-
Hello.
Is it possible to apply any activation function between hidden states in IndRNN in tensorflow framework?
Currently I don't see any argument similar to "activation"
```
Keyword Arguments…
-
`RNN`s use the zoneout mask of the first step to compute gradients for all steps.
For example, maybe we could change `GRU` backward from
https://github.com/lmnt-com/haste/blob/3d92d702fa68a6705444…
-
Hello,I found a performance issue in the definition of `get_training_set` ,
batzner/indrnn/blob/master/examples/sequential_mnist.py,
[dataset.map](https://github.com/batzner/indrnn/blob/67246b513113…
-
I assume this is not supposed to happen, but I checked the model's parameters after training and these were the values from the final IndRNN layer in my model:
`rnn2.bias
Parameter containing:
tens…
-
I noticed that the zoneout is still applied even after I call model.eval() and I'm assuming that this is not the desired behavior. I'm therefore manually changing the zoneout value to 0 during evaluat…
-
When I run an RNN with the example (e.g., GRU, IndRNN) I get illegal memory access error.
```
import torch
import haste_pytorch as haste
x = torch.rand([25, 5, 128]).cuda()
gru_layer = has…
-
Hi,
I am trying to install haste_pytorch on windows using Pip as following:
```
pip install haste_pytorch
```
However, I am getting this error:
```
WARNING: pip is being invoked by an old …
-
Hi, is there any chance to implement a cuda version of IndRNNCell? the purpose is to speed up processing variable length sequences.
-
Hello @sharvil ,
I been using the CPU IndRNN implementation of hast during my development. The results have been great.
When I moved to production, that presumably will use the cuda version of I…
-
Hello, I found there may be some numerical precision problems in some of the rnn routines.
I compiled the haste_pytorch and modified check function 'self_consistency' at haste/validation/pytorch.p…
w1d2s updated
4 years ago