You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@liushuan I have successufully run your provided code and got proper face region on some images.
However, I still do not got the same output between MNN and CAFFE with the same model.
If I had a input file(just been decoded by opencv, and have been substracted by mean value and normed, in NCHW layout ), how to send this input file to MNN to get same output ?
The text was updated successfully, but these errors were encountered:
@liushuan I have successufully run your provided code and got proper face region on some images.
However, I still do not got the same output between MNN and CAFFE with the same model.
If I had a input file(just been decoded by opencv, and have been substracted by mean value and normed, in NCHW layout ), how to send this input file to MNN to get same output ?
Hello, I encountered the same problem, have you solved it?
@jayle19930918 Not yet. I try to compare the first layer(Convolution) output between Caffe and MNN, while MNN has transformed the output that I could not make sure that whether it was the true output or not.
@liushuan I have successufully run your provided code and got proper face region on some images.
However, I still do not got the same output between MNN and CAFFE with the same model.
If I had a input file(just been decoded by opencv, and have been substracted by mean value and normed, in NCHW layout ), how to send this input file to MNN to get same output ?
The text was updated successfully, but these errors were encountered: