Open changtimwu opened 7 years ago
squeezenet 1.1 has lower computation requirement. https://github.com/DeepScale/SqueezeNet/tree/master/SqueezeNet_v1.1
many options. Can we combine them all?
few of squeezenet implementations include deep compression. Only songhan himself implement it. It's caffe only.
general quantization techniques in tensorflow and songhan leaves positive comments on it. By utilizaing this, maybe we can create deep compression + squeezenet in tensorflow.
some chinese doc
reading group: http://www.kdnuggets.com/2016/09/deep-learning-reading-group-squeezenet.html
darknet's tinynet could be smaller than squeezenet.
https://pjreddie.com/darknet/tiny-darknet/
implementation:
the same author also proposes squeezdet to prove that squeezenet applied to kitti tasks https://arxiv.org/abs/1612.01051
about the quantization, Dorefa does an excellent work.
Its 2nd author creates a good framework tensorpack for this paper.
Trained Ternary Quantization is the derived work.
let's compare https://github.com/songhan/SqueezeNet-DSD-Training and original squeezenet to tell if DSD is repeatable.
google mobilenet https://arxiv.org/abs/1704.04861
Speed/accuracy trade-offs for modern convolutional object detectors https://arxiv.org/abs/1611.10012
another detailed discussion of two different approaches to minimize model size. network vs precision https://arxiv.org/pdf/1605.06402.pdf
really nice to read. The keras author demonstrates typical image classification procedure.
https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html gist: https://gist.github.com/fchollet/f35fbc80e066a49d65f1688a7e99f069
We should follow this guy. All his repos are much related to us. https://github.com/Zehaos?tab=repositories
mysterious company
http://www.dt42.io
https://github.com/DT42
looks good it has nothing to do with UBER. UberNet : Training a ‘Universal’ Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory
https://github.com/allanzelener/YAD2K YOLO9000's tensorflow/keras implementation
I want to try squeezenet 1.1
rcmalli implement it but his input/output is a mess.
chasingbob 's dog vs cat example utilizes DT42's squeezenet 1.0 implementation.
So, I should try chasingbob and alter his model with squeezenet 1.1
ARM compute lib and squeezenet https://arxiv.org/abs/1704.03751
let's trace this without bullshits https://github.com/mtmd/Mobile_ConvNet
squeezenet just reduce number of parameters. It doesn't save computation. table clip from mobilenet paper