hxch

I have the same problem as well......

But it happened when I run the convertCaffe.py. (the process of generating the prototxt and caffemodel) How could I solve the issue?

How do you turn the prototxt to in-place mode? Could you please show me an example?

Do you mean set the 'in_place' True in relu, bn and scale ?

I added 'engine: CAFFE' to some of the convolution layers and the caffemodel is generated successfully. Thank you so much!