-
Im trying to follow steps from
https://nvidia.github.io/OpenSeq2Seq/html/installation.html
and
https://nvidia.github.io/OpenSeq2Seq/html/speech-recognition.html#getting-started
to get pretrained…
-
### 🐛 Describe the bug
Run the following code below, change `device` to `cpu` or `mps` to see the difference:
```python
import torch
import timeit
device = "cpu" # cpu vs mps
gru = torch.…
-
sentence_input = Input(shape=(MAX_SENT_LENGTH,), dtype='int32')
embedded_sequences = embedding_layer(sentence_input)
l_lstm = Bidirectional(GRU(100, return_sequences=True))(embedded_sequences)
l_at…
-
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 g…
-
Hi,
Thanks for implementing and publishing this interesting method.
I saw the "cell" type parameter is set to GRU in the file hp_df.csv, however, in Fig. 3 in the paper you showed that you used Bi…
-
Hi,
python train.py
Using TensorFlow backend.
Traceback (most recent call last):
File "train.py", line 9, in
from keras.layers import GRU, Dense, Embedding, ChainCRF, LSTM, Bidirectional,…
-
I am getting the following error, when trying to run the code given.
tensorflow.python.framework.errors_impl.InvalidArgumentError: No OpKernel was registered to support Op 'CudnnRNN' used by {{nod…
-
运行到score, _ = model(x)时，出错，不知道是什么原因呢？TypeError: gru() received an invalid combination of arguments - got (Tensor, Tensor, list, float, int, float, bool, bool, bool), but expected one of:
* (Tensor d…
-
The code is the same：in
layer_stack = [
L.Bidirectional(L.GRU(**config['layer_bgru']), name='layer_bgru'),
L.Dropout(**config['layer_dropout'], name='layer_dropout'),…
-
In the batch translation example, encoder is:
```
class EncoderRNN(nn.Module):
def __init__(self, input_size, hidden_size, n_layers=1, dropout=0.1):
super(EncoderRNN, self).__init__()
…