caffe_srgan
caffe_srgan copied to clipboard
ShenghaiRong
A Caffe Implementation of SRGAN
Hey there, your pixelshuffler works very well, thank you for sharing it!! It makes training very slow, though, because it's CPU, only. I don't suppose you have a GPU (reshape_layer.cu)...
使用您的reshape layer，在make runtest时，遇到问题 ‘const class caffe: ReshapeParameter’没有名为pixelshuffler的成员 请问该如何解决？ 谢谢
Could you please share the revised **test_reshape_layer** with the pixelshuffle? thanks.
Hi, Thank you for sharing the code. If I want to use the pixelshffuler_layer, what should I do? Thanks.
Hi ! Thank you for your sharing resource. I tried to make your files in my caffe. But there are some errors in 'solver.cpp' which I really don't know how...
Which version of Caffe was used for the modified layers? https://github.com/BVLC/caffe/releases I tried with several versions but I can't compile my caffe with the modifications: caffe_srgam/include/layers*.hpp ----> caffe_main/include/caffe/layers caffe_srgam/include/solver.hpp ---->...
what is your version of boost,there is an error when I make caffe with boost1.61 and boost1.64 like this: src/caffe/solver.cpp:107:5: error: no matching function for call to ‘caffe::Net::Net(caffe::NetParameter&, boost::shared_ptr::element_type*)’ net_.reset(new...
Hi, happy to see that you are trying to implement SRGAN using caffe, I am wonder whether you have implemented the PSNR of SRResNet in paper proposed.
