-
## 🐛 Bug
This warning gets printed during every single forward pass in PyTorch 1.2. In PyTorch 1.1, it was only printed once.
```
/pytorch/aten/src/ATen/native/cudnn/RNN.cpp:1266: UserWarning: …
-
export rnn.GRU op failed, error message as follow:
AttributeError: No conversion function registered for op type _rnn_param_concat yet.
-
I really appreciate the nice implementation of RNN. I came across a question when I am trying to understand the training procedure.
In line the function feval(x), the variable "grad_params" are init…
-
How to handle it?
**Summary:**
```
2018-09-12 12:26:58.870469: W T:\src\github\tensorflow\tensorflow\core\common_runtime\bfc_allocator.cc:219] Allocator (GPU_0_bfc) ran out of memory trying to …
-
## 🚀 Feature
I would like to request the addition of support for Recurrent Neural Networks (RNNs) in the KFACOptimizer class. Currently, the KFACOptimizer class works for linear and 2D convolution …
-
Hello. When I am trying to train a new model on google colab. I run into the following error:
```
Training new model w/ 3-layer, 128-cell LSTMs
Training on 125,286 character sequences.
Epoch 1/2…
-
I believe this training script only works with tensorflow 1.x so just noting that we should test / upgrade for compatibility with tensorflow 2.0 at some point.
-
Hi!@AlexKuhnle
Sorry to bother you! I met an error when I use "dropout" parameter to create the network as below
_network = [dict(type='retrieve', tensors = ['obs']), dict(type='rnn', size=512, dro…
-
**Hello, thanks a lot for your great job which is very excellent and inspires me a lot.**
**Now I am trying to run your code UCF101_CRNN.py on a Windows PC but facing a Runtime** **problem.**
**I tr…
-
This Paper is about assist Guided Policy Search by using memory which implemented by RNN
https://arxiv.org/abs/1507.01273