MemNet

MemNet copied to clipboard

issue about number of parameters

2

Hi, thanks for your sharing. I don't know how to calculate the number of parameters of M6R6. Parameters of memory block are 64x3x3x64x12 + 64x6x1x1x64 = 466944 ≈ 467k. So...

Jee-King

Hi, thank you so much for the source code. Besides, could you please provide the resulting image of the degradation model? I am not familiar with caffe. I test the...

juingzhou

Hi, @tyshiwo , Thanks for your excellent work. I have read the MemNet paper, and I find that in table 2 the Memnet parameters is 677K, I'm confused by the...

Zamirquito

Can you give a test using python caffe

1

Recently I use python caffe to test your model,but the effect is shit.And I use python opencv2.4.11 to read the image,change the input channels to RGB,use the matlab formula to...

akafen

To generate the input of JPEG Deblocking, use MATLAB JPEG encoder to compress images. Could you illustrate the MATLAB JPEG encoder? Is JPEG2000 compress algorithm? or other tools? Thanks

lyatdawn

can't import into matlab

1

layers = importCaffeLayers('MemNet_M6R6_80C64_train.prototxt') Gives the error: Error using nnet.internal.cnn.caffe.CaffeModelReader/importLayers (line 294) The layer 'weight_output_end_01' specifies a Scale layer without a preceding BatchNorm layer. Scale layers are only supported when preceded...

meyert11