Easy to configure Python program that make use of Google's DeepDream
- Install NumPy, SciPy, Pillow and Caffe. NumPy, SciPy & Pillow can be installed via PIP.
- Download deploy.prototxt from bvlc_googlenet.
- Add line
force_backward: trueto deploy.prototxt file. - Download bvlc_googlenet.caffemodel from bvlc_googlenet.
- Make sure those two files are on root directory of DeepDreamer.
python deepdreamer.py image.jpg
usage: deepdreamer.py [-h] [--zoom {true,false}] [--scale SCALE]
[--dreams DREAMS] [--itern ITERN] [--octaves OCTAVES]
[--octave-scale OCTAVE_SCALE] [--layers LAYERS]
[--clip {true,false}] [--list-layers]
[image]
positional arguments:
image
optional arguments:
-h, --help show this help message and exit
--zoom {true,false} zoom dreams (default: true)
--scale SCALE scale coefficient for zoom (default: 0.05)
--dreams DREAMS number of images (default: 100)
--itern ITERN dream iterations (default: 10)
--octaves OCTAVES dream octaves (default: 4)
--octave-scale OCTAVE_SCALE
dream octave scale (default: 1.4)
--layers LAYERS dream layers (default: inception_4c/output)
--clip {true,false} clip dreams (default: true)
--list-layers list layers