tensor2tensor
tensor2tensor copied to clipboard
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
### Description I run this command 't2t-trainer --problem=librispeech --model=transformer --data_dir=~/dataset/t2t/librispeech/ --output_dir=. --hparams_set=transformer_librispeech --worker_gpu=1' and it's stuck after printing 'Successfully opened dynamic library libcublas.so.10.0'. Then I set TF_CPP_MIN_VLOG_LEVEL=2, it keeps printing...
### How to resolve this error? I am running this code on Jupyter notebook. I have imported `tensor2tensor` and `tensorflow` packages, however, this error arises. Can anyone assist what is...
### Description use_vocab_from_other_problem seems to return a function instead of a problem instance I could directly change vocab_filename, but since this is the recommended approach, guess i better ask. ......
### Description TensorFlow 2.0 has no attribute `to_float`. ### Environment information ``` OS: Windows 10 Home Edition $ pip freeze | grep tensor mesh-tensorflow==0.1.4 tensor2tensor==1.14.1 tensorboard==2.0.1 tensorflow==2.0.0 tensorflow-datasets==1.3.0 tensorflow-estimator==2.0.1 tensorflow-gan==2.0.0...
### Description The `t2t-trainer` command fails to run. ### Environment information ``` Google Colab environment. In fact, you can just reproduce this problem merely by executing the notebook https://github.com/tensorflow/tensor2tensor/blob/master/tensor2tensor/notebooks/Transformer_translate.ipynb in...
Cheap, localized solution to the bug described in #1911 For the TF2 codepath, provide additional two methods to the `DummyModule`: `load_checkpoint` and `get_trainable_variables`.
### Description In the TensorFlow v2 codepath, there is a bug preventing loading the checkpoint. The bug is very clear in the code. In `tensor2tensor/utils/contrib.py`, in the absence of `tensorflow.contrib`,...
### Description When I tried to run the example about the EN-DE translation, I obtained this error tensorflow.python.framework.errors_impl.UnimplementedError: File system scheme 'http' not implemented (file: 'http://www.statmt.org/wmt13/training-parallel-commoncrawl.tgz') ### Environment information ```...
Ubuntu 18.04 Python 3.7.9 Tensorflow 2.3.1 When I follow https://github.com/magenta/magenta/blob/master/magenta/models/score2perf/README.md, The problem happens when I follow **Training** and **Sampling from the model** part. The Training command is like below at...
### Description When running SV2P algorithm on the BAIR Robot Pushing dataset, having the evaluation metrics not be an empty array means that the model crashes when trying to evaluate....