-
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…
-
## ❓Question
We were trying to convert an rnn model from torch to coreml, which was using the [uisrnn](https://github.com/google/uis-rnn) package. Though the conversion went through fine, we found …
-
```
What feature or additional map(s) coverage are you looking for?
1.
Please add the following maps:
GRU
http://en.wikipedia.org/wiki/Sao_Paulo-Guarulhos_International_Airport
TPE
http://en.wikiped…
-
I tried to inference the following network, but CNTK would finish without any output. But if change the code to return the layers before `rnn_gru_cell_add_91_scope`, it runs OK. Is this because there…
-
你好，我现在大概有50万张图片，如果直接用卷积网络加全连接输出会有一定的过拟合但是验证集也能到80多的精度。可是如果在卷积层和最后全连接输出中间加上双向gru（神经元宽度256，dropout0.5） 就会过拟合特别严重，甚至约训练验证集loss越高，请问是因为数据量太少么？
-
Hi，how can i get these two models :
cnn_model = torch.load('./model/resnet101_with_fft')
model = torch.load('./model/resnet101')
in 'cnn_gru_pytorch.py'
-
### What
Let's support CircleGRU as custom circle operation in compiler FE and onert-micro.
### Why
Some target models for onert-micro contains such pattern. This conversion accelerates the …
-
Stack Overflow
https://stackoverflow.com/questions/63630129/valueerror-grureset-after-false-is-not-compatible-with-grureset-after-true
-
Hi
I am confused about this code for GRU MAC calculation
What I know about LSTM MAC …
-
torch.nn.GRU 's input shape is [[sequence_size, batch_size, hidden_size]](https://pytorch.org/docs/stable/nn.html#torch.nn.GRU).
But your code such as https://github.com/Nrgeup/controllable-text-attr…