def oneMix(mask, data=None, target=None):
#Mix
if not (data is None):
stackedMask0, _ = torch.broadcast_tensors(mask[0], data[0])
data = (stackedMask0 * data[0] +
(1 - stackedMask0) * data[1]).unsqueeze(0)
if not (target is None):
stackedMask0, _ = torch.broadcast_tensors(mask[0], target[0])
target = (stackedMask0 * target[0] +
(1 - stackedMask0) * target[1]).unsqueeze(0)
return data, target
def face_add_arbitrary(faces, face_ix_to, per_face_data, output, counts=None):
ind_1d = faces[:, face_ix_to]
one = torch.ones((1, ), dtype=torch.float32, device=faces.device)
if len(ind_1d.shape) < len(per_face_data.shape):
ind_2d, _ = torch.broadcast_tensors(ind_1d.unsqueeze(1), per_face_data)
else:
ind_2d = ind_1d
one_1d, _ = torch.broadcast_tensors(one, ind_1d)
output.scatter_add_(0, ind_2d, per_face_data)
if counts is not None:
counts.scatter_add_(0, ind_1d, one_1d)
def __and__(self, y):
"""Bitwise AND operator (element-wise)"""
result = self.clone()
# TODO: Remove explicit broadcasts to allow smaller beaver triples
if isinstance(y, BinarySharedTensor):
broadcast_tensors = torch.broadcast_tensors(result.share, y.share)
result.share = broadcast_tensors[0].clone()
elif torch.is_tensor(y):
broadcast_tensors = torch.broadcast_tensors(result.share, y)
result.share = broadcast_tensors[0].clone()
return result.__iand__(y)
def normalize(MEAN, STD, data=None, target=None):
#Normalize
if not (data is None):
if data.shape[1] == 3:
STD = torch.Tensor(STD).unsqueeze(0).unsqueeze(2).unsqueeze(
3).cuda()
MEAN = torch.Tensor(MEAN).unsqueeze(0).unsqueeze(2).unsqueeze(
3).cuda()
STD, data = torch.broadcast_tensors(STD, data)
MEAN, data = torch.broadcast_tensors(MEAN, data)
data = ((data - MEAN) / STD).float()
return data, target
def test_method_interface():
shape = 11, 13
lin = LinearMasked(*shape)
mask = torch.tensor(1.0)
lin.mask_(mask)
assert torch.allclose(*torch.broadcast_tensors(lin.mask, mask))
assert torch.allclose(lin.weight_masked, mask * lin.weight)
lin.mask_(None)
assert lin.mask is None
with pytest.raises(RuntimeError, match=r"has no sparsity mask"):
lin.weight_masked
# enable/disable
mask = torch.randint(2, size=(1, 1)).float()
lin.mask_(mask)
assert torch.allclose(*torch.broadcast_tensors(lin.mask, mask))
assert torch.allclose(lin.weight_masked, mask * lin.weight)
# output masking
mask = torch.randint(2, size=(shape[1], 1)).float()
lin.mask_(mask)
assert torch.allclose(*torch.broadcast_tensors(lin.mask, mask))
assert torch.allclose(lin.weight_masked, mask * lin.weight)
# input masking
mask = torch.randint(2, size=(
1,
shape[0],
)).float()
lin.mask_(mask)
assert torch.allclose(*torch.broadcast_tensors(lin.mask, mask))
assert torch.allclose(lin.weight_masked, mask * lin.weight)
# unstructured masking
mask = torch.randint(2, size=(
shape[1],
shape[0],
)).float()
lin.mask_(mask)
assert torch.allclose(*torch.broadcast_tensors(lin.mask, mask))
assert torch.allclose(lin.weight_masked, mask * lin.weight)
# mask is overwritten (recreated), so `torch.expand` raises
with pytest.raises(RuntimeError, match=r"must match the existing size"):
lin.mask_(torch.ones(shape[1], 2))
# mask is set anew, so `torch.expand` raises
lin.mask_(None)
with pytest.raises(RuntimeError, match=r"must match the existing size"):
lin.mask_(torch.ones(0, shape[0]))
def forward(self, x):
feature = self.layer(x).view(-1, self.numkernel, self.dimsize)
feature = feature.unsqueeze(3)
feature_ = feature.permute(3, 1, 2, 0)
feature, feature_ = torch.broadcast_tensors(feature, feature_)
norm = torch.sum(torch.abs(feature - feature_), dim=2)
eraser = torch.eye(feature.shape[0], device=torch.device('cuda')).view(
feature.shape[0], 1, feature.shape[0])
eraser, norm = torch.broadcast_tensors(eraser, norm)
c_b = torch.exp(-(norm + eraser * 1e6))
o_b = torch.sum(c_b, dim=2)
x = torch.cat((x, o_b), dim=1)
return x
def tridiagonal_solve(b, A_upper, A_diagonal, A_lower):
"""Solves a tridiagonal system Ax = b.
The arguments A_upper, A_digonal, A_lower correspond to the three diagonals of A. Letting U = A_upper, D=A_digonal
and L = A_lower, and assuming for simplicity that there are no batch dimensions, then the matrix A is assumed to be
of size (k, k), with entries:
D[0] U[0]
L[0] D[1] U[1]
L[1] D[2] U[2] 0
L[2] D[3] U[3]
. . .
. . .
. . .
L[k - 3] D[k - 2] U[k - 2]
0 L[k - 2] D[k - 1] U[k - 1]
L[k - 1] D[k]
Arguments:
b: A tensor of shape (..., k), where '...' is zero or more batch dimensions
A_upper: A tensor of shape (..., k - 1).
A_diagonal: A tensor of shape (..., k).
A_lower: A tensor of shape (..., k - 1).
Returns:
A tensor of shape (..., k), corresponding to the x solving Ax = b
Warning:
This implementation isn't super fast. You probably want to cache the result, if possible.
"""
# This implementation is very much written for clarity rather than speed.
A_upper, _ = torch.broadcast_tensors(A_upper, b[..., :-1])
A_lower, _ = torch.broadcast_tensors(A_lower, b[..., :-1])
A_diagonal, b = torch.broadcast_tensors(A_diagonal, b)
channels = b.size(-1)
new_b = np.empty(channels, dtype=object)
new_A_diagonal = np.empty(channels, dtype=object)
outs = np.empty(channels, dtype=object)
new_b[0] = b[..., 0]
new_A_diagonal[0] = A_diagonal[..., 0]
for i in range(1, channels):
w = A_lower[..., i - 1] / new_A_diagonal[i - 1]
new_A_diagonal[i] = A_diagonal[..., i] - w * A_upper[..., i - 1]
new_b[i] = b[..., i] - w * new_b[i - 1]
outs[channels - 1] = new_b[channels - 1] / new_A_diagonal[channels - 1]
for i in range(channels - 2, -1, -1):
outs[i] = (new_b[i] -
A_upper[..., i] * outs[i + 1]) / new_A_diagonal[i]
return torch.stack(outs.tolist(), dim=-1)
def __init__(self,
loc,
covariance_matrix=None,
precision_matrix=None,
scale_tril=None,
validate_args=None):
if loc.dim() < 1:
raise ValueError("loc must be at least one-dimensional.")
if (covariance_matrix is not None) + (scale_tril is not None) + (
precision_matrix is not None) != 1:
raise ValueError(
"Exactly one of covariance_matrix or precision_matrix or scale_tril may be specified."
)
loc_ = loc.unsqueeze(-1) # temporarily add dim on right
if scale_tril is not None:
if scale_tril.dim() < 2:
raise ValueError(
"scale_tril matrix must be at least two-dimensional, "
"with optional leading batch dimensions")
self.scale_tril, loc_ = torch.broadcast_tensors(scale_tril, loc_)
elif covariance_matrix is not None:
if covariance_matrix.dim() < 2:
raise ValueError(
"covariance_matrix must be at least two-dimensional, "
"with optional leading batch dimensions")
self.covariance_matrix, loc_ = torch.broadcast_tensors(
covariance_matrix, loc_)
else:
if precision_matrix.dim() < 2:
raise ValueError(
"precision_matrix must be at least two-dimensional, "
"with optional leading batch dimensions")
self.precision_matrix, loc_ = torch.broadcast_tensors(
precision_matrix, loc_)
self.loc = loc_[..., 0] # drop rightmost dim
self.normalizing_constant = torch.nn.Parameter(torch.tensor([1.]))
batch_shape, event_shape = self.loc.shape[:-1], self.loc.shape[-1:]
super(UnnormMVGaussian, self).__init__(batch_shape,
event_shape,
validate_args=validate_args)
if scale_tril is not None:
self._unbroadcasted_scale_tril = scale_tril
else:
if precision_matrix is not None:
self.covariance_matrix = torch.inverse(
precision_matrix).expand_as(loc_)
self._unbroadcasted_scale_tril = torch.cholesky(
self.covariance_matrix)
def __init__(self,
loc,
covariance_matrix=None,
precision_matrix=None,
scale_tril=None,
validate_args=None):
if loc.dim() < 1:
raise ValueError("loc must be at least one-dimensional.")
if (covariance_matrix is not None) + (scale_tril is not None) + (
precision_matrix is not None) != 1:
raise ValueError(
"Exactly one of covariance_matrix or precision_matrix or scale_tril may be specified."
)
loc_ = loc.unsqueeze(-1) # temporarily add dim on right
if scale_tril is not None:
if scale_tril.dim() < 2:
raise ValueError(
"scale_tril matrix must be at least two-dimensional, "
"with optional leading batch dimensions")
self.scale_tril, loc_ = torch.broadcast_tensors(scale_tril, loc_)
elif covariance_matrix is not None:
if covariance_matrix.dim() < 2:
raise ValueError(
"covariance_matrix must be at least two-dimensional, "
"with optional leading batch dimensions")
self.covariance_matrix, loc_ = torch.broadcast_tensors(
covariance_matrix, loc_)
else:
if precision_matrix.dim() < 2:
raise ValueError(
"precision_matrix must be at least two-dimensional, "
"with optional leading batch dimensions")
self.precision_matrix, loc_ = torch.broadcast_tensors(
precision_matrix, loc_)
self.loc = loc_[..., 0] # drop rightmost dim
batch_shape, event_shape = self.loc.shape[:-1], self.loc.shape[-1:]
super(MultivariateNormal, self).__init__(batch_shape,
event_shape,
validate_args=validate_args)
if scale_tril is not None:
self._unbroadcasted_scale_tril = scale_tril
elif covariance_matrix is not None:
#self._unbroadcasted_scale_tril = torch.cholesky(covariance_matrix)
self._unbroadcasted_scale_tril = torch.sqrt(covariance_matrix)
else: # precision_matrix is not None
raise NotImplementedError(
'Only covariance_matrix or scale_tril may be specified')
def generate_binary_triple(size0, size1, device=None):
"""Generate binary triples of given size"""
generator = TTPClient.get().get_generator(device=device)
a = generate_kbit_random_tensor(size0,
generator=generator,
device=device)
b = generate_kbit_random_tensor(size1,
generator=generator,
device=device)
if comm.get().get_rank() == 0:
# Request c from TTP
c = TTPClient.get().ttp_request("binary", device, size0, size1)
else:
size2 = torch.broadcast_tensors(a, b)[0].size()
c = generate_kbit_random_tensor(size2,
generator=generator,
device=device)
# Stack to vectorize scatter function
a = BinarySharedTensor.from_shares(a)
b = BinarySharedTensor.from_shares(b)
c = BinarySharedTensor.from_shares(c)
return a, b, c
def log_prob(self, value):
if self._validate_args:
self._validate_sample(value)
value = value.long().unsqueeze(-1)
value, log_pmf = torch.broadcast_tensors(value, self.logits)
value = value[..., :1]
return log_pmf.gather(-1, value).squeeze(-1)
def forward(self, inputs, caps, mask=None):
B, R, input_dim = inputs.shape # (B, R, in)
C, output_dim = caps.shape[1], self.output_dim #
inputs = inputs[None, :, :, None, :] # (1, B, R, 1, in)
caps = caps[None, :, :, None, :].transpose(0, 2) # (C, B, 1, 1, in)
inputs, caps = torch.broadcast_tensors(inputs,
caps) # (C, B, R, 1, in)
u = torch.cat([inputs, caps], axis=-1) # (C, B, R, 1, 2*in)
u = self.dense_out(u) # (C, B, R, 1, out)
if mask is not None:
float_mask = mask.float()[None, :, :, None,
None] # (B, R) => (1, B, R, 1, 1)
else:
float_mask = 1.
b = torch.zeros(C, B, R, 1, 1).to(inputs.device) # (C, B, R, 1, 1)
for i in range(self.n_iter):
v = b.softmax(dim=0) * float_mask # (C, B, R, 1, 1)
c_hat = (u * v).sum(2, keepdims=True) # (C, B, 1, 1, out)
c = squash(c_hat, dim=-1) # (C, B, 1, 1, out)
b = b + (c * u).sum(-1, keepdims=True) # (C, B, R, 1, 1)
out_c = c[:, :, 0, 0, :].permute(1, 0, 2) # (B, C, out)
out_v = v[:, :, :, 0, 0].permute(1, 2, 0) # (B, R, C)
out_b = b[:, :, :, 0, 0].permute(1, 2, 0) # (B, R, C)
# print(out_v[0, 0])
return out_c, out_v, out_b
def proj_tangent(x, u):
assert x.shape[-2:] == u.shape[-2:], "Wrong shapes"
x, u = torch.broadcast_tensors(x, u)
x_shape = x.shape
x = x.reshape(-1, x_shape[-2], x_shape[-1])
u = u.reshape(-1, x_shape[-2], x_shape[-1])
xt = x.transpose(-1, -2)
batch_size, n = x.shape[0:2]
I = torch.eye(n, dtype=x.dtype, device=x.device)
I = I.expand_as(x)
mu = x * u
A = linalg.block_matrix([[I, x], [xt, I]])
B = A[:, :, 1:]
z1 = mu.sum(dim=-1).unsqueeze(-1)
zt1 = mu.sum(dim=-2).unsqueeze(-1)
b = torch.cat(
[z1, zt1],
dim=1,
)
rhs = B.transpose(1, 2) @ (b - A[:, :, 0:1])
lhs = B.transpose(1, 2) @ B
zeta, _ = torch.solve(rhs, lhs)
alpha = torch.cat(
[torch.ones(batch_size, 1, 1, dtype=x.dtype), zeta[:, 0:n - 1]], dim=1)
beta = zeta[:, n - 1:2 * n - 1]
rgrad = mu - (alpha + beta.transpose(-1, -2)) * x
rgrad = rgrad.reshape(x_shape)
return rgrad
def __init__(self, loc, cov_factor, cov_diag, validate_args=None):
if loc.dim() < 1:
raise ValueError("loc must be at least one-dimensional.")
