def test_sample_ae():
"""
Visualize some samples from the trained unsupervised GSN.
"""
with open("gsn_ae_example.pkl") as f:
gsn = pickle.load(f)
# random point to start at
mb_data = MNIST(which_set='test').X[105:106, :]
history = gsn.get_samples([(0, mb_data)], walkback=1000,
symbolic=False, include_first=True)
history = list(itertools.chain(*history))
history = np.vstack(history)
tiled = image.tile_raster_images(history,
img_shape=[28,28],
tile_shape=[50,50],
tile_spacing=(2,2))
image.save("gsn_ae_example.png", tiled)
# code to get log likelihood from kernel density estimator
# this crashed on GPU (out of memory), but works on CPU
pw = ParzenWindows(MNIST(which_set='test').X, .20)
print pw.get_ll(history)
def test_sample_supervised(idxs=None, noisy=True):
"""
Visualize samples and labels produced by GSN.
"""
with open("gsn_sup_example.pkl") as f:
gsn = pickle.load(f)
gsn._corrupt_switch = noisy
ds = MNIST(which_set='test', one_hot=True)
if idxs is None:
data = ds.X[100:150]
else:
data = ds.X[idxs]
# change the walkback parameter to make the data fill up rows in image
samples = gsn.get_samples([(0, data)],
indices=[0, 2],
walkback=21, symbolic=False,
include_first=True)
stacked = vis_samples(samples)
tiled = image.tile_raster_images(stacked,
img_shape=[28,28],
tile_shape=[50,50],
tile_spacing=(2,2))
image.save("gsn_sup_example.png", tiled)
def test_sample_ae():
"""
Visualize some samples from the trained unsupervised GSN.
"""
with open("gsn_ae_example.pkl") as f:
gsn = pickle.load(f)
# random point to start at
mb_data = MNIST(which_set='test').X[105:106, :]
history = gsn.get_samples([(0, mb_data)],
walkback=1000,
symbolic=False,
include_first=True)
history = list(itertools.chain(*history))
history = np.vstack(history)
tiled = image.tile_raster_images(history,
img_shape=[28, 28],
tile_shape=[50, 50],
tile_spacing=(2, 2))
image.save("gsn_ae_example.png", tiled)
# code to get log likelihood from kernel density estimator
# this crashed on GPU (out of memory), but works on CPU
pw = ParzenWindows(MNIST(which_set='test').X, .20)
print(pw.get_ll(history))
def test_sample_supervised(idxs=None, noisy=True):
"""
Visualize samples and labels produced by GSN.
"""
with open("gsn_sup_example.pkl") as f:
gsn = pickle.load(f)
gsn._corrupt_switch = noisy
ds = MNIST(which_set='test')
if idxs is None:
data = ds.X[100:150]
else:
data = ds.X[idxs]
# change the walkback parameter to make the data fill up rows in image
samples = gsn.get_samples([(0, data)],
indices=[0, 2],
walkback=21,
symbolic=False,
include_first=True)
stacked = vis_samples(samples)
tiled = image.tile_raster_images(stacked,
img_shape=[28, 28],
tile_shape=[50, 50],
tile_spacing=(2, 2))
image.save("gsn_sup_example.png", tiled)
def demo():
num_frames = 300
height = 10
width = 10
config = BilliardVideoConfig(
num_frames = num_frames,
height = height,
width = width,
ball_diameter = 5,
min_val = .1,
max_val = .9,
vel_multiplier = 4.0,
vel_noise = .04,
vel_decay = .001,
frames_burnin = 1000,
frames_simulate = 20000,
)
bil = BilliardVideo('train', config)
iterator = bil.iterator(mode = None,
batch_size = 10,
num_batches = 2,
ignore_data_specs = True)
for batch_idx, batch in enumerate(iterator):
#print batch.shape
#print batch.sum()
assert len(batch.shape) == 5
assert batch.shape[4] == 1 # single channel
if batch_idx == 0:
prefix = 'billiard_frame_'
for frame_idx in xrange(num_frames):
frameIm = image.tile_raster_images(batch[0,frame_idx:frame_idx+1], img_shape = (height,width), tile_shape=(1,1))
image.save('%s%03d.png' % (prefix, frame_idx), frameIm)
print 'Saved: %s*.png' % prefix
print 'Convert to gif by running:\n convert -delay 3 %s* billiard_video.gif' % (prefix)
flattened = np.reshape(batch,
(batch.shape[0]*batch.shape[1],
np.prod(batch.shape[2:])))
tiled = image.tile_raster_images(-flattened,
img_shape=[height, width],
tile_shape=[batch.shape[0], batch.shape[1]],
tile_spacing=(5,1))
filename = 'billiard_batch_%03d.png' % batch_idx
image.save(filename, tiled)
#image.save(filename, 255-tiled)
print 'Saved:', filename
from pylearn2.utils import image
import numpy as np
for i in xrange(5000):
print i
number = str(i)
while len(number) != 4:
number = '0' + number
img = image.load('/Tmp/video/' + number + '.png')
out = np.zeros((406, 406, 3))
for ofs_r in [0, 1]:
for ofs_c in [0, 1]:
out[ofs_r::2, ofs_c::2, :] = img
image.save('/Tmp/video_resized/' + number + '.png', out)
if isinstance(space, VectorSpace):
# For some reason format_as from VectorSpace is not working right
samples = model.generator.mlp.fprop(Z).eval()
is_color = samples.shape[-1] % 3 == 0 and samples.shape[-1] != 48 * 48
samples = dataset.get_topological_view(samples)
else:
total_dimension = space.get_total_dimension()
import numpy as np
num_colors = 1
if total_dimension % 3 == 0:
num_colors = 3
w = int(np.sqrt(total_dimension / num_colors))
from pylearn2.space import Conv2DSpace
desired_space = Conv2DSpace(shape=[w, w], num_channels=num_colors, axes=('b',0,1,'c'))
samples = space.format_as(batch=model.generator.mlp.fprop(Z),
space=desired_space).eval()
is_color = samples.shape[-1] == 3
from pylearn2.utils import image
for i in xrange(endpoints * steps_per_point):
img = samples[i, :, :, :]
img /= np.abs(img).max()
number = str(i)
while len(number) < len(str(endpoints * steps_per_point)):
number = '0' + number
path = 'video/' + number + '.png'
image.save(path, img)
