-
```
Traceback (most recent call last):
File "C:\Users\xion\Anaconda2\envs\tensorflow-gpu\lib\site-packages\tensorfl
ow\python\client\session.py", line 1322, in _do_call
return fn(*args)
F…
-
Hello,
I am doing some tests with your example:
https://keras.rstudio.com/articles/examples/lstm_seq2seq.html
Instead of LSTM layers in the enocder/decoder I would like to have bidirectiona…
-
I am getting the following error. This has occured after adding extra GRU and bidirectional rnn layers to my existing model. Can someone please explain what these mean?
```
INFO:tensorflow:Init TPU …
-
Following #272, unidirectional GRUs are implemented with stubs.
Next step is to add support for the reverse time direction. Ideally input shapes should be the same as PyTorch or Chainer.
-
Hi,
I am currently testing medaka 0.6.2 on GPUs using the promethion machine with its Tensor V100 socket.
I subset the origina file for testing to a single contig to polish, only working with …
-
```python
import os
from keras.models import Model
from keras.layers.core import Dense, Dropout, Activation, Reshape, Permute, RepeatVector, Lambda
from keras.layers.convolutional import Conv2D, C…
-
i run the train.py and the cuda memory just get larger after serveral epochs,and here is the strange thing: if i don't create new batches use the same data, the cuda memory usage stays still,but if i …
-
Hi,
so working with version 0.4.4 now.
There are a few things which are still unclear to me when using custom metrics and trying to load the saved_models.
def GRU_test(x_train,y_train,…
-
Thanks for the great work !
I am also trying to use the pertained model to evaluate the test set of CNN / Daily Mail summarization dataset. However, I keep having an error:
FailedPreconditionError…
-
Hey I tried to implement your paper in keras on EMODB database
where time step is 300
and 5 conv2d layers followed by one blstm and attention layer
training size is (339,300,40,30)
but not getting…