event_shape = loc.shape[-1:]
if cov_factor.dim() < 2:
raise ValueError("cov_factor must be at least two-dimensional, "
"with optional leading batch dimensions")
if cov_factor.shape[-2:-1] != event_shape:
raise ValueError("cov_factor must be a batch of matrices with shape {} x m"
.format(event_shape[0]))
if cov_diag.shape[-1:] != event_shape:
raise ValueError("cov_diag must be a batch of vectors with shape {}".format(event_shape))
loc_ = loc.unsqueeze(-1)
cov_diag_ = cov_diag.unsqueeze(-1)
try:
loc_, self.cov_factor, cov_diag_ = torch.broadcast_tensors(loc_, cov_factor, cov_diag_)
except RuntimeError:
raise ValueError("Incompatible batch shapes: loc {}, cov_factor {}, cov_diag {}"
.format(loc.shape, cov_factor.shape, cov_diag.shape))
self.loc = loc_[..., 0]
self.cov_diag = cov_diag_[..., 0]
batch_shape = self.loc.shape[:-1]
self._unbroadcasted_cov_factor = cov_factor
self._unbroadcasted_cov_diag = cov_diag
self._capacitance_tril = _batch_capacitance_tril(cov_factor, cov_diag)
super(LowRankMultivariateNormal, self).__init__(batch_shape, event_shape,
validate_args=validate_args)
def forward(self, x):
set_feat = self.small_xf(x)
comb_feat = torch.cat(torch.broadcast_tensors(x, set_feat.unsqueeze(-2)), dim=-1)
heads = self.w(comb_feat).view(comb_feat.size()[:3]+(self.heads, -1))
q = self.q.view((1, 1, 1)+self.q.size())
e_heads = (heads * q).sum(dim=-1)
return F.softmax(e_heads, dim=-2)
def _broadcast_prediction_target(prediction, target):
""" broadcast prediction and target in identical shapes
Args:
prediction (Tensor): prediction
target (Tensor): target
Returns:
prediction and target in the same shape
"""
if not torch.is_tensor(prediction):
prediction = torch.tensor(prediction)
if not torch.is_tensor(target):
target = torch.tensor(target, dtype=prediction.dtype, device=prediction.device)
target = target.to(dtype=prediction.dtype, device=prediction.device)
while len(prediction.shape) < 4:
prediction = prediction[:, None]
while len(target.shape) < 4:
target = target[:, None]
try:
prediction, target = torch.broadcast_tensors(prediction.clone(), target.clone())
except RuntimeError:
raise RuntimeError("failed to broadcast target in the same shape as prediction")
return prediction, target
def broadcast_all(*values):
r"""
Given a list of values (possibly containing numbers), returns a list where each
value is broadcasted based on the following rules:
- `torch.*Tensor` instances are broadcasted as per :ref:`_broadcasting-semantics`.
- numbers.Number instances (scalars) are upcast to tensors having
the same size and type as the first tensor passed to `values`. If all the
values are scalars, then they are upcasted to scalar Tensors.
Args:
values (list of `numbers.Number` or `torch.*Tensor`)
Raises:
ValueError: if any of the values is not a `numbers.Number` or
`torch.*Tensor` instance
"""
if not all(
isinstance(v, torch.Tensor) or isinstance(v, Number)
for v in values):
raise ValueError(
'Input arguments must all be instances of numbers.Number or torch.tensor.'
)
if not all([isinstance(v, torch.Tensor) for v in values]):
options = dict(dtype=torch.get_default_dtype())
for value in values:
if isinstance(value, torch.Tensor):
options = dict(dtype=value.dtype, device=value.device)
break
values = [
v if isinstance(v, torch.Tensor) else torch.tensor(v, **options)
for v in values
]
return torch.broadcast_tensors(*values)
def color_loss(input, target, reduction='mean'):
