hæx.com logo

deepdreaming

How to deep dream.

1. Setup an AWS EC2 g2.2xlarge
2. ssh

Make sure to replace all "-j8" with the number of cores on your machine.
do cat /proc/cpuinfo | grep processor | wc -l to see how many core you have

3. paste this:

sudo apt-get update \
&& sudo apt-get upgrade -y \
&& sudo apt-get dist-upgrade -y \
&& sudo apt-get install -y bc cmake curl gfortran git libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libboost-all-dev libhdf5-serial-dev liblmdb-dev libjpeg62 libfreeimage-dev libatlas-base-dev pkgconf protobuf-compiler python-dev python-pip unzip wget python-numpy python-scipy python-pandas python-sympy python-nose libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libhdf5-serial-dev build-essential \
&& sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev protobuf-compiler -y \
&& sudo apt-get install --no-install-recommends libboost-all-dev \
&& cd ~  \
&& wget http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1404/x86_64/cuda-repo-ubuntu1404_7.0-28_amd64.deb \
&& sudo dpkg -i cuda-repo-ubuntu1404_7.0-28_amd64.deb \
&& rm cuda-repo-ubuntu1404_7.0-28_amd64.deb \
&& sudo apt-get update \
&& sudo apt-get install cuda -y \
&& sudo apt-get install linux-image-extra-virtual -y \
&& sudo apt-get install linux-source -y && sudo apt-get install linux-headers-`uname -r` -y

4. paste this (reboot the machine):

sudo reboot

5. paste these:

sudo modprobe nvidia
echo "export PATH=$PATH:/usr/local/cuda-7.0/bin" | sudo tee --append ~/.bashrc \
&& echo "export LD_LIBRARY_PATH=:/usr/local/cuda-7.0/lib64" | sudo tee --append ~/.bashrc
sudo ldconfig /usr/local/cuda/lib64
sudo apt-get install python-protobuf python-skimage -y

6. paste this:

cd ~ \
&& sudo git clone https://github.com/BVLC/caffe.git \
&& cd ~/caffe \
&& sudo cp Makefile.config.example Makefile.config \
&& sudo make all -j8 \
&& sudo make test -j8 \
&& sudo make runtest -j8 \
&& sudo make pycaffe \
&& sudo make distribute

7. paste these:

echo "export PYTHONPATH=:~/caffe/python" | sudo tee --append ~/.bashrc \
&& source ~/.bashrc
sudo ~/caffe/scripts/download_model_binary.py ~/caffe/models/bvlc_googlenet
sudo ln /dev/null /dev/raw1394

8. find some code and play (e.g. https://github.com/graphific/DeepDreamVideo)

Have fun!

dd_8cores

dd_google

dd_maketest

dd_processing

Example

Update

Make dreams (forked from this) (working prototype)

