def test_triangle_code():
rng = np.random.RandomState([20,18,9])
m = 5
n = 6
k = 7
X = as_floatX(rng.randn(m,n))
D = as_floatX(rng.randn(k,n))
D_norm_squared = np.sum(D**2,axis=1)
X_norm_squared = np.sum(X**2,axis=1)
sq_distance = -2.0 * np.dot(X,D.T) + D_norm_squared + np.atleast_2d(X_norm_squared).T
distance = np.sqrt(sq_distance)
mu = np.mean(distance, axis = 1)
expected = np.maximum(0.0,mu.reshape(mu.size,1)-distance)
Xv = T.matrix()
Dv = T.matrix()
code = triangle_code(X = Xv, centroids = Dv)
actual = function([Xv,Dv],code)(X,D)
assert np.allclose(expected, actual)
def _execute(self):
global num_superpixels
num_output_features = self.num_output_features
idxs = self.idxs
top = self.top
bottom = self.bottom
left = self.left
right = self.right
save_path = self.save_path
batch_size = self.batch_size
dataset_family = self.dataset_family
which_set = self.which_set
model = self.model
size = self.size
nan = 0
dataset_descriptor = dataset_family[which_set][size]
dataset = dataset_descriptor.dataset_maker()
expected_num_examples = dataset_descriptor.num_examples
full_X = dataset.get_design_matrix()
num_examples = full_X.shape[0]
assert num_examples == expected_num_examples
if self.restrict is not None:
assert self.restrict[1] <= full_X.shape[0]
print('restricting to examples ',self.restrict[0],' through ',self.restrict[1],' exclusive')
full_X = full_X[self.restrict[0]:self.restrict[1],:]
assert self.restrict[1] > self.restrict[0]
#update for after restriction
num_examples = full_X.shape[0]
assert num_examples > 0
dataset.X = None
dataset.design_loc = None
dataset.compress = False
patchifier = ExtractGridPatches( patch_shape = (size,size), patch_stride = (1,1) )
pipeline = serial.load(dataset_descriptor.pipeline_path)
assert isinstance(pipeline.items[0], ExtractPatches)
pipeline.items[0] = patchifier
print('defining features')
V = T.matrix('V')
mu = model.mu
feat = triangle_code(V, mu)
assert feat.dtype == 'float32'
print('compiling theano function')
f = function([V],feat)
nhid = model.mu.get_value().shape[0]
if config.device.startswith('gpu') and nhid >= 4000:
f = halver(f, model.nhid)
topo_feat_var = T.TensorType(broadcastable = (False,False,False,False), dtype='float32')()
if self.pool_mode == 'mean':
region_features = function([topo_feat_var],
topo_feat_var.mean(axis=(1,2)) )
elif self.pool_mode == 'max':
region_features = function([topo_feat_var],
topo_feat_var.max(axis=(1,2)) )
else:
assert False
def average_pool( stride ):
def point( p ):
return p * ns / stride
rval = np.zeros( (topo_feat.shape[0], stride, stride, topo_feat.shape[3] ) , dtype = 'float32')
for i in xrange(stride):
for j in xrange(stride):
rval[:,i,j,:] = region_features( topo_feat[:,point(i):point(i+1), point(j):point(j+1),:] )
return rval
output = np.zeros((num_examples,num_output_features),dtype='float32')
fd = DenseDesignMatrix(X = np.zeros((1,1),dtype='float32'), view_converter = DefaultViewConverter([1, 1, nhid] ) )
ns = 32 - size + 1
depatchifier = ReassembleGridPatches( orig_shape = (ns, ns), patch_shape=(1,1) )
if len(range(0,num_examples-batch_size+1,batch_size)) <= 0:
print(num_examples)
print(batch_size)
for i in xrange(0,num_examples-batch_size+1,batch_size):
print(i)
t1 = time.time()
d = copy.copy(dataset)
d.set_design_matrix(full_X[i:i+batch_size,:])
t2 = time.time()
#print '\tapplying preprocessor'
d.apply_preprocessor(pipeline, can_fit = False)
X2 = d.get_design_matrix()
t3 = time.time()
#print '\trunning theano function'
feat = f(X2)
t4 = time.time()
assert feat.dtype == 'float32'
feat_dataset = copy.copy(fd)
if contains_nan(feat):
nan += np.isnan(feat).sum()
feat[np.isnan(feat)] = 0
feat_dataset.set_design_matrix(feat)
#print '\treassembling features'
feat_dataset.apply_preprocessor(depatchifier)
#print '\tmaking topological view'
topo_feat = feat_dataset.get_topological_view()
assert topo_feat.shape[0] == batch_size
t5 = time.time()
#average pooling
superpixels = average_pool(num_superpixels)
assert batch_size == 1
if self.pool_mode == 'mean':
for j in xrange(num_output_features):
output[i:i+batch_size, j] = superpixels[:,top[j]:bottom[j]+1,
left[j]:right[j]+1, idxs[j]].mean()
elif self.pool_mode == 'max':
for j in xrange(num_output_features):
output[i:i+batch_size, j] = superpixels[:,top[j]:bottom[j]+1,
left[j]:right[j]+1, idxs[j]].max()
else:
assert False
assert output[i:i+batch_size,:].max() < 1e20
t6 = time.time()
print((t6-t1, t2-t1, t3-t2, t4-t3, t5-t4, t6-t5))
if self.chunk_size is not None:
assert save_path.endswith('.npy')
