-
when i run the code, I meet the following problem. I hope that you can help me. Thanks.
(pytorch_gpu) G:\RNN-Capsule>python main.py --rnn_type LSTM --name_model 'LSTM-Capsule' --data_dir ./data-rt-a…
ZXXSG updated
5 months ago
-
Your bidirectional LSTM's implementation has a mistake. ```go_backwards=True``` in LSTM (rnn_1b, rnn_2b) is only reverse the input before using LSTM, so you have to reverse the output of LSTM before …
-
With the current Flux RNN design, where each data batch is a Vector of `length = seq_length` and whose elements are of size `[features, batch_size]`, I'm afraid it misses some performance opportunitie…
-
i have saved the model and want to use the model to predict. but i always got error. my predict code as follows:
```vocab = open('data/latex_vocab.txt').read().split('\n')
vocab_to_idx = dict([(v…
-
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
3 months ago
-
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
1 month ago
-
This is not a feature suggestion per so, but a question about this awesome package for Weka.
I was wondering if it is possible to define a configuration for a RNN such as it can be considered a bid…
-
The architecture in the paper suggests unidirectional RNNs. Is there any reason why you used bidirectional RNNs in neural_transducer.py ?
-
**Describe the bug**
The ONNX [LSTM operator](https://github.com/onnx/onnx/blob/master/docs/Operators.md#attributes-26) states that the `activations` attribute is optional. The [LSTM backend implem…
samgd updated
5 years 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…