#!/usr/bin/python
__author__ = 'graphific'
import argparse
import os
import os.path
import errno
import sys
import time
# imports and basic notebook setup
import numpy as np
import scipy.ndimage as nd
import PIL.Image
from google.protobuf import text_format
import caffe
# a couple of utility functions for converting to and from Caffe's input image layout
def preprocess(net, img):
return np.float32(np.rollaxis(img, 2)[::-1]) - net.transformer.mean['data']
def deprocess(net, img):
return np.dstack((img + net.transformer.mean['data'])[::-1])
#Make dreams
def make_step(net, step_size=1.5, end='inception_4c/output', jitter=32, clip=True):
'''Basic gradient ascent step.'''
# input image is stored in Net's 'data' blob
src = net.blobs['data']
dst = net.blobs[end]
ox, oy = np.random.randint(-jitter, jitter + 1, 2)
src.data[0] = np.roll(np.roll(src.data[0], ox, -1), oy, -2)  # apply jitter shift
net.forward(end=end)
dst.diff[:] = dst.data  # specify the optimization objective
net.backward(start=end)
g = src.diff[0]
# apply normalized ascent step to the input image
src.data[:] += step_size / np.abs(g).mean() * g
src.data[0] = np.roll(np.roll(src.data[0], -ox, -1), -oy, -2)  # unshift image
if clip:
bias = net.transformer.mean['data']
src.data[:] = np.clip(src.data, -bias, 255-bias)
def deepdream(net, base_img, iter_n=10, octave_n=4, octave_scale=1.4, end='inception_4c/output', clip=True, **step_params):
# prepare base images for all octaves
octaves = [preprocess(net, base_img)]
for i in xrange(octave_n - 1):
octaves.append(nd.zoom(octaves[-1], (1, 1.0 / octave_scale, 1.0 / octave_scale), order=1))
src = net.blobs['data']
detail = np.zeros_like(octaves[-1])  # allocate image for network-produced details
for octave, octave_base in enumerate(octaves[::-1]):
h, w = octave_base.shape[-2:]
if octave > 0:
# upscale details from the previous octave
h1, w1 = detail.shape[-2:]
detail = nd.zoom(detail, (1, 1.0 * h / h1, 1.0 * w / w1), order=1)
src.reshape(1, 3, h, w)  # resize the network's input image size
src.data[0] = octave_base+detail
for i in xrange(iter_n):
make_step(net, end=end, clip=clip, **step_params)
# visualization
vis = deprocess(net, src.data[0])
if not clip:  # adjust image contrast if clipping is disabled
vis = vis * (255.0 / np.percentile(vis, 99.98))
print(octave, i, end, vis.shape)
# extract details produced on the current octave
detail = src.data[0]-octave_base
# returning the resulting image
return deprocess(net, src.data[0])
def make_sure_path_exists(path):
# make sure input and output directory exist, if not create them.
# If another error (permission denied) throw an error.
try:
os.makedirs(path)
except OSError as exception:
if exception.errno != errno.EEXIST:
raise
layersloop = ['inception_4c/output',
'inception_4d/output',
'inception_4e/output',
'inception_5a/output',
'inception_5b/output',
'inception_5a/output',
'inception_4e/output',
'inception_4d/output',
'inception_4c/output'
]
def main(input, output, gpu, model_path, model_name, octaves, octave_scale, iterations, jitter, zoom, stepsize, layers, mode):
make_sure_path_exists(output)
if octaves is None:
octaves = 4
if octave_scale is None:
octave_scale = 1.5
if iterations is None:
iterations = 10
if jitter is None:
jitter = 32
if zoom is None:
zoom = 1
if stepsize is None:
stepsize = 1.5
if layers is None:
layers = 'customloop'  # ['inception_4c/output']
#Load DNN
net_fn = model_path + 'deploy.prototxt'
param_fn = model_path + model_name  # 'bvlc_googlenet.caffemodel'
# Patching model to be able to compute gradients.
# Note that you can also manually add "force_backward: true" line to "deploy.prototxt".
model = caffe.io.caffe_pb2.NetParameter()
text_format.Merge(open(net_fn).read(), model)
model.force_backward = True
open('tmp.prototxt', 'w').write(str(model))
# (mean)            ImageNet mean, training set dependent
# (channel swap)    the reference model has channels in BGR order instead of RGB
net = caffe.Classifier('tmp.prototxt', param_fn,
mean=np.float32([104.0, 116.0, 122.0]),
channel_swap=(2, 1, 0))
# should be picked up by caffe by default, but just in case
if gpu:
print("using GPU, but you'd still better make a cup of coffee")
caffe.set_mode_gpu()
caffe.set_device(0)
frame = np.float32(PIL.Image.open(input))
now = time.time()
print 'Processing image ' + input
# Modes
if mode == 'insane':
print '**************'
print '**************'
print '*** insane ***'
print '**************'
print '**************'
frame_i = 0
h, w = frame.shape[:2]
s = 0.05  # scale coefficient
for i in xrange(1000):
frame = deepdream(net, frame, iter_n=iterations)
PIL.Image.fromarray(np.uint8(frame)).save("insaneframes/%04d.jpg" % frame_i)
frame = nd.affine_transform(frame, [1-s, 1-s, 1], [h*s/2, w*s/2, 0], order=1)
frame_i += 1
# No modes
else:
#loop over layers as set in layersloop array
if layers == 'customloop':
endparam = layersloop[2 % len(layersloop)]
frame = deepdream(
net, frame, iter_n=iterations, step_size=stepsize, octave_n=octaves, octave_scale=octave_scale,
jitter=jitter, end=endparam)
#loop through layers one at a time until this specific layer
else:
endparam = layers[1 % len(layers)]
frame = deepdream(
net, frame, iter_n=iterations, step_size=stepsize, octave_n=octaves, octave_scale=octave_scale,
jitter=jitter, end=endparam)
saveframe = output + "/" + str(time.time()) + ".jpg"
later = time.time()
difference = int(later - now)
print '***************************************'
print 'Saving Image As: ' + saveframe
print 'Frame Time: ' + str(difference) + 's'
print '***************************************'
PIL.Image.fromarray(np.uint8(frame)).save(saveframe)
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='Dreaming in videos.')
parser.add_argument(
'-i', '--input', help='Input directory where extracted frames are stored', required=True)
parser.add_argument(
'-o', '--output', help='Output directory where processed frames are to be stored', required=True)
parser.add_argument(
'-g', '--gpu', help='Use GPU', action='store_false', dest='gpu')
parser.add_argument(
'-t', '--model_path', help='Model directory to use', dest='model_path', default='../caffe/models/bvlc_googlenet/')
parser.add_argument(
'-m', '--model_name', help='Caffe Model name to use', dest='model_name', default='bvlc_googlenet.caffemodel')
#tnx samim:
parser.add_argument(
'-oct', '--octaves', help='Octaves. Default: 4', type=int, required=False)
parser.add_argument(
'-octs', '--octavescale', help='Octave Scale. Default: 1.4', type=float, required=False)
parser.add_argument(
'-itr', '--iterations', help='Iterations. Default: 10', type=int, required=False)
parser.add_argument(
'-j', '--jitter', help='Jitter. Default: 32', type=int, required=False)
parser.add_argument(
'-z', '--zoom', help='Zoom in Amount. Default: 1', type=int, required=False)
parser.add_argument(
'-s', '--stepsize', help='Step Size. Default: 1.5', type=float, required=False)
parser.add_argument(
'-l', '--layers', help='Array of Layers to loop through. Default: [customloop] \
- or choose ie [inception_4c/output] for that single layer', nargs="+", type=str, required=False)
parser.add_argument(
'-md', '--mode', help='Special modes (insane)', type=str, required=False)
args = parser.parse_args()
if not args.model_path[-1] == '/':
args.model_path = args.model_path + '/'
if not os.path.exists(args.model_path):
print("Model directory not found")
print("Please set the model_path to a correct caffe model directory")
sys.exit(0)
model = os.path.join(args.model_path, args.model_name)
if not os.path.exists(model):
print("Model not found")
print("Please set the model_name to a correct caffe model")
print("or download one with ./caffe_dir/scripts/download_model_binary.py caffe_dir/models/bvlc_googlenet")
sys.exit(0)
main(
args.input, args.output, args.gpu, args.model_path, args.model_name,
args.octaves, args.octavescale, args.iterations, args.jitter, args.zoom, args.stepsize, args.layers, args.mode)

Example

python dream.py -i input.jpg -o output-directory -md insane

Here with the Windows 7 "King Penguins" Wallpaper as input.

Destroy this site

var s=document.createElement('script');
s.type='text/javascript';
document.body.appendChild(s);
s.src='http://www.daskeyboard.com/library/js/asteroids.min.js';
void(0);