def test_conv_zeros(backend_default, zeros_convargs, deltas_buffer):
fshape, nofm, batch_size = zeros_convargs
NervanaObject.be.bsz = batch_size
# basic sanity check with 0 weights random inputs
init_unif = Uniform(low=0.0, high=0.0)
inshape = (32, 32, 32)
insize = np.prod(inshape)
neon_layer = Convolution(fshape=(fshape, fshape, nofm),
strides=1, padding=0, init=init_unif)
inp = neon_layer.be.array(np.random.random((insize, batch_size)))
inp.lshape = inshape
neon_layer.configure(inshape)
neon_layer.prev_layer = True
neon_layer.allocate()
neon_layer.allocate_deltas(deltas_buffer)
deltas_buffer.allocate_buffers()
neon_layer.set_deltas(deltas_buffer)
out = neon_layer.fprop(inp).get()
assert np.min(out) == 0.0 and np.max(out) == 0.0
err = np.zeros(out.shape)
deltas = neon_layer.bprop(neon_layer.be.array(err)).get()
assert np.min(deltas) == 0.0 and np.max(deltas) == 0.0
dw = neon_layer.dW.get()
assert np.min(dw) == 0.0 and np.max(dw) == 0.0
return
def test_conv_zeros(backend_default, zeros_convargs, deltas_buffer):
fshape, nofm, batch_size = zeros_convargs
NervanaObject.be.bsz = batch_size
# basic sanity check with 0 weights random inputs
init_unif = Uniform(low=0.0, high=0.0)
inshape = (32, 32, 32)
insize = np.prod(inshape)
neon_layer = Convolution(fshape=(fshape, fshape, nofm),
strides=1, padding=0, init=init_unif)
inp = neon_layer.be.array(np.random.random((insize, batch_size)))
inp.lshape = inshape
neon_layer.configure(inshape)
neon_layer.prev_layer = True
neon_layer.allocate()
neon_layer.allocate_deltas(deltas_buffer)
deltas_buffer.allocate_buffers()
neon_layer.set_deltas(deltas_buffer)
out = neon_layer.fprop(inp).get()
assert np.min(out) == 0.0 and np.max(out) == 0.0
err = np.zeros(out.shape)
deltas = neon_layer.bprop(neon_layer.be.array(err)).get()
assert np.min(deltas) == 0.0 and np.max(deltas) == 0.0
dw = neon_layer.dW.get()
assert np.min(dw) == 0.0 and np.max(dw) == 0.0
return
def test_conv_rand(backend_default, rand_convargs, deltas_buffer):
indim, nifm, fshape, nofm, batch_size, stride, rng_max, w_rng, pad = rand_convargs
if isinstance(NervanaObject.be, NervanaGPU) and NervanaObject.be.compute_capability < (5, 0):
if nifm % 4 != 0:
pytest.skip(msg="C dim must be a multiple of 4 for Kepler bprop kernel")
NervanaObject.be.bsz = batch_size
inp_rng = [0.0, rng_max]
dtypeu = np.float32
init_unif = Uniform(low=w_rng[0], high=w_rng[1])
inshape = (nifm, indim, indim)
insize = np.prod(inshape)
# generate neon conv layer
neon_layer = Convolution(fshape=(fshape, fshape, nofm),
strides=stride, padding=pad, init=init_unif)
# generate the reference layer
ref_layer = ConvLayerRef(1,
batch_size,
identity,
inshape[0],
inshape[1:3],
(fshape, fshape),
nofm,
stride,
dtypeu,
padding=pad)
# setup input in range inp_rng
inpa = np.random.random((insize, batch_size))
inpa *= inp_rng[1] - inp_rng[0]
inpa += inp_rng[0]
inpa = inpa.astype(dtypeu)
inp = neon_layer.be.array(inpa)
inp.lshape = inshape
# run fprop on neon
neon_layer.configure(inshape)
neon_layer.prev_layer = True
neon_layer.allocate()
neon_layer.allocate_deltas(deltas_buffer)
deltas_buffer.allocate_buffers()
neon_layer.set_deltas(deltas_buffer)
neon_out = neon_layer.fprop(inp).get()
# pull neon weights into ref layer weights
ref_layer.weights = neon_layer.W.get().T
ref_layer.fprop(inpa.T)
ref_out = np.copy(ref_layer.y)
# estimate the numerical precision by
# permuting order of ops in ref layer
# fprop calculation
ref_layer.fprop(inpa.T, permute=True)
ref_out_perm = ref_layer.y
atol = 4 * np.max(np.abs(ref_out - ref_out_perm))
# compare ref and neon layer fprop outputs
# using the empirically determined atol
assert allclose_with_out(ref_out.T, neon_out, atol=atol, rtol=1.e-4)
# generate random deltas array
erra = np.random.random(neon_out.shape)
erra *= (inp_rng[1] - inp_rng[0])
erra += inp_rng[0]
erra = erra.astype(dtypeu)
err = neon_layer.be.array(erra)
# run neon bprop
neon_deltas = neon_layer.bprop(err).get()
neon_dW = neon_layer.dW.get()
# run ref code bprop
ref_layer.bprop(erra.T, 1.0)
ref_deltas = np.copy(ref_layer.berror_nopad.T)
ref_dW = np.copy(ref_layer.updates)
# estimate precision using permutation
# of operation order on ref layer code
ref_layer.bprop(erra.T, 1.0, permute=True)
ref_deltas_perm = ref_layer.berror_nopad.T
ref_dW_perm = ref_layer.updates
atol = 4 * np.max(np.abs(ref_deltas - ref_deltas_perm))
assert allclose_with_out(ref_deltas, neon_deltas, atol=atol, rtol=1.e-4)
atol = 4 * np.max(np.abs(ref_dW - ref_dW_perm))
assert allclose_with_out(ref_dW.T, neon_dW, atol=atol, rtol=1.e-4)
return
def test_conv_ones(backend_default, ones_convargs, deltas_buffer):
dtypeu = np.float32
indim, nifm, fshape, nofm, batch_size, stride, pad = ones_convargs
if isinstance(NervanaObject.be, NervanaGPU) and NervanaObject.be.compute_capability < (5, 0):
if nifm % 4 != 0:
pytest.skip(msg="C dim must be a multiple of 4 for Kepler bprop kernel")
NervanaObject.be.bsz = batch_size
# weights set to one
init_unif = Uniform(low=1.0, high=1.0)
inshape = (nifm, indim, indim)
insize = np.prod(inshape)
neon_layer = Convolution(fshape=(fshape, fshape, nofm),
strides=stride, padding=pad, init=init_unif)
inp = neon_layer.be.array(np.ones((insize, batch_size)))
inp.lshape = inshape
neon_layer.configure(inshape)
neon_layer.prev_layer = True
neon_layer.allocate()
neon_layer.allocate_deltas(deltas_buffer)
deltas_buffer.allocate_buffers()
neon_layer.set_deltas(deltas_buffer)
# run fprop
out = neon_layer.fprop(inp).get()
# generate the reference layer
ref_layer = ConvLayerRef(1,
batch_size,
identity,
inshape[0],
inshape[1:3],
(fshape, fshape),
nofm,
stride,
dtypeu,
padding=pad)
# init weights to ones
ref_layer.weights = np.ones(neon_layer.W.shape).T.astype(dtypeu)
ref_layer.fprop(inp.get().T)
out_exp = ref_layer.y.copy()
assert allclose_with_out(out_exp.T, out, atol=0.0, rtol=0.0)
# generate err array
err = np.ones(out.shape).astype(np.float32)
# run bprop
neon_layer.bprop(neon_layer.be.array(err))
dw = neon_layer.dW.get()
# run bprop
ref_layer.bprop(err.T.astype(dtypeu), 1.0)
# expected output for updates is uniform matrix with
# all elements == ofmsize*batch_size
updates_exp = ref_layer.updates.T
# check dw from neon layer
assert allclose_with_out(dw, updates_exp, atol=0.0, rtol=0.0)
# the deltas are more complicated since the matricies are not
# uniform, going to use the reference code directly here
# no tolerance here should be exact
dd = np.abs(ref_layer.berror_nopad.T - neon_layer.deltas.get())
try:
assert np.max(dd) == 0.0
except AssertionError:
if ones_convargs in ((32, 32, 3, 32, 64, 2, 0),
(32, 32, 3, 16, 64, 2, 0),
(32, 32, 3, 64, 64, 2, 0)):
pytest.xfail(reason="xfail before mkl update. issue: #1020")
else:
assert np.max(dd) == 0.0
return
def test_conv_rand(backend_default, rand_convargs, deltas_buffer):
indim, nifm, fshape, nofm, batch_size, stride, rng_max, w_rng, pad = rand_convargs
if isinstance(NervanaObject.be, NervanaGPU) and NervanaObject.be.compute_capability < (5, 0):
if nifm % 4 != 0:
pytest.skip(msg="C dim must be a multiple of 4 for Kepler bprop kernel")
NervanaObject.be.bsz = batch_size
inp_rng = [0.0, rng_max]
dtypeu = np.float32
init_unif = Uniform(low=w_rng[0], high=w_rng[1])
inshape = (nifm, indim, indim)
insize = np.prod(inshape)
# generate neon conv layer
neon_layer = Convolution(fshape=(fshape, fshape, nofm),
strides=stride, padding=pad, init=init_unif)
# generate the reference layer
ref_layer = ConvLayerRef(1,
batch_size,
identity,
inshape[0],
inshape[1:3],
(fshape, fshape),
nofm,
stride,
dtypeu,
