def test_init_with_X_or_topo():
# tests that constructing with topo_view works
# tests that construction with design matrix works
# tests that conversion from topo_view to design matrix and back works
# tests that conversion the other way works too
rng = np.random.RandomState([1, 2, 3])
topo_view = rng.randn(5, 2, 2, 3)
d1 = DenseDesignMatrix(topo_view=topo_view)
X = d1.get_design_matrix()
d2 = DenseDesignMatrix(X=X, view_converter=d1.view_converter)
topo_view_2 = d2.get_topological_view()
assert np.allclose(topo_view, topo_view_2)
X = rng.randn(*X.shape)
topo_view_3 = d2.get_topological_view(X)
X2 = d2.get_design_matrix(topo_view_3)
assert np.allclose(X, X2)
def test_init_with_X_or_topo():
# tests that constructing with topo_view works
# tests that construction with design matrix works
# tests that conversion from topo_view to design matrix and back works
# tests that conversion the other way works too
rng = np.random.RandomState([1, 2, 3])
topo_view = rng.randn(5, 2, 2, 3)
d1 = DenseDesignMatrix(topo_view=topo_view)
X = d1.get_design_matrix()
d2 = DenseDesignMatrix(X=X, view_converter=d1.view_converter)
topo_view_2 = d2.get_topological_view()
assert np.allclose(topo_view, topo_view_2)
X = rng.randn(*X.shape)
topo_view_3 = d2.get_topological_view(X)
X2 = d2.get_design_matrix(topo_view_3)
assert np.allclose(X, X2)
def test_extract_reassemble():
""" Tests that ExtractGridPatches and ReassembleGridPatches are
inverse of each other """
rng = np.random.RandomState([1, 3, 7])
topo = rng.randn(4, 3 * 5, 3 * 7, 2)
dataset = DenseDesignMatrix(topo_view=topo)
patch_shape = (3, 7)
extractor = ExtractGridPatches(patch_shape, patch_shape)
reassemblor = ReassembleGridPatches(patch_shape=patch_shape,
orig_shape=topo.shape[1:3])
dataset.apply_preprocessor(extractor)
dataset.apply_preprocessor(reassemblor)
new_topo = dataset.get_topological_view()
assert new_topo.shape == topo.shape
if not np.all(new_topo == topo):
assert False
def test_extract_reassemble():
""" Tests that ExtractGridPatches and ReassembleGridPatches are
inverse of each other """
rng = np.random.RandomState([1, 3, 7])
topo = rng.randn(4, 3 * 5, 3 * 7, 2)
dataset = DenseDesignMatrix(topo_view=topo)
patch_shape = (3, 7)
extractor = ExtractGridPatches(patch_shape, patch_shape)
reassemblor = ReassembleGridPatches(patch_shape=patch_shape,
orig_shape=topo.shape[1:3])
dataset.apply_preprocessor(extractor)
dataset.apply_preprocessor(reassemblor)
new_topo = dataset.get_topological_view()
assert new_topo.shape == topo.shape
if not np.all(new_topo == topo):
assert False
def get_feats_from_cnn(rows, model=None):
"""
fprop rows using best trained model and returns activations of the
penultimate layer
"""
conf = utils.get_config()
patch_size = conf['patch_size']
region_size = conf['region_size']
batch_size = None
preds = utils.get_predictor(model=model, return_all=True)
y = np.zeros(len(rows))
samples = np.zeros(
(len(rows), region_size, region_size, 1), dtype=np.float32)
for i, row in enumerate(rows):
print 'processing %i-th image: %s' % (i, row['image_filename'])
try:
samples[i] = utils.get_samples_from_image(row, False)[0]
except ValueError as e:
