Lingvo is a framework for building neural networks in Tensorflow, particularly sequence models.
A list of publications using Lingvo can be found here.
There are two ways to set up Lingvo: installing a fixed version through pip, or cloning the repository and building it with bazel. Docker configurations are provided for each case.
If you would just like to use the framework as-is, it is easiest to just install it through pip. This makes it possible to develop and train custom models using a frozen version of the Lingvo framework. However, it is difficult to modify the framework code or implement new custom ops.
If you would like to develop the framework further and potentially contribute pull requests, you should avoid using pip and clone the repository instead.
pip:
The Lingvo pip package (available for python
3.6 and 3.7) can be installed with just pip3 install lingvo.
See the codelab for how to get started with the pip package.
From sources:
The prerequisites are:
- a TensorFlow 2.0 installation,
- a
C++compiler (only g++ 7.3 is officially supported), and - the bazel build system.
Refer to docker/dev.dockerfile for a set of working requirements.
git clone the repository, then use bazel to build and run targets directly.
The python -m module commands in the codelab need to be mapped onto bazel run commands.
docker:
Docker configurations are available for both situations. Instructions can be found in the comments on the top of each file.
- lib.dockerfile has the Lingvo pip package preinstalled.
- dev.dockerfile can be used to build Lingvo from sources.
pip:
mkdir -p /tmp/mnist
python3 -m lingvo.tools.keras2ckpt --dataset=mnistbazel:
mkdir -p /tmp/mnist
bazel run -c opt //lingvo/tools:keras2ckpt -- --dataset=mnistThe following files will be created in /tmp/mnist:
mnist.data-00000-of-00001: 53MB.mnist.index: 241 bytes.
pip:
cd /tmp/mnist
curl -O https://raw.githubusercontent.com/tensorflow/lingvo/master/lingvo/tasks/image/params/mnist.py
python3 -m lingvo.trainer --run_locally=cpu --mode=sync --model=mnist.LeNet5 --logdir=/tmp/mnist/logbazel:
(cpu) bazel build -c opt //lingvo:trainer
(gpu) bazel build -c opt --config=cuda //lingvo:trainer
bazel-bin/lingvo/trainer --run_locally=cpu --mode=sync --model=image.mnist.LeNet5 --logdir=/tmp/mnist/log --logtostderrAfter about 20 seconds, the loss should drop below 0.3 and a checkpoint will be saved, like below. Kill the trainer with Ctrl+C.
trainer.py:518] step: 205, steps/sec: 11.64 ... loss:0.25747201 ...
checkpointer.py:115] Save checkpoint
checkpointer.py:117] Save checkpoint done: /tmp/mnist/log/train/ckpt-00000205
Some artifacts will be produced in /tmp/mnist/log/control:
params.txt: hyper-parameters.model_analysis.txt: model sizes for each layer.train.pbtxt: the trainingtf.GraphDef.events.*: a tensorboard events file.
As well as in /tmp/mnist/log/train:
checkpoint: a text file containing information about the checkpoint files.ckpt-*: the checkpoint files.
Now, let's evaluate the model on the "Test" dataset. In the normal training setup the trainer and evaler should be run at the same time as two separate processes.
pip:
python3 -m lingvo.trainer --job=evaler_test --run_locally=cpu --model=mnist.LeNet5 --logdir=/tmp/mnist/logbazel:
bazel-bin/lingvo/trainer --job=evaler_test --run_locally=cpu --model=image.mnist.LeNet5 --logdir=/tmp/mnist/log --logtostderrKill the job with Ctrl+C when it starts waiting for a new checkpoint.
base_runner.py:177] No new check point is found: /tmp/mnist/log/train/ckpt-00000205
The evaluation accuracy can be found slightly earlier in the logs.
base_runner.py:111] eval_test: step: 205, acc5: 0.99775392, accuracy: 0.94150388, ..., loss: 0.20770954, ...
To run a more elaborate model, you'll need a cluster with GPUs. Please refer to
third_party/py/lingvo/tasks/mt/README.md
for more information.
- car.kitti.StarNetCarModel07013
- car.kitti.StarNetPedCycModel07043
- car.waymo.StarNetVehicle3
- car.waymo.StarNetPed3
- mt.wmt14_en_de.WmtEnDeTransformerBase6
- mt.wmt14_en_de.WmtEnDeRNMT6
- mt.wmtm16_en_de.WmtCaptionEnDeTransformer6
[1]: Listen, Attend and Spell. William Chan, Navdeep Jaitly, Quoc V. Le, and Oriol Vinyals. ICASSP 2016.
[2]: End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results. Jan Chorowski, Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. arXiv 2014.
[3]: StarNet: Targeted Computation for Object Detection in Point Clouds. Jiquan Ngiam, Benjamin Caine, Wei Han, Brandon Yang, Yuning Chai, Pei Sun, Yin Zhou, Xi Yi, Ouais Alsharif, Patrick Nguyen, Zhifeng Chen, Jonathon Shlens, and Vijay Vasudevan. arXiv 2019.
[4]: Gradient-based learning applied to document recognition. Yann LeCun, Leon Bottou, Yoshua Bengio, and Patrick Haffner. IEEE 1998.
[5]: Exploring the Limits of Language Modeling. Rafal Jozefowicz, Oriol Vinyals, Mike Schuster, Noam Shazeer, and Yonghui Wu. arXiv, 2016.
[6]: The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation. Mia X. Chen, Orhan Firat, Ankur Bapna, Melvin Johnson, Wolfgang Macherey, George Foster, Llion Jones, Mike Schuster, Noam Shazeer, Niki Parmar, Ashish Vaswani, Jakob Uszkoreit, Lukasz Kaiser, Zhifeng Chen, Yonghui Wu, and Macduff Hughes. ACL 2018.
Please cite this paper when referencing Lingvo.
@misc{shen2019lingvo,
title={Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling},
author={Jonathan Shen and Patrick Nguyen and Yonghui Wu and Zhifeng Chen and others},
year={2019},
eprint={1902.08295},
archivePrefix={arXiv},
primaryClass={cs.LG}
}