The problem with the allocation of memory for labels in mxnet, python

Question

I classify five classes, color, 128x128 pixel images, batch size = 64, using the Generative Adversarial Network. When creating a discriminator module, when execution

discriminator.bind(data_shapes = image_iter.provide_data, label_shapes = [('label', (batch_size, ))], inputs_need_grad = True)

I get an error:

data: (64, 3, 128, 128) label: (64,) Error in operator dloss: Shape inconsistent, Provided=[64], inferred shape=[64,25]

And I do not understand where does the number "25" come from? Operator dloss:

discriminatorSymbol = mx.sym.LogisticRegressionOutput(data = fl5, label = label, name = 'dloss')

I took all the information from this example. And everything works there.

Answer 1

The GAN from this example expects input as (batch_size, channels, 64, 64), but your data is (64, 3, 128, 128). So you get a shape mismatch because the output of your discriminator is 25 instead of 1.

print( mx.visualization.print_summary(discriminatorSymbol, shape={'data':(64,3,128,128)})) gives

Layer (type)                                        Output Shape            Param #     Previous Layer
========================================================================================================================
data(null)                                          3x128x128               0
________________________________________________________________________________________________________________________
d1(Convolution)                                     128x64x64               6144        data
________________________________________________________________________________________________________________________
dact1(LeakyReLU)                                    128x64x64               0           d1
________________________________________________________________________________________________________________________
d2(Convolution)                                     256x32x32               524288      dact1
________________________________________________________________________________________________________________________
dbn2(BatchNorm)                                     256x32x32               512         d2
________________________________________________________________________________________________________________________
dact2(LeakyReLU)                                    256x32x32               0           dbn2
________________________________________________________________________________________________________________________
d3(Convolution)                                     512x16x16               2097152     dact2
________________________________________________________________________________________________________________________
dbn3(BatchNorm)                                     512x16x16               1024        d3
________________________________________________________________________________________________________________________
dact3(LeakyReLU)                                    512x16x16               0           dbn3
________________________________________________________________________________________________________________________
d4(Convolution)                                     1024x8x8                8388608     dact3
________________________________________________________________________________________________________________________
dbn4(BatchNorm)                                     1024x8x8                2048        d4
________________________________________________________________________________________________________________________
dact4(LeakyReLU)                                    1024x8x8                0           dbn4
________________________________________________________________________________________________________________________
d5(Convolution)                                     1x5x5                   16384       dact4
________________________________________________________________________________________________________________________
flatten0(Flatten)                                   25                      0           d5