print '{1} Value error: {0}'.format(str(e), row['image_filename'])
y[i] = utils.is_positive(row)
ds = DenseDesignMatrix(topo_view=samples)
pipeline = utils.get_pipeline(
ds.X_topo_space.shape, patch_size, batch_size)
pipeline.apply(ds)
return preds[-2](ds.get_topological_view()), y
def get_feats_from_cnn(rows, model=None):
"""
fprop rows using best trained model and returns activations of the
penultimate layer
"""
conf = utils.get_config()
patch_size = conf['patch_size']
region_size = conf['region_size']
batch_size = None
preds = utils.get_predictor(model=model, return_all=True)
y = np.zeros(len(rows))
samples = np.zeros((len(rows), region_size, region_size, 1),
dtype=np.float32)
for i, row in enumerate(rows):
print 'processing %i-th image: %s' % (i, row['image_filename'])
try:
samples[i] = utils.get_samples_from_image(row, False)[0]
except ValueError as e:
print '{1} Value error: {0}'.format(str(e), row['image_filename'])
y[i] = utils.is_positive(row)
ds = DenseDesignMatrix(topo_view=samples)
pipeline = utils.get_pipeline(ds.X_topo_space.shape, patch_size,
batch_size)
pipeline.apply(ds)
return preds[-2](ds.get_topological_view()), y
print 'running theano function'
feat = f(X2)
feat_dataset = DenseDesignMatrix(X=feat,
view_converter=DefaultViewConverter(
[1, 1, feat.shape[1]]))
print 'reassembling features'
ns = 32 - size + 1
depatchifier = ReassembleGridPatches(orig_shape=(ns, ns),
patch_shape=(1, 1))
feat_dataset.apply_preprocessor(depatchifier)
print 'making topological view'
topo_feat = feat_dataset.get_topological_view()
assert topo_feat.shape[0] == X.shape[0]
print 'assembling visualizer'
n = np.ceil(np.sqrt(model.nhid))
pv3 = PatchViewer(grid_shape=(X.shape[0], num_filters),
patch_shape=(ns, ns),
is_color=False)
pv4 = PatchViewer(grid_shape=(n, n),
patch_shape=(size, size),
is_color=True,
pad=(7, 7))
pv5 = PatchViewer(grid_shape=(1, num_filters),
patch_shape=(size, size),
print 'compiling theano function'
f = function([V],feat)
print 'running theano function'
feat = f(X2)
feat_dataset = DenseDesignMatrix(X = feat, view_converter = DefaultViewConverter([1, 1, feat.shape[1]] ) )
print 'reassembling features'
ns = 32 - size + 1
depatchifier = ReassembleGridPatches( orig_shape = (ns, ns), patch_shape=(1,1) )
feat_dataset.apply_preprocessor(depatchifier)
print 'making topological view'
topo_feat = feat_dataset.get_topological_view()
assert topo_feat.shape[0] == X.shape[0]
print 'assembling visualizer'
n = np.ceil(np.sqrt(model.nhid))
pv3 = PatchViewer(grid_shape = (X.shape[0], num_filters), patch_shape=(ns,ns), is_color= False)
pv4 = PatchViewer(grid_shape = (n,n), patch_shape = (size,size), is_color = True, pad = (7,7))
pv5 = PatchViewer(grid_shape = (1,num_filters), patch_shape = (size,size), is_color = True, pad = (7,7))
idx = sorted(range(model.nhid), key = lambda l : -topo_feat[:,:,:,l].std() )
W = model.W.get_value()
weights_view = dataset.get_weights_view( W.T )
def make_majority_vote():
model_paths = ['convnet_' + str(i + 1) + '.pkl' for i in range(10)]
out_path = 'submission.csv'
models = []
for model_path in model_paths:
print('Loading ' + model_path + '...')
