def test_blocksparse_gpu_gemv_opt():
b = tensor.fmatrix()
W = tensor.ftensor4()
h = tensor.ftensor3()
iIdx = tensor.lmatrix()
oIdx = tensor.lmatrix()
o = sparse_block_dot(W, h, iIdx, b, oIdx)
f = theano.function([W, h, iIdx, b, oIdx], o, mode=mode_with_gpu)
assert isinstance(f.maker.fgraph.toposort()[-2].op, GpuSparseBlockGemv)
def test_blocksparse_gpu_gemv_opt():
b = tensor.fmatrix()
W = tensor.ftensor4()
h = tensor.ftensor3()
iIdx = tensor.lmatrix()
oIdx = tensor.lmatrix()
o = sparse_block_dot(W, h, iIdx, b, oIdx)
f = theano.function([W, h, iIdx, b, oIdx], o, mode=mode_with_gpu)
assert isinstance(f.maker.fgraph.toposort()[-2].op, GpuSparseBlockGemv)
def test_blocksparse_gpu_outer_opt():
b = tensor.fmatrix()
W = tensor.ftensor4()
h = tensor.ftensor3()
iIdx = tensor.lmatrix()
oIdx = tensor.lmatrix()
o = sparse_block_dot(W, h, iIdx, b, oIdx)
f = theano.function([W, h, iIdx, b, oIdx],
[o, tensor.grad(o.sum(), wrt=W)],
mode=mode_with_gpu)
assert isinstance(f.maker.fgraph.toposort()[-2].op, GpuSparseBlockOuter)
def test_blocksparse_gpu_outer_opt():
b = tensor.fmatrix()
W = tensor.ftensor4()
h = tensor.ftensor3()
iIdx = tensor.lmatrix()
oIdx = tensor.lmatrix()
o = sparse_block_dot(W, h, iIdx, b, oIdx)
f = theano.function([W, h, iIdx, b, oIdx], [o, tensor.grad(o.sum(),
wrt=W)],
mode=mode_with_gpu)
assert isinstance(f.maker.fgraph.toposort()[-2].op, GpuSparseBlockOuter)
def test_blocksparse_inplace_gemv_opt():
b = tensor.fmatrix()
W = tensor.ftensor4()
h = tensor.ftensor3()
iIdx = tensor.lmatrix()
oIdx = tensor.lmatrix()
o = sparse_block_dot(W, h, iIdx, b, oIdx)
f = theano.function([W, h, iIdx, b, oIdx], o)
if theano.config.mode == "FAST_COMPILE":
assert not f.maker.fgraph.toposort()[-1].op.inplace
else:
assert f.maker.fgraph.toposort()[-1].op.inplace
def test_blocksparse_inplace_outer_opt():
b = tensor.fmatrix()
W = tensor.ftensor4()
h = tensor.ftensor3()
iIdx = tensor.lmatrix()
oIdx = tensor.lmatrix()
o = sparse_block_dot(W, h, iIdx, b, oIdx)
theano.printing.debugprint(tensor.grad(o.sum(), wrt=W))
f = theano.function([W, h, iIdx, b, oIdx],
[o, tensor.grad(o.sum(), wrt=W)])
if theano.config.mode == "FAST_COMPILE":
assert not f.maker.fgraph.toposort()[-1].op.inplace
else:
assert f.maker.fgraph.toposort()[-1].op.inplace
def test_sparseblockdot(self):
"""
Compares the numpy version of sparseblockgemv to sparse_block_dot.
"""
b = tensor.fmatrix()
W = tensor.ftensor4()
h = tensor.ftensor3()
iIdx = tensor.imatrix()
oIdx = tensor.imatrix()
o = sparse_block_dot(W, h, iIdx, b, oIdx)
f = theano.function([W, h, iIdx, b, oIdx], o, mode=self.mode)
W_val, h_val, iIdx_val, b_val, oIdx_val = BlockSparse_Gemv_and_Outer.gemv_data()
th_out = f(W_val, h_val, iIdx_val, b_val, oIdx_val)
ref_out = BlockSparse_Gemv_and_Outer.gemv_numpy(b_val.take(oIdx_val, axis=0), W_val, h_val, iIdx_val, oIdx_val)
utt.assert_allclose(ref_out, th_out)
def test_sparseblockdot(self):
"""
Compares the numpy version of sparseblockgemv to sparse_block_dot.
"""
b = tensor.fmatrix()
W = tensor.ftensor4()
h = tensor.ftensor3()
iIdx = tensor.imatrix()
oIdx = tensor.imatrix()
o = sparse_block_dot(W, h, iIdx, b, oIdx)
f = theano.function([W, h, iIdx, b, oIdx], o, mode=self.mode)
W_val, h_val, iIdx_val, b_val, oIdx_val = \
BlockSparse_Gemv_and_Outer.gemv_data()
th_out = f(W_val, h_val, iIdx_val, b_val, oIdx_val)
ref_out = BlockSparse_Gemv_and_Outer.gemv_numpy(
b_val.take(oIdx_val, axis=0), W_val, h_val, iIdx_val, oIdx_val)
utt.assert_allclose(ref_out, th_out)
def metaop(b, h, W):
return sparse_block_dot(W, h, iIdx, b, oIdx)
def metaop(b, h, W):
return sparse_block_dot(W, h, iIdx, b, oIdx)
