ComplexUpSampling2D is too slow compiling about cvnn HOT 7 CLOSED

Thank you for the feedback. I will try to give it a look.
Indeed, it's hard for me in many ways to keep up with TensorFlow performances. However, if it's too much I will try to take a look.

Does this happen with bilinear or nearest interpolation? or both?
If you can, could you provide an idea of time difference? (any code to test, exact time of one vs the other? any gist?)

Regards,

from cvnn.

This code is taking 15 minutes to compile

in1 = Input(shape=(64,64,1),dtype=tf.complex64)
out = ComplexUpSampling2D()(in1)
model = Model(inputs=in1, outputs=out)

I proved disabling the eager execution, but it does not improve.

from cvnn.

To compile! I miss-read and thought it was to run. Ok, there is definitively a problem. I will take a look. Thank you!

from cvnn.

No. Once compiled, it runs very well.

from cvnn.

Great, I created the gist and indeed it takes ages to compile.

One important remark, the code you sent me you use the Input layers, is that from TensorFlow? If so, be careful! The last time I checked, even if you use complex64 it casts the input to float32 and it tells you nothing. Probably it changed in newer versions but maybe it didn't. Is better if you use cvnn.layers.complex_input.

from cvnn.

I proved the input layer in this gist, and it seems to work fine

from cvnn.

Since Version 1.1.70 this bug is fixed.
However, as it can be seen here, the align_corners parameter is not longer supported.

from cvnn.