try:
with open(model_path, 'rb') as f:
models.append(pkl.load(f))
except Exception as e:
try:
with gzip.open(model_path, 'rb') as f:
models.append(pkl.load(f))
except Exception as e:
usage()
print(
model_path +
"doesn't seem to be a valid model path, I got this error when trying to load it: "
)
print(e)
# load the test set
with open('test_data_for_pylearn2.pkl', 'rb') as f:
dataset = pkl.load(f)
dataset = DenseDesignMatrix(X=dataset,
view_converter=DefaultViewConverter(
shape=[32, 32, 1], axes=['b', 0, 1, 'c']))
preprocessor = GlobalContrastNormalization(subtract_mean=True,
sqrt_bias=0.0,
use_std=True)
preprocessor.apply(dataset)
predictions = []
print('Model description:')
print('')
print(models[1])
print('')
for model in models:
model.set_batch_size(dataset.X.shape[0])
X = model.get_input_space().make_batch_theano()
Y = model.fprop(X) # forward prop the test data
y = T.argmax(Y, axis=1)
f = function([X], y)
x_arg = dataset.get_topological_view()
y = f(x_arg.astype(X.dtype))
assert y.ndim == 1
assert y.shape[0] == dataset.X.shape[0]
# add one to the results!
y += 1
predictions.append(y)
predictions = np.array(predictions, dtype='int32')
y = mode(predictions.T, axis=1)[0]
y = np.array(y, dtype='int32')
import itertools
y = list(itertools.chain(*y))
assert len(y) == dataset.X.shape[0]
util.write_results(y, out_path)
print('Wrote predictions to submission.csv.')
return np.reshape(y, (1, -1))
from pylearn2.utils import serial
stl10 = serial.load('/data/lisa/data/stl10/stl10_32x32/train.pkl')
batch = stl10.X[24:25,:]
img = stl10.view_converter.design_mat_to_topo_view(batch)[0,...] / 127.5
from pylearn2.gui.patch_viewer import PatchViewer
pv = PatchViewer((27,27),(6,6),pad=(1,1),is_color=True)
pipeline = serial.load('/data/lisa/data/stl10/stl10_patches/preprocessor.pkl')
del pipeline.items[0]
from pylearn2.datasets.dense_design_matrix import DenseDesignMatrix, DefaultViewConverter
for row in xrange(27):
for col in xrange(27):
patch = img[row:row+6,col:col+6]
d = DenseDesignMatrix( topo_view = patch.reshape(1,6,6,3), view_converter = DefaultViewConverter((6,6,3)) )
d.apply_preprocessor(pipeline)
pv.add_patch(d.get_topological_view()[0,...], rescale = True)
pv.show()
def make_majority_vote():
model_paths = ['convnet_' + str(i+1) + '.pkl' for i in range(10)]
out_path = 'submission.csv'
models = []
for model_path in model_paths:
print('Loading ' + model_path + '...')
try:
with open(model_path, 'rb') as f:
models.append(pkl.load(f))
except Exception as e:
try:
with gzip.open(model_path, 'rb') as f:
models.append(pkl.load(f))
except Exception as e:
usage()
print(model_path + "doesn't seem to be a valid model path, I got this error when trying to load it: ")
print(e)
# load the test set
with open('test_data_for_pylearn2.pkl', 'rb') as f:
dataset = pkl.load(f)
dataset = DenseDesignMatrix(X=dataset, view_converter=DefaultViewConverter(shape=[32, 32, 1], axes=['b', 0, 1, 'c']))
preprocessor = GlobalContrastNormalization(subtract_mean=True, sqrt_bias=0.0, use_std=True)
preprocessor.apply(dataset)
predictions = []
print('Model description:')
print('')
print(models[1])
print('')
for model in models:
model.set_batch_size(dataset.X.shape[0])
X = model.get_input_space().make_batch_theano()
Y = model.fprop(X) # forward prop the test data
y = T.argmax(Y, axis=1)
f = function([X], y)
x_arg = dataset.get_topological_view()
y = f(x_arg.astype(X.dtype))
assert y.ndim == 1
assert y.shape[0] == dataset.X.shape[0]
# add one to the results!
y += 1
predictions.append(y)
predictions = np.array(predictions, dtype='int32')
y = mode(predictions.T, axis=1)[0]
y = np.array(y, dtype='int32')
import itertools
y = list(itertools.chain(*y))
assert len(y) == dataset.X.shape[0]
util.write_results(y, out_path)
print('Wrote predictions to submission.csv.')
