bert, sagemaker, aws, ec2, nboost,lambda
https://pypi.org/project/nboost/
https://github.com/hanxiao/bert-as-service#using-bert-as-service-to-serve-http-requests-in-json
http://www.lib4dev.in/info/koursaros-ai/nboost/LICENSE#setting-up-an-elasticsearch-server
언급된것처럼 gpu 서버 너무 비쌈...
https://beomi.github.io/2018/03/18/Create_GPU_spot_EC2_for_ML/
https://github.com/tensorflow/serving/blob/master/tensorflow_serving/g3doc/docker.md
간단하게 tf 서빙서버를 만드는 것도 방법이나 bert 를 쓸거면 bert를 쓰는게 나을 거라고 판단.
https://tensorflowkorea.gitbooks.io/tensorflow-kr/content/g3doc/tutorials/tfserve/
https://www.tensorflow.org/tfx/serving/docker
https://www.tensorflow.org/tfx/serving/serving_advanced
https://www.tensorflow.org/guide/saved_model?hl=ko
https://www.tensorflow.org/tutorials/keras/save_and_load?hl=ko
https://zzsza.github.io/data/2018/07/12/tensorflow-serving-tutorial/
https://www.tensorflow.org/tfx/serving/api_rest
보고 깜짝 놀람, 자사 gcp 서비스들을 이용해서 시스템 구축하는걸 다 문서화해놓음;
gcp 를 썼다면 이런 문서들을 기반으로 text-embedding 시스템을 구축했을 것.
https://github.com/GoogleCloudPlatform/realtime-embeddings-matching/tree/master/text-semantic-search
aws arn
이걸로 lambda 세팅할 때 도움 많이 받음. ㅠㅠ 물론 이걸 사용하는 일은 없었다고 한다.
https://github.com/antonpaquin/Tensorflow-Lambda-Layer/blob/master/arn_tables/tensorflow_keras.md
https://towardsdatascience.com/word-embedding-using-bert-in-python-dd5a86c00342
https://bert-as-service.readthedocs.io/en/latest/source/server.html
https://github.com/DemisEom/bertsearch
이걸로 쉽게 돌려볼 수 있었을까?
https://github.com/Hironsan/bertsearch
https://bert-as-service.readthedocs.io/en/latest/source/server.html
https://www.elastic.co/kr/blog/text-similarity-search-with-vectors-in-elasticsearch
https://github.com/mikepm35/TfLambdaDemo
https://medium.com/@mike.p.moritz/running-tensorflow-on-aws-lambda-using-serverless-5acf20e00033
https://www.youtube.com/watch?v=neHlZCMUN8U
https://www.slideshare.net/awskorea/aws-lambda-tensorflow-keras-inferences
https://mc.ai/serverless-vision-inference-using-aws-lambda-and-tflite/
tflite로도 뭔갈 해보려고 했으나 잘 되지 않음. 결국 런타임을 lambda 에서 돌리는데는 무리가 있었음.
https://aws.amazon.com/ko/blogs/korea/build-a-serverless-frontend-for-an-amazon-sagemaker-endpoint/
https://medium.com/circuitpeople/serverless-large-file-downloads-to-s3-a11b4ef4788e
https://blog.haandol.com/2020/03/07/search-keyword-correction.html
https://docs.aws.amazon.com/ko_kr/dlami/latest/devguide/tutorial-tfserving.html
https://gist.github.com/nacyot/8366310
삽질한다고 도커 많이 써봄.
수확이었다.
https://stackoverflow.com/questions/30604846/docker-error-no-space-left-on-device
ec2 t2.micro에다가 이것저것 설치하다보니 마주한 문제.
https://aws.amazon.com/ko/premiumsupport/knowledge-center/batch-job-failure-disk-space/
https://tfhub.dev/tensorflow/bert_multi_cased_L-12_H-768_A-12/2
구글이 최고여
https://urbanbase.github.io/dev/2019/10/24/Machine-Learning-Prototype.html
https://github.com/harusametime/sagemaker-notebooks/tree/master/tf_bert_classifier/src/bert
https://hackernoon.com/exploring-the-aws-lambda-deployment-limits-9a8384b0bec3
https://github.com/serverless/serverless
https://dreamgonfly.github.io/2018/01/19/pytorch-on-aws-lambda.html
사실 삽질중에 pytorch 서빙서버가 공식으로 aws에서 나와서 좀 고민하긴했음.
https://github.com/tgjeon/TF-Eager-Execution-Guide-KR/blob/master/guide.md
https://www.whatap.io/ko/blog/37/
https://github.com/mikepm35/TfLambdaDemo
https://medium.com/smellslikeml/serverless-vision-inference-using-aws-lambda-and-tflite-613c084f64d2
https://github.com/aws/sagemaker-tensorflow-serving-container
https://github.com/jina-ai/jina/tree/master/docs/chapters/101
이것도 신기하긴했음.
https://docs.jina.ai/api/jina.html
https://github.com/jina-ai/examples/tree/master/x-as-service
https://course.fast.ai/#pytorch-and-fastai
http://xplordat.com/2019/10/28/semantics-at-scale-bert-elasticsearch/
https://github.com/ryfeus/lambda-packs
lambda pack들, 람다 세팅할 때 도움이 많이 됨.
https://mc.ai/serving-pytorch-nlp-models-on-aws-lambda/
https://www.tensorflow.org/tfx/serving/serving_config#reloading_model_server_configuration
https://www.tensorflow.org/tfx/serving/custom_source
https://www.tensorflow.org/tfx/serving/signature_defs#objective
https://github.com/hanxiao/bert-as-service/issues/221
https://towardsdatascience.com/how-to-build-a-semantic-search-engine-in-3-minutes-9e579da92913
https://towardsdatascience.com/serving-tensorflow-models-serverless-6a39614094ff
https://github.com/kaushaltrivedi/fast-bert
fast bert, bert 종류들 많아서 다 살펴볼만