-
I am trying to use t2t for text summarization. However, I didn't find any documents that describe how to set the hyper-parameters. For example, how to limit the decoding length?
So, could someone t…
-
**My error**
(venv) developer@ubuntu:~/Desktop/sphinx-source$ g2p-seq2seq --interactive --model_dir /home/developer/Desktop/sphinx-source/pocketsphinx/model/
Traceback (most recent call last):
Fi…
-
### Description
####cmd
```
t2t-trainer --registry_help
#export CUDA_VISIBLE_DEVICES=""
PROBLEM=translate_enzh_wmt32k
MODEL=transformer
HPARAMS=transformer_base_single_gpu
HOME=`pwd`
DATA_D…
-
I'm interested in adding static inputs to sequence problems (transformer model). Specifically, I'd like to add a multihot vector to every FFN layer in the decoder stack. My current attempt has been to…
-
### Description
I am running tensor2tensor in a Kubernetes container environment. I find that no matter how many GPU I allocate to the container, tensor2tensor will always be able to use up all GPU…
-
Thanks for sharing the code.
I was trying to run the code, but this is what I got:
```
./main/gen_orig.sh: line 6: t2t-datagen: command not found
```
BTW, how did you run BLEU evaluation on C…
-
Hi,
I installed g2p using setup.py but while running the interactive command:
/usr/local/bin/g2p-seq2seq --interactive --model_dir g2pdict
i am getting the following error
INFO:tensorflow:Import…
-
Hi.
Is it possible or is it planned to build an interface to store model in memory and then decode sentence passed.
I want to load model and test it dynamically. Creating a text file, then launchin…
-
In `T2TModel` there is
```python
# Replace the two methods below in order to add custom SessionRunHooks to
# the training procedure.
@staticmethod
def train_hooks():
return []
@staticmeth…
-
I invoked the Dataflow compute embeddings job as follows
```
- python2
- -m
- code_search.dataflow.cli.create_function_embeddings
- --runner=DataflowRunner
- -…
jlewi updated
5 years ago