def backward(self, top, propagate_down, bottom):
with pu.caffe_cuda_context():
h = caffe.cublas_handle()
import scikits.cuda.linalg as linalg
top_diff = top[0].diff_as_pycuda_gpuarray()
ts = [self.t1_, self.t2_]
for i in xrange(len(bottom)):
if not propagate_down[i]:
continue
diff = bottom[i].diff_as_pycuda_gpuarray()
data = bottom[(i + 1) % 2].data_as_pycuda_gpuarray()
# Belew 3 conditions are complicated and might be hard to
# understand.
swap = ts[i] ^ bool(i)
t1 = ts[i]
t2 = (not t1) ^ ts[(i + 1) % 2]
for b in xrange(bottom[0].shape[0]):
x = top_diff[b]
y = data[b]
t1_, t2_ = t1, t2
if swap:
x, y = y, x
t1_, t2_ = t2_, t1_
linalg.dot(x,
y,
transa=blas_trans(t1_),
transb=blas_trans(t2_),
handle=h,
out=diff[b])
def forward(self, bottom, top):
"""
"""
with pu.caffe_cuda_context():
h = caffe.cublas_handle()
batch_size = bottom[0].shape[0]
dim = bottom[0].count / bottom[0].shape[0]
pred = bottom[0].data_as_pycuda_gpuarray()
label = bottom[1].data_as_pycuda_gpuarray()
mask = bottom[2].data_as_pycuda_gpuarray()
# Use bottom[0,1].diff as temporary buffer
diff = bottom[0].diff_as_pycuda_gpuarray()
diff2 = bottom[1].diff_as_pycuda_gpuarray()
# Compute diff
self.k_masked_diff_(diff, pred, label, mask)
self.k_squared_(diff, diff2)
import scikits.cuda.linalg as linalg
# This needs scikits.cuda 0.5.0a3 or later
# (sudo) pip install scikits.cuda=>0.5.0a3
linalg.dot(diff.reshape(batch_size, dim), self.multipier_sum_,
handle=h, out=self.diff_sum_)
linalg.dot(diff2.reshape(batch_size, dim), self.multipier_sum_,
handle=h, out=self.diff2_sum_)
linalg.dot(mask.reshape(batch_size, dim), self.multipier_sum_,
handle=h, out=self.mask_sum_)
self.k_ensure_mask_sum_(self.mask_sum_)
term1 = self.k_div_sum_(self.diff2_sum_, self.mask_sum_)
term2 = self.k_div_squared_sum_(self.diff_sum_, self.mask_sum_)
top[0].data[...] = (term1.get() - self.lambda_ * term2.get()) \
/ batch_size
def backward(self, top, propagate_down, bottom):
with pu.caffe_cuda_context():
h = caffe.cublas_handle()
import scikits.cuda.linalg as linalg
top_diff = top[0].diff_as_pycuda_gpuarray()
ts = [self.t1_, self.t2_]
for i in xrange(len(bottom)):
if not propagate_down[i]:
continue
diff = bottom[i].diff_as_pycuda_gpuarray()
data = bottom[(i + 1) % 2].data_as_pycuda_gpuarray()
# Belew 3 conditions are complicated and might be hard to
# understand.
swap = ts[i] ^ bool(i)
t1 = ts[i]
t2 = (not t1) ^ ts[(i + 1) % 2]
for b in xrange(bottom[0].shape[0]):
x = top_diff[b]
y = data[b]
t1_, t2_ = t1, t2
if swap:
x, y = y, x
t1_, t2_ = t2_, t1_
linalg.dot(x, y,
transa=blas_trans(t1_), transb=blas_trans(t2_),
handle=h, out=diff[b])
def forward(self, bottom, top):
with pu.caffe_cuda_context():
h = caffe.cublas_handle()
import scikits.cuda.linalg as linalg
mat1 = bottom[0].data_as_pycuda_gpuarray()
mat2 = bottom[1].data_as_pycuda_gpuarray()
mato = top[0].data_as_pycuda_gpuarray()
for b in xrange(bottom[0].shape[0]):
linalg.dot(mat1[b], mat2[b],
transa=blas_trans(self.t1_),
transb=blas_trans(self.t2_),
handle=h, out=mato[b])
def forward(self, bottom, top):
with pu.caffe_cuda_context():
h = caffe.cublas_handle()
import scikits.cuda.linalg as linalg
mat1 = bottom[0].data_as_pycuda_gpuarray()
mat2 = bottom[1].data_as_pycuda_gpuarray()
mato = top[0].data_as_pycuda_gpuarray()
for b in xrange(bottom[0].shape[0]):
linalg.dot(mat1[b],
mat2[b],
transa=blas_trans(self.t1_),
transb=blas_trans(self.t2_),
handle=h,
out=mato[b])
def forward(self, bottom, top):
"""
"""
with pu.caffe_cuda_context():
h = caffe.cublas_handle()
batch_size = bottom[0].shape[0]
dim = bottom[0].count / bottom[0].shape[0]
pred = bottom[0].data_as_pycuda_gpuarray()
label = bottom[1].data_as_pycuda_gpuarray()
# Use bottom[0,1].diff as temporary buffer
diff = bottom[0].diff_as_pycuda_gpuarray()
diff2 = bottom[1].diff_as_pycuda_gpuarray()
mask = bottom[0].diff_as_pycuda_gpuarray()
# Compute diff
self.k_masked_diff_(diff, pred, label)
self.k_squared_(diff, diff2)
import scikits.cuda.linalg as linalg
# This needs scikits.cuda 0.5.0a3 or later
# (sudo) pip install scikits.cuda=>0.5.0a3
linalg.dot(diff.reshape(batch_size, dim),
self.multipier_sum_,
handle=h,
out=self.diff_sum_)
linalg.dot(diff2.reshape(batch_size, dim),
self.multipier_sum_,
handle=h,
out=self.diff2_sum_)
mask.fill(dtype(1.0))
linalg.dot(mask.reshape(batch_size, dim),
self.multipier_sum_,
handle=h,
out=self.mask_sum_)
self.k_ensure_mask_sum_(self.mask_sum_)
term1 = self.k_div_sum_(self.diff2_sum_, self.mask_sum_)
term2 = self.k_div_squared_sum_(self.diff_sum_, self.mask_sum_)
top[0].data[...] = (term1.get() - self.lambda_ * term2.get()) \
/ batch_size