-
I was trying to run this model on my custom data. I got stuck with this error. I am not sure whether is this due to dynet version issue. I am attaching the error log below. It will be great if you can…
-
It looks like I am doing something extremely stupid, so please bear with me. I am trying to run simple an4 training example from your README.md. It seems like training during the first epoch goes fine…
-
Hi,
I tried to feed my conv layer output with size [None, 12, 8, 1024] to a LSTM layer, and I tried to use ConvLSTM2D but it said the input dimension should be 7 while my conv output is 4, appar…
-
Trying to Reshape the Output from the Embedding Layer but unsuccessful. below is the code:
```
main_input = Input(shape=self.input_shape)
embedded = Embedding(self.alphabet_size, self.embedding…
-
### System information
- **Have I written custom code (as opposed to using a stock example script provided in TensorFlow)**:
N/A
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**:
m…
-
Splitting this off from #370, which will remain for tensorflow2 conversion. I would prefer this route if we can get it to work. Asking for help from the community on this one.
One example of a pyto…
ghost updated
2 years ago
-
Hi,
I have a NN in which I train a seq-2-seq model.
I want to combine word-level and character-level information. Currently I get an exception saying ``setting an array element with a sequence``…
-
Hi all,
I am currently trying to write an implementation of RNN for language modelling in Keras (in the spirit of RNNLM from Mikolov ([see here](http://www.fit.vutbr.cz/~imikolov/rnnlm/)), so in a …
-
batch_size_per_card 只能调到8，改成16就报错
这是在8的时候显卡使用情况
:
def __init__(self, classes_num: int):
super().__init__()
self.hidden_size = 128
…