save_path_pieces = save_path.split('.npy')
assert len(save_path_pieces) == 2
assert save_path_pieces[1] == ''
save_path = save_path_pieces[0] + '_' + chr(ord('A')+self.chunk_id)+'.npy'
np.save(save_path,output)
if nan > 0:
warnings.warn(str(nan)+' features were nan')
def _execute(self):
global num_superpixels
num_output_features = self.num_output_features
idxs = self.idxs
top = self.top
bottom = self.bottom
left = self.left
right = self.right
save_path = self.save_path
batch_size = self.batch_size
dataset_family = self.dataset_family
which_set = self.which_set
model = self.model
size = self.size
nan = 0
dataset_descriptor = dataset_family[which_set][size]
dataset = dataset_descriptor.dataset_maker()
expected_num_examples = dataset_descriptor.num_examples
full_X = dataset.get_design_matrix()
num_examples = full_X.shape[0]
assert num_examples == expected_num_examples
if self.restrict is not None:
assert self.restrict[1] <= full_X.shape[0]
print 'restricting to examples ', self.restrict[
0], ' through ', self.restrict[1], ' exclusive'
full_X = full_X[self.restrict[0]:self.restrict[1], :]
assert self.restrict[1] > self.restrict[0]
#update for after restriction
num_examples = full_X.shape[0]
assert num_examples > 0
dataset.X = None
dataset.design_loc = None
dataset.compress = False
patchifier = ExtractGridPatches(patch_shape=(size, size),
patch_stride=(1, 1))
pipeline = serial.load(dataset_descriptor.pipeline_path)
assert isinstance(pipeline.items[0], ExtractPatches)
pipeline.items[0] = patchifier
print 'defining features'
V = T.matrix('V')
mu = model.mu
feat = triangle_code(V, mu)
assert feat.dtype == 'float32'
print 'compiling theano function'
f = function([V], feat)
nhid = model.mu.get_value().shape[0]
if config.device.startswith('gpu') and nhid >= 4000:
f = halver(f, model.nhid)
topo_feat_var = T.TensorType(broadcastable=(False, False, False,
False),
dtype='float32')()
if self.pool_mode == 'mean':
region_features = function([topo_feat_var],
topo_feat_var.mean(axis=(1, 2)))
elif self.pool_mode == 'max':
region_features = function([topo_feat_var],
topo_feat_var.max(axis=(1, 2)))
else:
assert False
def average_pool(stride):
def point(p):
return p * ns / stride
rval = np.zeros(
(topo_feat.shape[0], stride, stride, topo_feat.shape[3]),
dtype='float32')
for i in xrange(stride):
for j in xrange(stride):
rval[:, i, j, :] = region_features(
topo_feat[:,
point(i):point(i + 1),
point(j):point(j + 1), :])
return rval
output = np.zeros((num_examples, num_output_features), dtype='float32')
fd = DenseDesignMatrix(X=np.zeros((1, 1), dtype='float32'),
view_converter=DefaultViewConverter(
[1, 1, nhid]))
ns = 32 - size + 1
depatchifier = ReassembleGridPatches(orig_shape=(ns, ns),
patch_shape=(1, 1))
if len(range(0, num_examples - batch_size + 1, batch_size)) <= 0:
print num_examples
print batch_size
for i in xrange(0, num_examples - batch_size + 1, batch_size):
print i
t1 = time.time()
d = copy.copy(dataset)
d.set_design_matrix(full_X[i:i + batch_size, :])
t2 = time.time()
#print '\tapplying preprocessor'
d.apply_preprocessor(pipeline, can_fit=False)
X2 = d.get_design_matrix()
t3 = time.time()
#print '\trunning theano function'
feat = f(X2)
t4 = time.time()
assert feat.dtype == 'float32'
feat_dataset = copy.copy(fd)
if np.any(np.isnan(feat)):
nan += np.isnan(feat).sum()
feat[np.isnan(feat)] = 0
feat_dataset.set_design_matrix(feat)
#print '\treassembling features'
feat_dataset.apply_preprocessor(depatchifier)
#print '\tmaking topological view'
topo_feat = feat_dataset.get_topological_view()
assert topo_feat.shape[0] == batch_size
t5 = time.time()
#average pooling
superpixels = average_pool(num_superpixels)
assert batch_size == 1
if self.pool_mode == 'mean':
for j in xrange(num_output_features):
output[i:i + batch_size,
j] = superpixels[:, top[j]:bottom[j] + 1,
left[j]:right[j] + 1,
idxs[j]].mean()
elif self.pool_mode == 'max':
for j in xrange(num_output_features):
output[i:i + batch_size,
j] = superpixels[:, top[j]:bottom[j] + 1,
left[j]:right[j] + 1,
idxs[j]].max()
else:
assert False
assert output[i:i + batch_size, :].max() < 1e20
t6 = time.time()
print(t6 - t1, t2 - t1, t3 - t2, t4 - t3, t5 - t4, t6 - t5)
if self.chunk_size is not None:
assert save_path.endswith('.npy')
save_path_pieces = save_path.split('.npy')
assert len(save_path_pieces) == 2
assert save_path_pieces[1] == ''
save_path = save_path_pieces[0] + '_' + chr(
ord('A') + self.chunk_id) + '.npy'
np.save(save_path, output)
if nan > 0:
warnings.warn(str(nan) + ' features were nan')
