-
## š Bug
Dropout with a manually implemented stacked version of RNN/LSTM/GRU (aka split_fw below) is faster than the standard pytorch RNN/LSTM/GRU module (aka std_fw below).
Here is the profilerā¦
gaelm updated
3 years ago
-
Hello @suriyadeepan, nice repo you got here. I am trying to resolve https://github.com/tensorflow/tensorflow/issues/10862 this bug. I find you functional scan method refreshing. My only question: how ā¦
-
Hi I just installed tflearn and upgraded tensorflow and I can not import tflearn.
I am using python 2.7, anaconda, gpu supported version of tensorflow
I tensorflow/stream_executor/dso_loader.cc:ā¦
-
I try to train a RNN network (seq2seq) with GRU and SRU cells. When training is done with GRU everything is ok, loss is decreasing an accuracy steadily rise. But when switch to GRU after few hours i gā¦
-
I install tensorflow-1.14.0 ,python3.
Here is the error.
tensorflow.python.framework.errors_impl.InvalidArgumentError: seq_lens(30) > input.dims(1)
[[{{node utt_encoder_4/zhuangtai/bidirecā¦
-
According to [a recent paper on LSTM sentiment analysis](https://link.springer.com/chapter/10.1007/978-3-319-39958-4_19), using a bidirectional RNN instead of a regular ("one-way") one might lead to iā¦
-
Hi,
When running `python main.py --batch_size 20 --data data/penn --dropouti 0.4 --dropouth 0.25 --seed 141 --epoch 500 --save PTB.pt` I get the following error:
```
/usr/local/lib/python3.6/diā¦
-
This tutorials helped me to write a single layer unit with CUDA code.
But how to write CUDA code of the multilayer units, like torch/nn/_functions/rnn.py 281?
```
output, hy, cy, reserve, new_weigā¦
haoyz updated
5 years ago
-
If I try to train the model on Visual Genome, this error occurs.
(tensorflow 1.2.1)
Traceback (most recent call last):
File "./exp-visgeno-rel/exp_train_visgeno_attbilstm_strong.py", line 65,ā¦
-
i install tflearn 0.3 and have tensoflow-gpu 0.12.1
got such error
ghost updated
4 years ago