-
[debug.zip](https://github.com/alibaba/TinyNeuralNetwork/files/15481413/debug.zip)
-
```
class SAMS(nn.Module):
def __init__(self, num_classes, in1, in2):
super(SAMS, self).__init__()
#####
self.hidden_size1 = 128
self.attention_size…
-
### Is your feature request related to a problem? Please describe.
Problem Statement: Develop an emotion recognition model capable of analyzing text data and accurately classifying the expressed emot…
-
在运行rnncapsule时出现了以下报错。
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
in
----> 1 model = …
-
To work with latest TF package, you'll need to make certain modification to the last part namely RNN codes.
tf.nn.rnn_cell is no longer there and you'll need to use tf.contrib.rnn.*, function name is…
-
Thank you very much for your excellent work and I'm replicating the results from your paper(Fast FullSubNet). I have reproduced the result of m= 2,8, but when m=infinity was reproduced, I could not ge…
-
### 🐛 Describe the bug
I am currently experimenting around `torch.compile` for use with a custom, pure-Python LiGRU implementation, which is a variant of the typical GRU architecture. This is not a…
-
## 🐛 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
-
Hi,
As mentioned [here](https://github.com/tensorflow/tensorflow/issues/63362#issuecomment-2226996257), a drop in model results was observed in the new version of TensorFlow using the new Keras. I …
-
Created by Alya Gomaa via monday.com integration. 🎉