return np.reshape(y, (1, -1))
def sar_predict(ann, image, outfile):
'''Predict on a image use a trianed model ann'''
#define prediction function
batch_size = ann.batch_size
X = ann.get_input_space().make_batch_theano()
y = ann.fprop(X)
f = theano.function([X], y)
#moving window
window = ann.get_input_space().shape[0]
rl = int(math.floor(window / 2))
rr = int(window - rl)
#extract patch
stride = 1
jcol = range(rl, image.shape[2] - rr, stride)
irow = range(rl, image.shape[1] - rr, stride)
nrow = len(irow)
ncol = len(jcol)
batch_size = ann.batch_size
yaml_src = ann.dataset_yaml_src.split()
mean_std_file = yaml_src[yaml_src.index('mean_std_file:') + 1]
# mean_std_file = re.search('\w+...\w+', mean_std_file).group(0)
mean_std_file = mean_std_file[1:-3]
print "mean_std_file:" + mean_std_file
preprocessor = Standardize(mean_std_file=mean_std_file)
# ann.set_batch_size(batch_size)
m = len(jcol) * len(irow)
extra = batch_size - m % batch_size
im_pred_tmp = np.zeros(shape=(m, ann.get_output_space().dim))
xshape = ann.get_input_space().shape
subimgs = np.zeros(shape=(batch_size, ann.get_input_space().num_channels,
xshape[0], xshape[1]),
dtype=ann.get_input_space().dtype)
for i in range(0, m - m % batch_size, batch_size):
for j in range(i, i + batch_size):
pos = [
math.floor(j / ncol) * stride + irow[0],
(j % ncol) * stride + jcol[0]
]
subimgs[j - i, :] = image[:, pos[0] - rl:pos[0] + rr,
pos[1] - rl:pos[1] + rr]
#the default input_space for pylearn convnet is (b,0,1,c)
#the axis of subimgs should be permuted
batch = DenseDesignMatrix(topo_view=np.transpose(
subimgs, (0, 2, 3, 1)),
axes=('b', 0, 1, 'c'))
preprocessor.apply(batch)
im_pred_tmp[i:i + batch_size, :] = f(batch.get_topological_view())
im_pred_tmp = np.transpose(im_pred_tmp)
im_pred_tmp = im_pred_tmp.reshape(im_pred_tmp.shape[0], nrow, ncol)
#output tif
def WriteArrayToTiff(array, outfile):
driver = gdal.GetDriverByName('GTiff')
ds = driver.Create(outfile, array.shape[2], array.shape[1],
array.shape[0], GDT_Float32)
nchannels = im_pred_tmp.shape[0]
for band, i in zip(array, range(nchannels)):
ds.GetRasterBand(i + 1).WriteArray(array[i, :, :])
ds.FlushCache()
ds = None
im_pred = np.zeros(shape=(im_pred_tmp.shape[0], image.shape[1],
image.shape[2]))
im_pred[:, rl:image.shape[1] - rr, rl:image.shape[2] - rr] = im_pred_tmp
# np.save(outfile+".pyn",im_pred)
WriteArrayToTiff(im_pred, outfile)
print 'prediction max is {}'.format(im_pred.max())
print(len(models))
for model in models:
print(model)
model.set_batch_size(dataset.X.shape[0])
X = model.get_input_space().make_batch_theano()
Y = model.fprop(X) # forward prop the test data
y = T.argmax(Y, axis=1)
f = function([X], y)
x_arg = dataset.get_topological_view()
y = f(x_arg.astype(X.dtype))
assert y.ndim == 1
assert y.shape[0] == dataset.X.shape[0]
# add one to the results!
y += 1
predictions.append(y)
print(y)
predictions = np.array(predictions, dtype='int32')
y = mode(predictions.T, axis=1)[0]
y = np.array(y, dtype='int32')
