Tf Squeezenet Save

TensorFlow version of SqueezeNet with converted pretrained weights

Project README


TensorFlow version of SqueezeNet with converted pretrained weights. The official github of SqueezeNet creators has some information on SqueezeNet v1.1.

Usage: --in identity.jpg

Current implementation is SqueezeNet v 1.1 (signature pool 1/3/5) without bypasses.

synset_words.txt file is a copy from either caffe or torch tutorials.

Model weights are converted from keras HDF5 model file from

Originally, this SqueezeNet was implemented for style transfer, see the original repository here: The style transfer version contains pretrained weights with classifier chopped off, resulting in even smaller file (<3MB).

Fooling the classifier

The netowork can modify images that will fool the classifier into recognizing the modified image as desired class. Usage: --in identity.jpg --fool 8 will take the input image identity.jpg and generate new image bnased on it, which will be classified as 'n01514859 hen'. Class number is the number of line in the 'synset_words.txt' file minus 1, i.e. starting with 0.


Open Source Agenda is not affiliated with "Tf Squeezenet" Project. README Source: avoroshilov/tf-squeezenet

Open Source Agenda Badge

Open Source Agenda Rating