fix docs

docs/installation/deltann_compile.md → docs/development/deltann_compile.md

@@ -1,4 +1,3 @@
-
 # DELTA-NN compile
 
 Deltann support tensorflow， tensorflow lite，and tensorflow serving.
@@ -239,3 +238,25 @@ bazel build //tensorflow_serving/model_servers:tensorflow_model_server
 ```
 cd delta/deltann && ./build.sh linux x86_64 tfserving
 ```
+
+## Build in docker, using on bare metal
+
+When link with `libx_ops.so`, `libdeltann.so` and `libtensorflow_cc.so`, `libtensorflow_framework.so`,
+mabe has problems as below:
+
+```
+/lib/deltann/lib/tensorflow/libtensorflow_cc.so: undefined reference to `std::_V2::error_category::equivalent(std::error_code const&, int) const@GLIBCXX_3.4.21'
+./lib/deltann/lib/tensorflow/libtensorflow_cc.so: undefined reference to `std::random_device::_M_init(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)@GLIBCXX_3.4.21'
+./lib/deltann/lib/deltann/libdeltann.so: undefined reference to `std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::basic_string(char const*, std::allocator<char> const&)@GLIBCXX_3.4.21'
+./lib/deltann/lib/deltann/libdeltann.so: undefined reference to `std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_data() const@GLIBCXX_3.4.21'
+./lib/deltann/lib/deltann/libdeltann.so: undefined reference to `std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::append(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)@GLIBCXX_3.4.21'
+./lib/deltann/lib/custom_ops/libx_ops.so: undefined reference to `std::out_of_range::out_of_range(char const*)@GLIBCXX_3.4.21'
+./lib/deltann/lib/custom_ops/libx_ops.so: undefined reference to `VTT for std::__cxx11::basic_ostringstream<char, std::char_traits<char>, std::allocator<char> >@GLIBCXX_3.4.21'
+...
+./lib/deltann/lib/custom_ops/libx_ops.so: undefined reference to `powf@GLIBC_2.27'
+./lib/deltann/lib/tensorflow/libtensorflow_cc.so: undefined reference to `expf@GLIBC_2.27'
+./lib/deltann/lib/tensorflow/libtensorflow_cc.so: undefined reference to `lgammaf@GLIBC_2.23'
+./lib/deltann/lib/custom_ops/libx_ops.so: undefined reference to `logf@GLIBC_2.27'
+./lib/deltann/lib/tensorflow/libtensorflow_cc.so: undefined reference to `lgamma@GLIBC_2.23'
+```
+You need copy `libstd++.so.xx` and `libc.so.xx` from docker, and link with these.

docs/development/docker.md

@@ -1,4 +1,4 @@
-# Docker 
+# Develop with Docker 
 
 ## Install Docker
 

docs/index.rst

@@ -22,7 +22,6 @@ Welcome to DELTA's documentation!
    installation/install_from_source
    installation/using_docker
    installation/manual_setup
-   installation/deltann_compile
    installation/install_on_macos
 
 
@@ -37,7 +36,6 @@ Welcome to DELTA's documentation!
    tutorials/training/text_class_source_example
    tutorials/training/data/asr_example
    tutorials/training/data/emotion-speech-cls
-   tutorials/training/data/kws-cls
    tutorials/deployment/dpl
    tutorials/deployment/deltann
 
@@ -47,6 +45,7 @@ Welcome to DELTA's documentation!
    :name: sec-devel
 
    development/docker
+   development/deltann_compile
    development/adding_op
    development/serving
    development/tensorrt
@@ -86,12 +85,3 @@ Welcome to DELTA's documentation!
    :name: sec-ver
 
    version
-
-
-
-Indices and tables
-==================
-
-* :ref:`genindex`
-* :ref:`modindex`
-* :ref:`search`

docs/introduction.md

@@ -23,3 +23,20 @@ It helps you to train, develop, and deploy NLP and/or speech models, featuring:
  - Easy-to-develop
    - Easily build state-of-the-art models using modularized components
    - All modules are reliable and fully-tested
+
+## References
+
+Please cite this [paper](https://arxiv.org/abs/1908.01853) when referencing DELTA.
+```bibtex
+@ARTICLE{delta,
+       author = {{Han}, Kun and {Chen}, Junwen and {Zhang}, Hui and {Xu}, Haiyang and
+         {Peng}, Yiping and {Wang}, Yun and {Ding}, Ning and {Deng}, Hui and
+         {Gao}, Yonghu and {Guo}, Tingwei and {Zhang}, Yi and {He}, Yahao and
+         {Ma}, Baochang and {Zhou}, Yulong and {Zhang}, Kangli and {Liu}, Chao and
+         {Lyu}, Ying and {Wang}, Chenxi and {Gong}, Cheng and {Wang}, Yunbo and
+         {Zou}, Wei and {Song}, Hui and {Li}, Xiangang},
+       title = "{DELTA: A DEep learning based Language Technology plAtform}",
+       journal = {arXiv e-prints},
+       year = "2019",
+       url = {https://arxiv.org/abs/1908.01853},
+}

docs/tutorials/deployment/deltann.md

@@ -1,4 +1,4 @@
-# DELTA-NN
+# DELTA-NN architecture 
 
 1. features
 1. compile

docs/tutorials/deployment/dpl.md

@@ -1,4 +1,4 @@
-# dpl
+# Deployment scripts - dpl
 The `dpl` directory is for orginating model `config`, `convert`, `testing`, `benchmarking` and `serving`.
 
 ## Inputs & Outputs

docs/tutorials/training/egs.md

@@ -1,4 +1,4 @@
-# Egs
+# Reproduce experiments - egs 
 
 The `egs` director is data-oriented for `data prepration` and model `training`, `evaluation` and `infering`.