def main():
"""A simple demo showing how to run decafnet."""
from decaf.util import smalldata, visualize
logging.getLogger().setLevel(logging.INFO)
net = DecafNet()
lena = smalldata.lena()
scores = net.classify(lena)
print 'prediction:', net.top_k_prediction(scores, 5)
visualize.draw_net_to_file(net._net, 'decafnet.png')
print 'Network structure written to decafnet.png'
def main():
"""A simple demo showing how to run jeffnet."""
from decaf.util import smalldata, visualize
logging.getLogger().setLevel(logging.INFO)
net = JeffNet()
lena = smalldata.lena()
scores = net.classify(lena)
print 'prediction:', net.top_k_prediction(scores, 5)
visualize.draw_net_to_file(net._net, 'jeffnet.png')
print 'Network structure written to jeffnet.png'
"""This demo will show how we do simple convolution on the lena image with
a 15*15 average filter.
"""
from decaf import base
from decaf.util import smalldata
from decaf.layers import convolution, fillers
import numpy as np
from skimage import io
"""The main demo code."""
img = np.asarray(smalldata.lena())
img = img.reshape((1,) + img.shape).astype(np.float64)
# wrap the img in a blob
input_blob = base.Blob()
input_blob.mirror(img)
# create a convolutional layer
layer = convolution.ConvolutionLayer(
name='convolution',
num_kernels=1,
ksize=15,
stride=1,
mode='same',
filler=fillers.ConstantFiller(value=1./15/15/3))
# run the layer
output_blob = base.Blob()
layer.forward([input_blob], [output_blob])
out = np.multiply(output_blob.data()[0, :, :, 0], 256).astype(np.uint8)
"""A bunch of test scripts to check the performance of jeffnet.
Recommended running command:
srun -p vision -c 8 --nodelist=orange6 python test_lena_prediction_pipeline.py
"""
from decaf.scripts import jeffnet
from decaf import util
from decaf.util import smalldata
import numpy as np
import cProfile as profile
# We will use a larger figure size since many figures are fairly big.
data_root='/u/vis/common/deeplearning/models/'
net = jeffnet.JeffNet(data_root+'imagenet.jeffnet.epoch90', data_root+'imagenet.jeffnet.meta')
lena = smalldata.lena()
timer = util.Timer()
print 'Testing single classification with 10-part voting (10 runs)...'
# run a pass to initialize data
scores = net.classify(lena)
timer.reset()
for i in range(10):
scores = net.classify(lena)
print 'Elapsed %s' % timer.total()
print 'Testing single classification with center_only (10 runs)...'
# run a pass to initialize data
scores = net.classify(lena, center_only=True)
timer.reset()
for i in range(10):
scores = net.classify(lena, center_only=True)
print 'Elapsed %s' % timer.total()
import argparse import sys import numpy as np try: import matplotlib.pyplot as pylab except: import scipy.misc as pylab from decaf.scripts.jeffnet import JeffNet from decaf.util import smalldata data_root = '/home/rodner/data/deeplearning/models/' if len(sys.argv)<2:\ img = smalldata.lena() else: imgfn = sys.argv[1] img = pylab.imread(imgfn) net = JeffNet(data_root+'imagenet.jeffnet.epoch90', data_root+'imagenet.jeffnet.meta') print "Classify image" for i in range(5): scores = net.classify(img, center_only=True) print "Okay" #print net.top_k_prediction(scores, 10)[1]
"""A bunch of test scripts to check the performance of decafnet.
Recommended running command:
srun -p vision -c 8 --nodelist=orange6 python test_lena_prediction_pipeline.py
"""
from decaf.scripts import decafnet
from decaf import util
from decaf.util import smalldata
import numpy as np
import cProfile as profile
# We will use a larger figure size since many figures are fairly big.
data_root='/u/vis/common/deeplearning/models/'
net = imagenet.DecafNet(data_root+'imagenet.decafnet.epoch90', data_root+'imagenet.decafnet.meta')
lena = smalldata.lena()
timer = util.Timer()
print 'Testing single classification with 10-part voting (10 runs)...'
# run a pass to initialize data
scores = net.classify(lena)
timer.reset()
for i in range(10):
scores = net.classify(lena)
print 'Elapsed %s' % timer.total()
print 'Testing single classification with center_only (10 runs)...'
# run a pass to initialize data
scores = net.classify(lena, center_only=True)
timer.reset()
for i in range(10):
scores = net.classify(lena, center_only=True)
print 'Elapsed %s' % timer.total()
"""This demo will show how we do simple convolution on the lena image with
a 15*15 average filter.
"""
from decaf import base
from decaf.util import smalldata
from decaf.layers import convolution, fillers
import numpy as np
from skimage import io
"""The main demo code."""
img = np.asarray(smalldata.lena())
img = img.reshape((1, ) + img.shape).astype(np.float64)
# wrap the img in a blob
input_blob = base.Blob()
input_blob.mirror(img)
# create a convolutional layer
layer = convolution.ConvolutionLayer(
name='convolution',
num_kernels=1,
ksize=15,
stride=1,
mode='same',
filler=fillers.ConstantFiller(value=1. / 15 / 15 / 3))
# run the layer
output_blob = base.Blob()
layer.forward([input_blob], [output_blob])
out = np.multiply(output_blob.data()[0, :, :, 0], 256).astype(np.uint8)
io.imsave('out.png', out)
