-
### Description
I am getting following error if i load model in `predict ` model. it works perfectly in `eval` mode.
```
ValueError: Incompatible shapes for matmul arguments: (8, 1, 64) and (2…
-
### Description
With t2t 1.6.6, tensorflow 1.8.0, I ran cifar100 with eval early stopping. The cmd failed quickly with crash at tensorboard/backend/event_processing/event_multiplexer.py, GetAccumulat…
-
@cshanbo @lukaszkaiser
Hi, I've read all your discussion in #111 but I don't know your tests' result on segmented Chinese dataset and non-segmented Chinese dataset. I'm using t2t on en-zh translatio…
-
### Description
Hi, I want to use adafactor to replace the Adam in my code; But I do not use the T2T framework;
Based on the google-released BERT-finetune framework, I just copy the source code of y…
-
TFP layers use function arguments for kernel_posterior_fn, kernel_posterior_tensor_fn, kernel_prior_fn, and kernel_divergence_fn (same for bias). Following discussion with fchollet@, wicke@, ashankar@…
-
I'm finding repeatedly that the g2p-seq2seq model generates strangely long pronunciations using the included model. For all sequences up to three letters long, the following strange outputs occur:
…
-
流行り物という事で論文を読んでみた。あまり理解出来てない。
でも勉強会で別の人が当番でこの論文の話をしてくれるので、質問出来る程度の理解まででいいか、という事で、そのメモをここに書いておく。
[Attention Is All You Need](https://arxiv.org/abs/1706.03762)
本家のソースは[Tensor2Tensor](https://github.co…
-
In Readme it says: "This implementation is based on python TensorFlow, which allows an efficient training on both CPU and GPU." Is g2p-seq2seq also able to use CPU only?
I am running it on Ubuntu …
-
Hello!
Is it possible to change inference type for lms from sampling next sentence based on target to calculating perplexity of target sentence as it is without changing too much code?
The way I se…
-
layers/common_hparams.py mentions a hyperparameter "pretrained_model_dir":
"Directory containing a checkpoint for a pretrained model. This will only be used if a new run is being started. Parameter…