-
Hello, I am training a single LSTM layer with these parameters :
number of examples : 27,000
size of sample : (2500, 1 , dtype=float64)
size of target : (250, 1 , dtype=float64)
batch size : 64
activa…
-
The new PaddlePaddle core calls REGISTER_OP macro to fill in information (input, outputs, attributes) of an operator into a global variable of type [OpProto](https://github.com/PaddlePaddle/Paddle/blo…
-
my lstm have all most same prediction value, is that i construct my networks wrong ?
this is my unroll_lstm referece example:
def lstm_unroll(num_lstm_layer, num_lstm_nerual, seq_len, input_size,
…
-
Hi, Hugh
If I want to cost 6 months or more to do perofrmance profiling/tuning, Can you give an priority of following:
\* clTorch
*cl-Caffe
\* deppCL
\* clNN
*othe…
-
Hi,
Thanks for providing this opensource lstm!
From your paper recurrent nerual network regularization, it's said that it will take half a day on NVIDIA K20 GPU, is that for this c…
-
Hi all,
I try to build a [MDN](http://research.microsoft.com/en-us/um/people/cmbishop/downloads/Bishop-NCRG-94-004.ps)-like model with keras. This basically adds a GMM on top of a network, which can …