Gathers scalable tensorflow and infrastructure deployment

Gather-Deployment

Gathers scalable tensorflow and infrastructure deployment, reusable purpose in the future.

Table of contents

• Tensorflow deployment

Tensorflow deployment

1. Object Detection. Flask SocketIO + WebRTC

• Stream from webcam using WebRTC -> Flask SocketIO to detect objects -> WebRTC -> Website.

2. Object Detection. Flask SocketIO + opencv

• Stream from OpenCV -> Flask SocketIO to detect objects -> OpenCV.

3. Speech streaming. Flask SocketIO

• Stream speech from microphone -> Flask SocketIO to do realtime speech recognition.

4. Text classification. Flask + Gunicorn

• Serve Tensorflow text model using Flask multiworker + Gunicorn.

5. Image classification. TF Serving

• Serve image classification model using TF Serving.

6. Image Classification using Inception. Flask SocketIO

• Stream image using SocketIO -> Flask SocketIO to classify.

7. Object Detection. Flask + opencv

• Webcam -> Opencv -> Flask -> web dashboard.

8. Face-detection using MTCNN. Flask SocketIO + opencv

• Stream from OpenCV -> Flask SocketIO to detect faces -> OpenCV.

9. Face-detection using MTCNN. opencv

• Webcam -> Opencv.

10. Image classification using Inception. Flask + Docker

• Serve Tensorflow image model using Flask multiworker + Gunicorn on Docker container.

11. Image classification using Inception. Flask + EC2 Docker Swarm + Nginx load balancer

• Serve inception on multiple AWS EC2, scale using Docker Swarm, balancing using Nginx.

12. Text classification. Hadoop streaming MapReduce

• Batch processing to classify texts using Tensorflow text model on Hadoop MapReduce.

13. Text classification. Kafka

• Stream text to Kafka producer and classify using Kafka consumer.

14. Text classification. Distributed TF using Flask + Gunicorn + Eventlet

• Serve text model on multiple machines using Distributed TF + Flask + Gunicorn + Eventlet. Means that, Distributed TF will split a single neural network model to multiple machines to do feed-forward.

15. Text classification. Tornado + Gunicorn

• Serve Tensorflow text model using Tornado + Gunicorn.

16. Text classification. Flask + Celery + Hadoop

• Submit large texts using Flask, signal queue celery job to process using Hadoop, delay Hadoop MapReduce.

17. Text classification. Luigi scheduler + Hadoop

• Submit large texts on Luigi scheduler, run Hadoop inside Luigi, event based Hadoop MapReduce.

18. Text classification. Luigi scheduler + Distributed Celery

• Submit large texts on Luigi scheduler, run Hadoop inside Luigi, delay processing.

19. Text classification. Airflow scheduler + elasticsearch + Flask

• Scheduling based processing using Airflow, store inside elasticsearch, serve it using Flask.

20. Text classification. Apache Kafka + Apache Storm

• Stream from twitter -> Kafka Producer -> Apache Storm, to do distributed minibatch realtime processing.

21. Text classification. Dask

• Batch processing to classify texts using Tensorflow text model on Dask.

22. Text classification. Pyspark

• Batch processing to classify texts using Tensorflow text model on Pyspark.

23. Text classification. Pyspark streaming + Kafka

• Stream texts to Kafka Producer -> Pyspark Streaming, to do minibatch realtime processing.

24. Text classification. PyFlink

• Batch processing to classify texts using Tensorflow text model on Flink batch processing.

25. Text classification. Streamz + Dask + Kafka

• Stream texts to Kafka Producer -> Streamz -> Dask, to do minibatch realtime processing.

Printscreen

All folders contain print screens, logs and instructions on how to start.

Notes

1. Deploy them on a server, change local in code snippets to your own IP.
2. WebRTC chrome only can tested on HTTPS server.
3. When come to real deployment, always prepare for up-scaling architectures. Learn about DevOps.
4. Please aware with your cloud cost!