def multibox_prior(data, sizes=(1,), ratios=(1,), steps=(-1, -1), offsets=(0.5, 0.5), clip=False):
"""Generate prior(anchor) boxes from data, sizes and ratios.
Parameters
----------
data : tvm.Tensor
4-D with shape [batch, c_in, h_in, w_in]]
sizes : tuple of float
Tuple of sizes for anchor boxes.
ratios : tuple of float
Tuple of ratios for anchor boxes.
steps : Tuple of float
Priorbox step across y and x, -1 for auto calculation.
offsets : tuple of int
Priorbox center offsets, y and x respectively.
clip : boolean
Whether to clip out-of-boundary boxes.
Returns
-------
out : tvm.Tensor
3-D tensor with shape [1, h_in * w_in * (num_sizes + num_ratios - 1), 4]
"""
out = hybrid_multibox_prior(data, tvm.convert(sizes), tvm.convert(ratios),
tvm.convert(steps), tvm.convert(offsets))
if clip:
out = topi.clip(out, 0, 1)
return out
def verify_clip(N, a_min, a_max, dtype):
A = tvm.placeholder((N, N), dtype=dtype, name='A')
B = topi.clip(A, a_min, a_max)
s = tvm.create_schedule([B.op])
# use memoize to pickle the test data for next time use
@memoize("topi.tests.test_topi_clip")
def get_ref_data():
a_np = np.random.uniform(a_min * 2, a_max * 2,
size=(N, N)).astype(dtype)
b_np = np.clip(a_np, a_min, a_max)
return a_np, b_np
a_np, b_np = get_ref_data()
def check_device(device):
ctx = tvm.context(device, 0)
if not ctx.exist:
print("Skip because %s is not enabled" % device)
return
print("Running on target: %s" % device)
with tvm.target.create(device):
s = topi.generic.schedule_injective(B)
a = tvm.nd.array(a_np, ctx)
b = tvm.nd.array(np.zeros(get_const_tuple(B.shape), dtype=dtype), ctx)
f = tvm.build(s, [A, B], device, name="clip")
f(a, b)
np.testing.assert_allclose(b.asnumpy(), b_np, rtol=1e-5)
for device in get_all_backend():
check_device(device)
def multibox_prior(data, sizes=(1,), ratios=(1,), steps=(-1, -1), offsets=(0.5, 0.5), clip=False):
"""Generate prior(anchor) boxes from data, sizes and ratios.
Parameters
----------
data : tvm.Tensor
4-D with shape [batch, c_in, h_in, w_in]]
sizes : tuple of float
Tuple of sizes for anchor boxes.
ratios : tuple of float
Tuple of ratios for anchor boxes.
steps : Tuple of float
Priorbox step across y and x, -1 for auto calculation.
offsets : tuple of int
Priorbox center offsets, y and x respectively.
clip : boolean
Whether to clip out-of-boundary boxes.
Returns
-------
out : tvm.Tensor
3-D tensor with shape [1, h_in * w_in * (num_sizes + num_ratios - 1), 4]
"""
out = hybrid_multibox_prior(data, tvm.convert(sizes), tvm.convert(ratios),
tvm.convert(steps), tvm.convert(offsets))
if clip:
out = topi.clip(out, 0, 1)
return out
def verify_clip(N, a_min, a_max, dtype):
A = tvm.placeholder((N, N), dtype=dtype, name='A')
B = topi.clip(A, a_min, a_max)
s = tvm.create_schedule([B.op])
# use memoize to pickle the test data for next time use
@memoize("topi.tests.test_topi_clip")
def get_ref_data():
a_np = np.random.uniform(a_min*2, a_max*2, size=(N, N)).astype(dtype)
b_np = np.clip(a_np, a_min, a_max)
return a_np, b_np
a_np, b_np = get_ref_data()
def check_device(device):
ctx = tvm.context(device, 0)
if not ctx.exist:
print("Skip because %s is not enabled" % device)
return
print("Running on target: %s" % device)
with tvm.target.create(device):
s = topi.generic.schedule_injective(B)
a = tvm.nd.array(a_np, ctx)
b = tvm.nd.array(np.zeros(get_const_tuple(B.shape), dtype=dtype), ctx)
f = tvm.build(s, [A, B], device, name="clip")
