-
Hi,
are there any plans to add cuDNN-accelerated versions of LSTM and GRU to the PyTorch backend? Without cuDNN acceleration, the LSTM and GRU are considerably (several times) slower, even when run…
foxik updated
4 months ago
-
Hi,
Thank you for this great work. Do you have any plans to make it possible to explain RNN/LSTM models? Right now I have to make the explanation with LIME and then I plot it with force_plot.
-
Hi sir,
As I am new to seq2seq model.I understand how you construct data and why you are using rnn with lstm.But I want to know whether seq2seq can be used for conversation. please explain the …
-
Running the solutions cell:
ValueError: Trying to share variable rnn/multi_rnn_cell/cell_0/lstm_cell/kernel, but specified shape (200, 400) and found shape (7697, 400).
-
### 🐛 Describe the bug
import torch.nn as nn
import torch as th
# If using CPU as the device, the following codes run perfectly
rnn = nn.LSTM(10, 20, 2).to(device="cpu", dtype=th.bfloat16)
inpu…
-
Hello, I didn't encounter any errors when training small amounts of data, but when I tried to train several Gs worth of data, I received the following error. Could you please advise me on how to fix i…
XLOXL updated
2 months ago
-
When trying to load the pretrained ESIM model for sentence retrieval I get the following error:
```
Exception has occurred: NotFoundError
Key encode_rnn/birnn/bidirectional_rnn/fw/basic_lstm_cell…
-
I notice the word:"added the ability for training recurrent models (with layers conv-lstm[conv_lstm]/conv-rnn[crnn]) for accurate detection on video."
So, the lstm/crnn can be used OCR?
-
What method do you think would be best for noising the LSTM?
End of Noisy Network paper seems to suggest that randomization technique from "Bayesian recurrent neural networks" https://arxiv.org/abs/1…
-
## 🐛 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 profiler…
gaelm updated
3 years ago