在Julia中的tf.nn.conv2d_transpose吗？

Question

Hello

A simple question but I don't find it: What is the equivalent of tf.nn.conv2d_transpose in Julia ?

Moreover, I have this link with some Julia commands for TensorFlow: https://github.com/malmaud/TensorFlow.jl/blob/master/docs/src/ops.md

Do you know an other link with more or other commands ?

Thank you

Answer 1

Looking at a part of the logistic regression example on the github page for the julia wrapper:

https://github.com/malmaud/TensorFlow.jl

Y=nn.softmax(X*W + B)
Loss = -reduce_sum(log(Y).*Y_obs)
optimizer = train.AdamOptimizer()
minimize_op = train.minimize(optimizer, Loss)
saver = train.Saver()

It looks like the TF packages are mimicked in Julia, and I specifically see the nn package referenced in the example as nn.softmax , so extrapolating from that example it must be nn.conv2d_transpose .