f(a, b)
tvm.testing.assert_allclose(b.asnumpy(), b_np, rtol=1e-5)
for device in get_all_backend():
check_device(device)
def verify_clip(N, a_min, a_max, dtype):
A = tvm.placeholder((N, N), dtype=dtype, name='A')
B = topi.clip(A, a_min, a_max)
s = tvm.create_schedule([B.op])
# use memoize to pickle the test data for next time use
@memoize("topi.tests.test_topi_clip")
def get_ref_data():
a_np = np.random.uniform(a_min*2, a_max*2, size=(N, N)).astype(dtype)
b_np = np.clip(a_np, a_min, a_max)
return a_np, b_np
a_np, b_np = get_ref_data()
def check_device(device):
if not tvm.module.enabled(device):
print("Skip because %s is not enabled" % device)
return
ctx = tvm.cpu(0) if device == "llvm" else tvm.gpu(0)
a = tvm.nd.array(a_np, ctx)
b = tvm.nd.array(np.zeros(get_const_tuple(B.shape), dtype=dtype), ctx)
f = tvm.build(s, [A, B], device, name="clip")
f(a, b)
np.testing.assert_allclose(b.asnumpy(), b_np, rtol=1e-5)
for device in ['llvm']:
check_device(device)
def verify_clip(N, a_min, a_max, dtype):
A = tvm.placeholder((N, N), dtype=dtype, name='A')
B = topi.clip(A, a_min, a_max)
s = tvm.create_schedule([B.op])
# use memoize to pickle the test data for next time use
@memoize("topi.tests.test_topi_clip")
def get_ref_data():
a_np = np.random.uniform(a_min * 2, a_max * 2,
size=(N, N)).astype(dtype)
b_np = np.clip(a_np, a_min, a_max)
return a_np, b_np
a_np, b_np = get_ref_data()
def check_device(device):
if not tvm.module.enabled(device):
print("Skip because %s is not enabled" % device)
return
ctx = tvm.cpu(0) if device == "llvm" else tvm.gpu(0)
a = tvm.nd.array(a_np, ctx)
b = tvm.nd.array(np.zeros(get_const_tuple(B.shape), dtype=dtype), ctx)
f = tvm.build(s, [A, B], device, name="clip")
f(a, b)
np.testing.assert_allclose(b.asnumpy(), b_np, rtol=1e-5)
for device in ['llvm']:
check_device(device)
def multibox_prior_gpu(data,
sizes=(1, ),
ratios=(1, ),
steps=(-1, -1),
offsets=(0.5, 0.5),
clip=False):
"""Generate prior(anchor) boxes from data, sizes and ratios.
Parameters
----------
data : tvm.Tensor
4-D with shape [batch, c_in, h_in, w_in]]
sizes : tuple of float
Tuple of sizes for anchor boxes.
ratios : tuple of float
Tuple of ratios for anchor boxes.
steps : Tuple of float
Priorbox step across y and x, -1 for auto calculation.
offsets : tuple of int
Priorbox center offsets, y and x respectively.
clip : boolean
Whether to clip out-of-boundary boxes.
Returns
-------
out : tvm.Tensor
3-D tensor with shape [1, h_in * w_in * (num_sizes + num_ratios - 1), 4]
"""
num_sizes = len(sizes)
num_ratios = len(ratios)
oshape = (1, data.shape[2] * data.shape[3] * (num_sizes + num_ratios - 1),
4)
out = tvm.extern(oshape, [data],
lambda ins, outs: multibox_prior_ir(
ins[0], outs[0], sizes, ratios, steps, offsets),
tag="multibox_prior")
if clip:
out = topi.clip(out, 0, 1)
return out
def multibox_prior_gpu(data, sizes=(1,), ratios=(1,), steps=(-1, -1),
offsets=(0.5, 0.5), clip=False):
"""Generate prior(anchor) boxes from data, sizes and ratios.
Parameters
----------
data : tvm.Tensor
4-D with shape [batch, c_in, h_in, w_in]]
sizes : tuple of float
Tuple of sizes for anchor boxes.
ratios : tuple of float
Tuple of ratios for anchor boxes.
steps : Tuple of float
Priorbox step across y and x, -1 for auto calculation.
offsets : tuple of int
Priorbox center offsets, y and x respectively.
clip : boolean
Whether to clip out-of-boundary boxes.
