , |
No description provided.
The text was updated successfully, but these errors were encountered: