-
Notifications
You must be signed in to change notification settings - Fork 1.7k
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
ONNX转换成MNN模型结果错误 #2916
Comments
This comment was marked as outdated.
This comment was marked as outdated.
模型中有些没有训练的fc层是稀疏化矩阵,使用--detectSparseSpeedUp=0 转换,也存在差异 |
ok , 已经复现,排查中 |
我运行debug 工具: 请问如何debug,是不是ConvTranspose 这个操作存在bug? |
ConvTranspose with group + BN / Scale 的合并有 bug ,内部已经修复,等待同步中 |
Marking as stale. No activity in 60 days. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
使用MNN 2.8版本源码编译的转换工具在mac平台,很多onnx转换都正常,但是我现在的onnx 模型转换结果错误。
使用../tools/script/testMNNFromOnnx.py 测试onnx 模型转换结果,输出的值和onnx不一致
TESTERROR enh value error : absMaxV:1.214276 - DiffMax 1.390584
我尝试上传我的onnx文件
The text was updated successfully, but these errors were encountered: