2017/05/07

Note of Image Segmentation by Machine Learning

An awesome implementation of the image segmentation by CNN
https://github.com/torrvision/crfasrnn/blob/master/README.md
http://www.robots.ox.ac.uk/~szheng/CRFasRNN.html

The problem here is that the model is too big, 500M. 
I do not need the classification part. 

related work
https://github.com/shelhamer/fcn.berkeleyvision.org


It is possible to porting it to mobile device, somebody has done this: 
http://libccv.org/post/how-to-run-a-state-of-the-art-image-classifier-on-a-iphone/
https://github.com/liuliu/klaus
at No comments:
Subscribe to: Posts (Atom)

Post Code on Blogger

Simplest way to post code to blogger for me: <pre style="background: #f0f0f0; border: 1px dashed #CCCCCC; color: black;overflow-x:...

  • How MSI-X Works
    Explain There is not interrupt PIN for PCIe interrupt. When device wants to raise an interrupt,  an interrupt message is sent to host via ...
  • PCIE Configuration & Enumeration
    Configure Space Addressing One of the major improvements the PCI Local Bus had over other I/O architectures was its configuration mechanism...
  • GNU's LMA and VMA
    What is LMA and VMA Every loadable or allocatable output section has two addresses. The first is the VMA, or virtual memory address. This ...