-
### Description
following the instruction and got this error:
AttributeError: 'HParams' object has no attribute 'layer_types'
### Environment information
```
OS: Linux Ubuntu 16.04
tensor2te…
-
### Description
When running t2t-decoder script ( En-De transformer-big) on a model which was trained on 8 GPUs using DistributedMirrorStrategy.
I get the following error
ValueError: Tensor("bod…
assij updated
3 years ago
-
### Description
from tf.mesh there is the transfomer dataset code that imports this function
```
from tensor2tensor.data_generators.ops import pack_sequences_ops
```
the code seems to be in the…
-
I have been using beam size of 3 and alpha 1.0 for beam search decoding looks like it is very slow .
Greedy search takes around 30-40 seconds for generating a sequence of length 250 words.
but beam…
-
### Description
I have used the available checkpoints for get the English to German translation task to run.
I observed that some outputs given by the model are wrong and the model fails for certain…
-
### Description
universal_transformer+dot_product_relative
### Environment information
OS: centos7.1
# Steps to reproduce:
export PATH=$PATH:/usr/local/python3/bin
PROBLEM=translate_ende_wmt32k
…
-
Hi I was wondering why the maximum batch size is ~100 using a GPU with ~11GB of RAM whereas in the [tensor2tensor](https://github.com/tensorflow/tensor2tensor) the maximum batch size there is 1024?
-
### Description
Problem: *CNN_dailymail*
Model: Transformer
hparams: transformer_prepend, transformer_base_v2
When I train the model with *transformer_prepend* hparams, the outputs of the de…
-
In 1d attention, the dimensions do not have to agree because the decoder input just consults the encoder output as memory, and the memory length can be different from the query length. However, it see…
-
Propose contributing a data generator for the following two problems involving brain tissue imaging, in-situ hybridization, and microarray data from the the [Allen Brain Atlas (human data)](http://hel…