-
Hi all,
I am trying to do sequence tagging (i.e., a label for each token in a sequence) using the `BiSequencer` model with LSTMs and have been running into some trouble trying to determine how to form…
-
On a high level this is an interface that would be nice to have for rnns:
```
(weights, state) = initrnn(input)
(output,state) = rnn(weights,input,state)
````
state can be used to encapsulate var…
-
Having this issue while running seld.py script. Could an…
-
이 분야 직접 판 적은 없고 그냥 트렌드 논문 몇개 주워읽는 정도로만 알아서, 틀린 내용이 있거나 횡설수설 할수도 있다.
**Meta Info.**
- [https://arxiv.org/pdf/2209.14916v1.pdf](https://arxiv.org/pdf/2209.14916v1.pdf)
- [https://guytevet.github.…
-
During testing of LSTM operator with non-standard layout (layout=1), new verify tests have been created to recreate a scenario where input shapes have to be transposed before calling `lstm`. Verify te…
-
Hi, I wonder what batch_size do you use for each neural model? It is really hard to reproduce results in Table 3 without knowing this parameter...
-
When compiling the dockerfile with `docker build .` error is raised at make install step of marian compilation:
```
CMake Error at src/3rd_party/sentencepiece/cmake_install.cmake:41 (file):
file …
-
tf version: 2.4.1
python: 3.6
Using the Bidirectional layer is returning the following error in graph mode
```
ValueError: Shape must be rank 1 but is rank 2 for '{{node cond/ReverseSequence}} =…
-
Tried various methods
The following are the log and error messages
[0317 23:46:02 @logger.py:87] Argv: train1.py test1
[0317 23:46:02 @parallel.py:195] [MultiProcessPrefetchData] Will fork a da…
-
I love your tool, I think it's very interesting. Are you planning on adding a support for more types of layers in the future?
Thanks.