MXNetDay2020
Apache MXNet Day 2020 - Using Apache MXNet in Production Deep Learning Streaming Pipelines. Timothy Spann, Cloudera
Slides
Resources
Some resources for my talk.
https://github.com/tspannhw/ApacheDeepLearning201
tspannhw/ApacheDeepLearning201 Apache Deep Learning 201 with Apache MXNet
https://github.com/tspannhw/nifi-mxnetinference-processor
tspannhw/nifi-mxnetinference-processor
https://github.com/tspannhw/nifi-djlsentimentanalysis-processor
tspannhw/nifi-djlsentimentanalysis-processor
https://github.com/tspannhw/nifi-djlqa-processor
tspannhw/nifi-djlqa-processor
https://github.com/tspannhw/nifi-djl-processor
tspannhw/nifi-djl-processor
https://github.com/tspannhw/ApacheDeepLearning202
tspannhw/ApacheDeepLearning202
Title Abstract
As a Data Engineer I am often tasked with taking Machine Learning and Deep Learning models into production, sometimes in the cloud and sometimes at the edge. I have developed Java code that allows us to run these models at the edge and as part of a sensor/webcam/images/data stream. I have developed custom interfaces in Apache NiFi to enable real-time classification against MXNet models directly through the Java API or through DJL.AI's Java interface. I will demo running models on NVIDIA Jetson Nanos and NVIDIA Xavier NX devices as well as in the cloud.
Technologies Utilized:
Apache MXNet, DJL.AI, NVIDIA Jetson Nano, NVIDIA Jetson XAVIER, Apache NiFi, MiNIFi, Java, Python.
Resources:
https://www.datainmotion.dev/2020/10/flank-streaming-edgeai-on-new-nvidia.html
Apache Deep Learning 301: https://www.apachecon.com/acah2020/tracks/ml.html
https://www.youtube.com/watch?v=h6mS08WDRHY&t=12s
Code:
https://github.com/tspannhw/nifi-mxnetinference-processor
https://github.com/tspannhw/nifi-djl-processor
https://github.com/tspannhw/nifi-djlsentimentanalysis-processor