Recognize artifacts using a neural network

[zwn]

There is an older attempt to bring DNN artifact detection started at https://github.com/robotika/subt-artf/tree/master/model. This issue is meant to track information related to that effort.

[zwn]

https://en.wikipedia.org/wiki/SqueezeNet

SqueezeNet was originally described in a paper entitled "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size." AlexNet is a deep neural network that has 240MB of parameters, and SqueezeNet has just 5MB of parameters.

Model compression (e.g. quantization and pruning of model parameters) can be applied to a deep neural network after it has been trained. In the SqueezeNet paper, the authors demonstrated that a model compression technique called Deep Compression can be applied to SqueezeNet to further reduce the size of the parameter file from 5MB to 500KB.

[zwn]

• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• SqueezeNext: Hardware-Aware Neural Network Design
• Tiny SSD: A Tiny Single-shot Detection Deep Convolutional Neural Network for Real-time Embedded Object Detection
• Towards Principled Design of Deep Convolutional Networks: Introducing SimpNet
• DeepRebirth: Accelerating Deep Neural Network Execution on Mobile Devices

[zwn]

pytorch and tensorflow are on its way to our base image