Peter Dolan ac6a9d9a51 Make Flux.onehot accessible in the MNIST example ... Alternatively, line 4 could be rewritten to data = [(trainfeatures(i), Flux.onehot(trainlabel(i), 0:9)) for i = 1:60_000]		2017-06-23 16:57:08 -07:00
..
char-rnn.jl	use fancy new callback api	2017-05-01 14:23:48 +01:00
integration-mx.jl	replace old shape inference system	2017-03-17 16:34:54 +00:00
integration-tf.jl	fix tensorflow dep	2017-04-27 12:48:11 +01:00
MNIST.jl	Make Flux.onehot accessible in the MNIST example	2017-06-23 16:57:08 -07:00
translation.jl	update translation model	2017-06-03 15:52:34 +01:00