pixDictionary = buildPixDictionary(target)
print("Len pixDict", len(pixDictionary))
print(pixDictionary)
print(input.size())
batch, channel, height, width = input.size()
ret = torch.empty(batch, channel, height, width)
nbPixelDif = len(pixDictionary)
nbPixel = height * width * batch
if target.requires_grad:
for img in range(batch):
for i in range(height):
for j in range(width):
mse = (input[img, :, i, j] - target[img, :, i, j])**2
nbApparition = pixDictionary[getIndexPix(
input[img, :, i, j].detach())]
color_coef = nbPixel / (nbPixelDif * nbApparition)
ret[img, :, i, j] = mse * color_coef
else:
expanded_input, expanded_target = torch.broadcast_tensors(
input, target)
for i in range(height):
for j in range(width):
mse = (expanded_input[i][j] - expanded_target[i][j])**2
nbApparition = pixDictionary[input[i][j]]
color_coef = nbPixel / (nbPixelDif * nbApparition)
ret[i][j] = mse * color_coef
if reduction != 'none':
ret = torch.mean(ret) if reduction == 'mean' else torch.sum(ret)
def __init__(self, name: str, shape: tc.Size, device=None, **params):
# for distributions whose parameter and random variable (or, one sample) have the same shape
if device is None: device = Distr.default_device
fnnames, fnvals, tennames, tenvals = [], [], [], []
for pmname, pmval in params.items():
if callable(pmval):
fnnames.append(pmname)
fnvals.append(pmval)
else:
tennames.append(pmname)
tenvals.append(pmval)
tenvals = tensorify(device, *tenvals)
if shape is None:
if Distr.has_name(name): shape = Distr.shape_var(name)
elif tenvals: shape = tc.broadcast_tensors(*tenvals)[0].shape
else: shape = tc.Size()
parents = set()
for fname, fval in zip(fnnames, fnvals):
parents_inc = fargnames(fval)
if parents_inc:
parents |= parents_inc
setattr(self, fname, fedic(fval))
else:
setattr(self,
fname,
lambda conds, fval=fval: tensorify(device, fval())[0].
expand(Distr.shape_bat(conds) + shape))
for tname, tval in zip(tennames, tenvals):
setattr(self,
tname,
lambda conds, tval=tval: tval.expand(
Distr.shape_bat(conds) + shape))
super(DistrElem, self).__init__(names_shapes={name: shape},
parents=parents)
self._name, self._shape, self._device = name, shape, device
def broadcast_all(*values):
r"""
Given a list of values (possibly containing numbers), returns a list where each
value is broadcasted based on the following rules:
- `torch.*Tensor` instances are broadcasted as per :ref:`_broadcasting-semantics`.
- numbers.Number instances (scalars) are upcast to tensors having
the same size and type as the first tensor passed to `values`. If all the
values are scalars, then they are upcasted to scalar Tensors.
Args:
values (list of `numbers.Number` or `torch.*Tensor`)
Raises:
ValueError: if any of the values is not a `numbers.Number` or
`torch.*Tensor` instance
"""
if not all(torch.is_tensor(v) or isinstance(v, Number) for v in values):
raise ValueError(
'Input arguments must all be instances of numbers.Number or torch.tensor.'
)
if not all(map(torch.is_tensor, values)):
new_tensor = _default_promotion
for value in values:
if torch.is_tensor(value):
new_tensor = value.new_tensor
break
values = [v if torch.is_tensor(v) else new_tensor(v) for v in values]
return torch.broadcast_tensors(*values)
def __init__(self,
loc,
scale=None,
link="probit",
sampling=5000,
validate_args=None):
if loc.dim() < 1:
raise ValueError("loc must be at least one-dimensional.")
loc_ = loc.unsqueeze(-1) # temporarily add dim on right
if scale.dim() < 2:
raise ValueError("scale must be at least two-dimensional, "
"with optional leading batch dimensions")
self.scale, loc_ = torch.broadcast_tensors(scale, loc_)
self.scale = scale
self._covariance_matrix = scale
self.loc = loc_[..., 0] # drop rightmost dim
self.df = scale.shape[-1]
self.sampling = sampling
self.alpha = 1.0
if link == "logit":
self.link = lambda value: torch.sigmoid(value)
self.alpha = 1.7012
elif link == "probit":
self.link = lambda value: torch.distributions.Normal(0.0, 1.0).cdf(
value)
elif link == "linear":
self.link = lambda value: torch.clamp(value, 0.0, 1.0)
batch_shape, event_shape = self.loc.shape[:-1], self.loc.shape[-1:]
super(MultivariateProbit, self).__init__(batch_shape,
event_shape,
validate_args=validate_args)
def pairwise_soft_dtw(data1, data2, sdtw=None, device=torch.device('cpu')):
if sdtw is None:
raise ValueError('sdtw is None - initialize it with SoftDTW')
# transfer to device
data1, data2 = data1.to(device), data2.to(device)
# (batch_size, seq_len, feature_dim=1)
A = data1.unsqueeze(dim=2)
# (cluster_size, seq_len, feature_dim=1)
B = data2.unsqueeze(dim=2)
distances = []
for b in B:
# (1, seq_len, 1)
b = b.unsqueeze(dim=0)
A, b = torch.broadcast_tensors(A, b)
# (batch_size, 1)
sdtw_distance = sdtw(b, A).view(-1, 1)
distances.append(sdtw_distance)
# (batch_size, cluster_size)
dis = torch.cat(distances, dim=1)
return dis
def forward(self, predicted_mesh):
predicted_mesh_verts = predicted_mesh.vertices
predicted_mesh_indices = predicted_mesh.indices
lap = laplacian(predicted_mesh_verts, predicted_mesh_indices)
# just measure squared distance from smooth version
avg_edge_l = average_edge_length_by_vertex(predicted_mesh_verts,
predicted_mesh_indices)
avg_edge_l, _ = torch.broadcast_tensors(avg_edge_l.unsqueeze(1), lap)
if self.edge_length_scale is not None:
loss_per_vertex = (predicted_mesh_verts -
lap) * self.edge_length_scale / avg_edge_l
else:
loss_per_vertex = predicted_mesh_verts - lap
if self.scale_by_orig_smoothness:
if self.orig is None:
# Add a little bit so that nothing's / 0
self.orig = loss_per_vertex.clone().detach() + 0.01
# Scale by orig. If the orig loss for a given vertex was HIGH,
# it's not so bad (divide)
# if the orig loss for a given vertex was LOW, then it is bad!
loss_per_vertex = loss_per_vertex - self.orig
sqrt_error = torch.sqrt(
torch.sum(loss_per_vertex * loss_per_vertex, dim=1))
mean_error = torch.mean(sqrt_error)
return mean_error
def test(args, model, device, test_loader, epoch, writer):
model.eval()
test_loss = 0
correct = 0
isEval = False
with torch.no_grad():
for data, target in test_loader:
data, target = data.to(device), target.to(device)
data, _ = torch.broadcast_tensors(
data, torch.zeros((steps, ) + data.shape))
data = data.permute(1, 2, 3, 4, 0)
output = model(data)
test_loss += F.cross_entropy(
output, target, reduction='sum').item() # sum up batch loss
pred = output.argmax(
dim=1,
keepdim=True) # get the index of the max log-probability
correct += pred.eq(target.view_as(pred)).sum().item()
test_loss /= len(test_loader.dataset)
writer.add_scalar('Test Loss /epoch', test_loss, epoch)
writer.add_scalar('Test Acc /epoch',
100. * correct / len(test_loader.dataset), epoch)
for i, (name, param) in enumerate(model.named_parameters()):
if '_s' in name:
writer.add_histogram(name, param, epoch)
print(
'\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
def broadcast_except(*tensors: torch.Tensor, dim=-1):
shape = torch.broadcast_tensors(*[t.select(dim, 0)
for t in tensors])[0].shape
return [
t.expand(*shape[:t.ndim + dim + 1], t.shape[dim],
*shape[t.ndim + dim + 1:]) for t in tensors
]
def broadcast_and_squeeze(*args):
assert all([is_tensor(ar) for ar in args]), 'at least 1 object is not torch tensor'
if all([np.prod(val.shape[2:]) == 1 for val in args]):
args = [val.contiguous().view(size=val.shape[:2] + tuple([1, 1])) for val in args]
uniformed_values = uniform_shapes(*args)
broadcasted_values = torch.broadcast_tensors(*uniformed_values)
return broadcasted_values
def _feature_dropout(self, p=0.5, training=True, inplace=False):
"""Randomly zeros out entire channels in the input tensor with probability
:attr:`p`. (a channel is a nD feature map, e.g., the :math:`j`-th channel
of the :math:`i`-th sample in the batched input is a nD tensor
:math:`\text{input}[i, j]`)."""
assert self.dim(
) >= 2, "feature dropout requires dimension to be at least 2"
assert p >= 0.0 and p <= 1.0, "dropout probability has to be between 0 and 1"
if training is False:
if inplace:
return self
else:
return self.clone()
# take first 2 dimensions
feature_dropout_size = self.size()[0:2]
# create dropout tensor over the first two dimensions
rand_tensor = crypten.mpc.rand(feature_dropout_size)
feature_dropout_tensor = rand_tensor > p
# Broadcast to remaining dimensions
for i in range(2, self.dim()):
feature_dropout_tensor = feature_dropout_tensor.unsqueeze(i)
feature_dropout_tensor.share, self.share = torch.broadcast_tensors(
feature_dropout_tensor.share, self.share)
if inplace:
result_tensor = self.mul_(feature_dropout_tensor).div_(1 - p)
else:
result_tensor = self.mul(feature_dropout_tensor).div_(1 - p)
return result_tensor
def loss(self, item, pred):
actual = item['pos'].unsqueeze(-2)
mask = item['mask'].unsqueeze(-1)
pred, actual = torch.broadcast_tensors(pred, actual)
loss = F.mse_loss(pred, actual, reduction='none').sum(-1)
loss *= mask
return loss.mean()
def _grid_offsets(H, W, dtype, device):
"""
Returns the grid offsets HxWx2 within [-1,1]
"""
if (H, W) in VideoTools._offset_cache:
return VideoTools._offset_cache[(H, W)]
else:
print("Create grid offsets for warping: W=%d, H=%d" % (W, H))
grid_offsetsH = torch.linspace(-1,
+1,
H,
dtype=dtype,
device=device)
grid_offsetsW = torch.linspace(-1,
+1,
W,
dtype=dtype,
device=device)
grid_offsetsH = torch.unsqueeze(grid_offsetsH, 1)
grid_offsetsW = torch.unsqueeze(grid_offsetsW, 0)
grid_offsets = torch.stack(torch.broadcast_tensors(
grid_offsetsW, grid_offsetsH),
dim=2)
grid_offsets = torch.unsqueeze(grid_offsets, 0) # batch dimension
grid_offsets = grid_offsets.detach()
VideoTools._offset_cache[(H, W)] = grid_offsets
return grid_offsets
def __init__(self, loc, precision_diag, belief, df, validate_args=True):
precision_diag, belief, df = self.convert_float_params_to_tensor(
loc, precision_diag, belief, df)
if loc.dim() < 1 or precision_diag.dim() < 1 or df.dim(
) < 1 or belief.dim() < 1:
raise ValueError(
"loc, precision_diag, df, belief must be at least one-dimensional."
)
if belief.size(-1) == 1 and precision_diag.size(-1) != 1:
raise ValueError(
"belief shouldn't end with dimensionality 1 if precision_diag doesn't"
)
if df.size(-1) == 1 and precision_diag.size(-1) != 1:
raise ValueError(
"df shouldn't end with dimensionality 1 if precision_diag doesn't"
)
df_, belief_ = df.unsqueeze(-1), belief.unsqueeze(
-1) # add dim on right
self.loc, self.precision_diag, df_, belief_ = torch.broadcast_tensors(
loc, precision_diag, df_, belief_)
self.df, self.belief = df_[..., 0], belief_[...,
0] # drop rightmost dim
batch_shape, event_shape = self.loc.shape[:-1], self.loc.shape[-1:]
self.dimensionality = event_shape.numel()
if (self.df <= (self.dimensionality + 1)).any():
raise ValueError(
"df must be greater than dimensionality + 1 to have expectation"
)
super(NormalDiagonalWishart,
self).__init__(batch_shape,
event_shape,
validate_args=validate_args)
