Don’t follow the TensorFlow docs since they explain how to setup a docker image and compile TF serving that takes forever. We can do much better. Some guy made a docker image with everything already compile on it, so we are going to use that one.
Source: towardsdatascience.com
Today, we are excited to announce the open source release of our latest and best performing semantic image segmentation model, DeepLab-v3+ [1], implemented in Tensorflow. This release includes DeepLab-v3+ models built on top of a powerful convolutional neural network (CNN) backbone architecture [2, 3] for the most accurate results, intended for server-side deployment. As part of this release, we are additionally sharing our Tensorflow model training and evaluation code, as well as models already pre-trained on the Pascal VOC 2012 and Cityscapes benchmark semantic segmentation tasks.
Read More
Automated front-end development using deeplearningSketchCode: Go from idea to HTML in 5secondsAshwin Kumar was previously the co-founder of Sway Finance, a Y Combinator-backed startup that used machine learning to automate accounting. At Insight, he developed a model that allows users to create working HTML websites from hand-drawn wireframes, significantly accelerating the design process. He is now a Deep Learning Scientist at Mythic.
Read More
The generator is a counterfeiter trying to produce seemingly real data. It has no idea of what the real data is, but it learns to adjust from the feedback of the other model. The discriminator is a inspector trying to determine what the fake counterfeit data is (by comparing it with real data), while trying to not raise false positives on the real data.
Read More