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
yulibcafe,cpp ,when you use the caffe model, you first revert it and the input shape change from caffe(nchw) to tf mode(nhwc), why you do that instead of using it as original caffe model
The text was updated successfully, but these errors were encountered:
That's an auto-mechanism in MNN, since data buffer from opencv image is nhwc. Then when you copy tensor to the input tensor of network, MNN would automatically transfer it to the target data format.
yulibcafe,cpp ,when you use the caffe model, you first revert it and the input shape change from caffe(nchw) to tf mode(nhwc), why you do that instead of using it as original caffe model
The text was updated successfully, but these errors were encountered: