def verify(target="llvm", algorithm=nnpack.ConvolutionAlgorithm.AUTO, with_bias=True):
if not tvm.get_global_func("tvm.contrib.nnpack.fully_connected_inference", True):
pytest.skip("extern function is not available")
if not nnpack.is_available():
pytest.skip("nnpack is not available")
ctx = tvm.cpu(0)
output = nnpack.convolution_inference(
data,
kernel,
bias if with_bias else None,
[PAD, PAD, PAD, PAD],
[STRIDE, STRIDE],
algorithm=algorithm,
)
s = te.create_schedule(output.op)
f = tvm.build(s, [data, kernel, bias, output], target)
na = np.random.uniform(size=dshape).astype(data.dtype)
nb = np.random.uniform(size=kshape).astype(kernel.dtype)
nc = np.zeros(bshape, dtype=bias.dtype)
ta = tvm.nd.array(na, ctx)
tb = tvm.nd.array(nb, ctx)
tc = tvm.nd.array(nc, ctx)
td = tvm.nd.array(np.zeros(oshape, dtype=output.dtype), ctx)
f(ta, tb, tc, td)
nd = np_conv(np.reshape(na, (BATCH, IC, IH, IW)), nb, PAD, STRIDE) + nc.reshape(
1, bshape[0], 1, 1
)
tvm.testing.assert_allclose(td.asnumpy(), nd.reshape(BATCH, IC, IH, IW), rtol=1e-5)
def verify(target="llvm",
algorithm=nnpack.ConvolutionAlgorithm.AUTO,
with_bias=True):
if not tvm.module.enabled(target):
print("skip because %s is not enabled..." % target)
return
if not tvm.get_global_func("tvm.contrib.nnpack.fully_connected_inference", True):
print("skip because extern function is not available")
return
if not nnpack.is_available():
return
ctx = tvm.cpu(0)
transformed_kernel = nnpack.convolution_inference_weight_transform(
kernel, algorithm=algorithm)
output = nnpack.convolution_inference_without_weight_transform(
data, transformed_kernel, bias if with_bias else None,
[PAD, PAD, PAD, PAD], [STRIDE, STRIDE],
algorithm=algorithm)
s = tvm.create_schedule(output.op)
f = tvm.build(s, [data, kernel, bias, output], target)
na = np.random.uniform(size=dshape).astype(data.dtype)
nb = np.random.uniform(size=kshape).astype(kernel.dtype)
nc = np.random.uniform(size=bshape).astype(bias.dtype) if with_bias else np.zeros(bshape, dtype=bias.dtype)
ta = tvm.nd.array(na, ctx)
tb = tvm.nd.array(nb, ctx)
tc = tvm.nd.array(nc, ctx)
td = tvm.nd.array(np.zeros(oshape, dtype=output.dtype), ctx)
f(ta, tb, tc, td)
nd = np_conv(np.reshape(na, (BATCH, IC, IH, IW)), nb, PAD, STRIDE) + nc.reshape(1, bshape[0], 1, 1)
tvm.testing.assert_allclose(
td.asnumpy(), nd.reshape(BATCH, IC, IH, IW), rtol=1e-5)
def verify(target="llvm"):
if not tvm.get_global_func("tvm.contrib.nnpack.fully_connected_inference", True):
pytest.skip("extern function is not available")
if not nnpack.is_available():
pytest.skip("nnpack is not available")
ctx = tvm.cpu(0)
f = tvm.build(s, [A, B, D, bias], target)
a = tvm.nd.array(np.random.uniform(size=(l)).astype(A.dtype), ctx)
b = tvm.nd.array(np.random.uniform(size=(m, l)).astype(B.dtype), ctx)
d = tvm.nd.array(np.zeros((m,), dtype=D.dtype), ctx)
bb = 10.0
f(a, b, d, bb)
tvm.testing.assert_allclose(d.asnumpy(), np.dot(a.asnumpy(), b.asnumpy().T) + bb, rtol=1e-5)
def verify(target="llvm"):
if not tvm.module.enabled(target):
print("skip because %s is not enabled..." % target)
return
if not tvm.get_global_func("tvm.contrib.nnpack.fully_connected_inference", True):
print("skip because extern function is not available")
return
if not nnpack.is_available():
return
ctx = tvm.cpu(0)
f = tvm.build(s, [A, B, D, bias], target)
a = tvm.nd.array(np.random.uniform(size=(l)).astype(A.dtype), ctx)
b = tvm.nd.array(np.random.uniform(size=(m, l)).astype(B.dtype), ctx)
d = tvm.nd.array(np.zeros((m, ), dtype=D.dtype), ctx)
bb = 10.0
f(a, b, d, bb)
tvm.testing.assert_allclose(
d.asnumpy(), np.dot(a.asnumpy(), b.asnumpy().T) + bb, rtol=1e-5)
def test_conv2d_nchw():
if not tvm.get_global_func(
"tvm.contrib.nnpack.convolution_inference_without_weight_transform", True
):
skip("extern function is not available")
if not nnpack.is_available():
skip("nnpack is not available")
devices = ["llvm -device=arm_cpu"]
autotvm.GLOBAL_SCOPE.silent = True
with WinogradFallback():
# resnet 18 workloads
verify_conv2d_nchw(1, 64, 56, 64, 3, 1, 1, devices=devices)
verify_conv2d_nchw(1, 128, 28, 128, 3, 1, 1, devices=devices)
verify_conv2d_nchw(1, 256, 14, 256, 3, 1, 1, devices=devices)
verify_conv2d_nchw(1, 512, 7, 512, 3, 1, 1, devices=devices)
# unet workloads
verify_conv2d_nchw(1, 3, 192, 12, 3, 1, 1, add_bias=True, devices=devices)
verify_conv2d_nchw(1, 4, 192, 12, 3, 1, 1, add_bias=True, devices=devices)
verify_conv2d_nchw(1, 12, 96, 24, 3, 1, 1, add_bias=True, devices=devices)
verify_conv2d_nchw(1, 24, 48, 48, 3, 1, 1, add_bias=True, devices=devices)
verify_conv2d_nchw(1, 48, 24, 96, 3, 1, 1, add_bias=True, devices=devices)
verify_conv2d_nchw(1, 96, 12, 180, 3, 1, 1, add_bias=True, devices=devices)
verify_conv2d_nchw(1, 180, 6, 220, 3, 1, 1, add_bias=True, devices=devices)
verify_conv2d_nchw(1, 220, 6, 180, 3, 1, 1, add_bias=True, devices=devices)
verify_conv2d_nchw(1, 180, 12, 96, 3, 1, 1, add_bias=True, devices=devices)
verify_conv2d_nchw(1, 96, 24, 48, 3, 1, 1, add_bias=True, devices=devices)
verify_conv2d_nchw(1, 48, 48, 24, 3, 1, 1, add_bias=True, devices=devices)
verify_conv2d_nchw(1, 24, 96, 12, 3, 1, 1, add_bias=True, devices=devices)
verify_conv2d_nchw(1, 12, 192, 1, 3, 1, 1, add_bias=True, devices=devices)
# relu, bias
verify_conv2d_nchw(1, 64, 56, 64, 3, 1, 1, add_bias=True, devices=devices)
verify_conv2d_nchw(1, 64, 56, 64, 3, 1, 1, add_relu=True, devices=devices)
verify_conv2d_nchw(1, 64, 56, 64, 3, 1, 1, add_relu=True, add_bias=True, devices=devices)
# werid workloads
verify_conv2d_nchw(1, 3, 3, 3, 3, 1, 1, devices=devices)
verify_conv2d_nchw(1, 13, 71, 59, 3, 1, 1, devices=devices)
autotvm.GLOBAL_SCOPE.silent = False
def verify(target="llvm",
algorithm=nnpack.ConvolutionAlgorithm.AUTO,
with_bias=True):
if not tvm.module.enabled(target):
print("skip because %s is not enabled..." % target)
return
if not tvm.get_global_func(
"tvm.contrib.nnpack.convolution_inference_without_weight_transform",
True):
print("skip because extern function is not available")
return
if not nnpack.is_available():
return
ctx = tvm.cpu(0)
transformed_kernel = nnpack.convolution_inference_weight_transform(
kernel, algorithm=algorithm)
output = nnpack.convolution_inference_without_weight_transform(
data,
transformed_kernel,
bias if with_bias else None, [PAD, PAD, PAD, PAD],
[STRIDE, STRIDE],
algorithm=algorithm)
s = tvm.create_schedule(output.op)
f = tvm.build(s, [data, kernel, bias, output], target)
na = np.random.uniform(size=dshape).astype(data.dtype)
nb = np.random.uniform(size=kshape).astype(kernel.dtype)
nc = np.random.uniform(size=bshape).astype(
bias.dtype) if with_bias else np.zeros(bshape, dtype=bias.dtype)
ta = tvm.nd.array(na, ctx)
tb = tvm.nd.array(nb, ctx)
tc = tvm.nd.array(nc, ctx)
td = tvm.nd.array(np.zeros(oshape, dtype=output.dtype), ctx)
f(ta, tb, tc, td)
nd = np_conv(np.reshape(na, (BATCH, IC, IH, IW)), nb, PAD,
STRIDE) + nc.reshape(1, bshape[0], 1, 1)
tvm.testing.assert_allclose(td.asnumpy(),
nd.reshape(BATCH, IC, IH, IW),
rtol=1e-5)
def verify(target="llvm"):
if not tvm.module.enabled(target):
print("skip because %s is not enabled..." % target)
return
if not tvm.get_global_func("tvm.contrib.nnpack.fully_connected_output",
True):
print("skip because extern function is not available")
return
if not nnpack.is_available():
return
ctx = tvm.cpu(0)
f = tvm.build(s, [A, B, D, bias], target)
a = tvm.nd.array(np.random.uniform(size=(n, l)).astype(A.dtype), ctx)
b = tvm.nd.array(np.random.uniform(size=(m, l)).astype(B.dtype), ctx)
d = tvm.nd.array(np.zeros((n, m), dtype=D.dtype), ctx)
bb = 10.0
f(a, b, d, bb)
tvm.testing.assert_allclose(d.asnumpy(),
np.dot(a.asnumpy(),
b.asnumpy().T) + bb,
rtol=1e-5)
def verify(target="llvm"):
if not tvm.module.enabled(target):
print("skip because %s is not enabled..." % target)
return
if not tvm.get_global_func("tvm.contrib.nnpack.fully_connected_inference", True):
print("skip because extern function is not available")
return
if not nnpack.is_available():
return
ctx = tvm.cpu(0)
f = tvm.build(s, [data, kernel, bias, output], target)
na = np.random.uniform(size=dshape).astype(data.dtype)
nb = np.random.uniform(size=kshape).astype(kernel.dtype)
nc = np.zeros(bshape, dtype=bias.dtype)
ta = tvm.nd.array(na, ctx)
tb = tvm.nd.array(nb, ctx)
tc = tvm.nd.array(nc, ctx)
td = tvm.nd.array(np.zeros(oshape, dtype=output.dtype), ctx)
f(ta, tb, tc, td)
nd = np_conv(na, nb, PAD)
tvm.testing.assert_allclose(
td.asnumpy(), nd, rtol=1e-5)
def verify(target="llvm"):
if not tvm.module.enabled(target):
print("skip because %s is not enabled..." % target)
return
if not tvm.get_global_func(
"tvm.contrib.nnpack.fully_connected_inference", True):
print("skip because extern function is not available")
return
if not nnpack.is_available():
return
ctx = tvm.cpu(0)
f = tvm.build(s, [data, kernel, bias, output], target)
na = np.random.uniform(size=dshape).astype(data.dtype)
nb = np.random.uniform(size=kshape).astype(kernel.dtype)
nc = np.zeros(bshape, dtype=bias.dtype)
ta = tvm.nd.array(na, ctx)
tb = tvm.nd.array(nb, ctx)
tc = tvm.nd.array(nc, ctx)
td = tvm.nd.array(np.zeros(oshape, dtype=output.dtype), ctx)
f(ta, tb, tc, td)
nd = np_conv(na, nb, PAD)
tvm.testing.assert_allclose(td.asnumpy(), nd, rtol=1e-5)