padding=pad)
# setup input in range inp_rng
inpa = np.random.random((insize, batch_size))
inpa *= inp_rng[1] - inp_rng[0]
inpa += inp_rng[0]
inpa = inpa.astype(dtypeu)
inp = neon_layer.be.array(inpa)
inp.lshape = inshape
# run fprop on neon
neon_layer.configure(inshape)
neon_layer.prev_layer = True
neon_layer.allocate()
neon_layer.allocate_deltas(deltas_buffer)
deltas_buffer.allocate_buffers()
neon_layer.set_deltas(deltas_buffer)
neon_out = neon_layer.fprop(inp).get()
# pull neon weights into ref layer weights
ref_layer.weights = neon_layer.W.get().T
ref_layer.fprop(inpa.T)
ref_out = np.copy(ref_layer.y)
# estimate the numerical precision by
# permuting order of ops in ref layer
# fprop calculation
ref_layer.fprop(inpa.T, permute=True)
ref_out_perm = ref_layer.y
atol = 4 * np.max(np.abs(ref_out - ref_out_perm))
# compare ref and neon layer fprop outputs
# using the empirically determined atol
assert allclose_with_out(ref_out.T, neon_out, atol=atol, rtol=1.e-4)
# generate random deltas array
erra = np.random.random(neon_out.shape)
erra *= (inp_rng[1] - inp_rng[0])
erra += inp_rng[0]
erra = erra.astype(dtypeu)
err = neon_layer.be.array(erra)
# run neon bprop
neon_deltas = neon_layer.bprop(err).get()
neon_dW = neon_layer.dW.get()
# run ref code bprop
ref_layer.bprop(erra.T, 1.0)
ref_deltas = np.copy(ref_layer.berror_nopad.T)
ref_dW = np.copy(ref_layer.updates)
# estimate precision using permutation
# of operation order on ref layer code
ref_layer.bprop(erra.T, 1.0, permute=True)
ref_deltas_perm = ref_layer.berror_nopad.T
ref_dW_perm = ref_layer.updates
atol = 4 * np.max(np.abs(ref_deltas - ref_deltas_perm))
assert allclose_with_out(ref_deltas, neon_deltas, atol=atol, rtol=1.e-4)
atol = 4 * np.max(np.abs(ref_dW - ref_dW_perm))
assert allclose_with_out(ref_dW.T, neon_dW, atol=atol, rtol=1.e-4)
return
def test_conv_ones(backend_default, ones_convargs, deltas_buffer):
dtypeu = np.float32
indim, nifm, fshape, nofm, batch_size, stride, pad = ones_convargs
if isinstance(NervanaObject.be, NervanaGPU) and NervanaObject.be.compute_capability < (5, 0):
if nifm % 4 != 0:
pytest.skip(msg="C dim must be a multiple of 4 for Kepler bprop kernel")
NervanaObject.be.bsz = batch_size
# weights set to one
init_unif = Uniform(low=1.0, high=1.0)
inshape = (nifm, indim, indim)
insize = np.prod(inshape)
neon_layer = Convolution(fshape=(fshape, fshape, nofm),
strides=stride, padding=pad, init=init_unif)
inp = neon_layer.be.array(np.ones((insize, batch_size)))
inp.lshape = inshape
neon_layer.configure(inshape)
neon_layer.prev_layer = True
neon_layer.allocate()
neon_layer.allocate_deltas(deltas_buffer)
deltas_buffer.allocate_buffers()
neon_layer.set_deltas(deltas_buffer)
# run fprop
out = neon_layer.fprop(inp).get()
# generate the reference layer
ref_layer = ConvLayerRef(1,
batch_size,
identity,
inshape[0],
inshape[1:3],
(fshape, fshape),
nofm,
stride,
dtypeu,
padding=pad)
# init weights to ones
ref_layer.weights = np.ones(neon_layer.W.shape).T.astype(dtypeu)
ref_layer.fprop(inp.get().T)
out_exp = ref_layer.y.copy()
assert np.allclose(out_exp.T, out, atol=0.0, rtol=0.0)
# generate err array
err = np.ones(out.shape).astype(np.float32)
# run bprop
neon_layer.bprop(neon_layer.be.array(err))
dw = neon_layer.dW.get()
# run bprop
ref_layer.bprop(err.T.astype(dtypeu), 1.0)
# expected output for updates is uniform matrix with
# all elements == ofmsize*batch_size
updates_exp = ref_layer.updates.T
# check dw from neon layer
assert np.allclose(dw, updates_exp, atol=0.0, rtol=0.0)
# the deltas are more complicated since the matricies are not
# uniform, going to use the reference code directly here
# no tolerance here should be exact
dd = np.abs(ref_layer.berror_nopad.T - neon_layer.deltas.get())
assert np.max(dd) == 0.0
return
