[머신러닝스터디/2016]
[머신러닝스터디/2016/목차]
== 내용 ==
 * transfer, image retraining, fine-tune
 * 튜토리얼로 [https://www.tensorflow.org/versions/r0.9/how_tos/image_retraining/index.html#training-on-flowers flower classification]을 해 보자.
  * bazel build는 까다롭다.
  * tensorflow 0.10rc에서 [https://github.com/tensorflow/models/blob/master/slim/scripts/finetune_inception_v1_on_flowers.sh 예제 스크립트] 실행 불가
  * tensorflow 0.11.0rc설치 후 실행 가능
  * 바이너리 링크 참고: https://github.com/tensorflow/tensorflow/blob/r0.11/tensorflow/g3doc/get_started/os_setup.md
  {{{
# Ubuntu/Linux 64-bit, CPU only, Python 2.7
$ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.11.0rc0-cp27-none-linux_x86_64.whl

# Ubuntu/Linux 64-bit
$ sudo apt-get install python-pip python-dev python-virtualenv
}}}
 * docker 

== 더보기 ==
 * install bazel in linux: [https://www.bazel.io/versions/master/docs/install.html#ubuntu link]
 * tensorflow model slim: [https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/slim link]
 * flower classification tutorial script : [https://github.com/tensorflow/models/blob/master/slim/scripts/finetune_inception_v1_on_flowers.sh link]