We look at exporting our model into saved_model and use that in java in order to run inference on images the model never is seen before.
Git repository
https://github.com/kalaspuffar/rcnn-model-test
Please follow me on twitter
Outro music: Danomate
- http://danomate.com
- https://www.youtube.com/user/danomate1
I talk about my experience at a hackathon last weekend. Github Repository https://github.com/kalaspuffar/simply-communication Please follow me on twitter Tweets by kalaspuffar Outro music: Danomate – http://danomate.com – https://www.youtube.com/user/danomate1
We will look into Ceph Dokan which is a new library and command-line client in order to mount your Ceph cluster to a drive letter in Windows 10. Ceph Dokan still very much in beta but it can pretty easily be installed and mounted using some Windows voodoo.
We’re looking into a solution using log4j to consolidate our logs in an third-party system using Application server and IBM has disabled the support for log4j in the application servers logging framework. I tried to reverse this process and check what was needed to enable this feature again. First of we need the log4j framework…
We look into how to use Java to create an image classification model using TFRecords and train it with python. Then we will read that model in TensorflowJS in order to predict images. Repository: https://ift.tt/2FKXZmy Please follow me on twitter Tweets by kalaspuffar Outro music: Sanaas Scylla
Doing a manual upgrade of my Ceph cluster. In the same process, I get the Debian operating system upgraded that my Ceph cluster is running on. The new version of Ceph called Pacific requires some extra measures and when you’ve updated you can’t go back.
We solve the day 4 challenges for the Advent of Code. Please follow me on twitter Tweets by kalaspuffar Outro music: Sanaas Scylla