Returns
-------
out : tvm.Tensor
3-D tensor with shape [1, h_in * w_in * (num_sizes + num_ratios - 1), 4]
"""
num_sizes = len(sizes)
num_ratios = len(ratios)
oshape = (
1, data.shape[2] * data.shape[3] * (num_sizes + num_ratios - 1), 4)
out = tvm.extern(oshape, [data], lambda ins, outs:
multibox_prior_ir(
ins[0], outs[0], sizes, ratios, steps, offsets),
tag="multibox_prior")
if clip:
out = topi.clip(out, 0, 1)
return out
def clip_compute(attrs, inputs, output_type, target):
assert len(inputs) == 1
return [topi.clip(inputs[0], attrs.a_min, attrs.a_max)]
def _interpolate(im, im_shape, x, y, out_size, dtype):
num_batch = im_shape[0]
height = im_shape[1]
width = im_shape[2]
channels = im_shape[3]
out_height = out_size[0]
out_width = out_size[1]
max_y = int(im_shape[1] - 1)
max_x = int(im_shape[2] - 1)
#[-1,1] -> [0, width-1]
x = topi.multiply(topi.add(x, tvm.const(1, dtype=dtype)), width / tvm.const(2, dtype=dtype))
y = topi.multiply(topi.add(y, tvm.const(1, dtype=dtype)), height / tvm.const(2, dtype=dtype))
# do sampling
dim3 = out_height * out_width * num_batch
x0 = topi.cast(topi.floor(x), 'int32')
y0 = topi.cast(topi.floor(y), 'int32')
x1 = topi.add(x0,tvm.const(1, dtype="int32"))
y1 = topi.add(y0,tvm.const(1, dtype="int32"))
x0 = topi.clip(x0, 0, max_x)
x1 = topi.clip(x1, 0, max_x)
y0 = topi.clip(y0, 0, max_y)
y1 = topi.clip(y1, 0, max_y)
dim2 = width
dim1 = width * height
base = tvm.compute((dim3,),lambda i:(i // (out_height * out_width)) * width * height, name = 'base')
base_y0 = topi.add(base, topi.multiply(y0, dim2))
base_y1 = topi.add(base, topi.multiply(y1, dim2))
idx_a = topi.add(base_y0, x0)
idx_b = topi.add(base_y1, x0)
idx_c = topi.add(base_y0, x1)
idx_d = topi.add(base_y1, x1)
im_flat = topi.reshape(im, (num_batch * height * width, channels))
im_flat = topi.cast(im_flat, dtype)
Ia = tvm.compute((dim3, channels),lambda i,j: im_flat[idx_a[i], j], name = 'Ia')
Ib = tvm.compute((dim3, channels),lambda i,j: im_flat[idx_b[i], j], name = 'Ib')
Ic = tvm.compute((dim3, channels),lambda i,j: im_flat[idx_c[i], j], name = 'Ic')
Id = tvm.compute((dim3, channels),lambda i,j: im_flat[idx_d[i], j], name = 'Id')
x0_f = topi.cast(x0, dtype)
x1_f = topi.cast(x1, dtype)
y0_f = topi.cast(y0, dtype)
y1_f = topi.cast(y1, dtype)
wa = topi.expand_dims(topi.multiply(topi.subtract(x1_f, x), topi.subtract(y1_f, y)), 1)
wb = topi.expand_dims(topi.multiply(topi.subtract(x1_f, x), topi.subtract(y, y0_f)), 1)
wc = topi.expand_dims(topi.multiply(topi.subtract(x, x0_f), topi.subtract(y1_f, y)), 1)
wd = topi.expand_dims(topi.multiply(topi.subtract(x, x0_f), topi.subtract(y, y0_f)), 1)
output = topi.add(topi.add(topi.add(topi.multiply(wa, Ia), topi.multiply(wb, Ib)),topi.multiply(wc, Ic)), topi.multiply(wd, Id))
return output
def _interpolate(im, im_shape, x, y, out_size, dtype):
num_batch = im_shape[0]
height = im_shape[1]
width = im_shape[2]
channels = im_shape[3]
out_height = out_size[0]
out_width = out_size[1]
max_y = int(im_shape[1] - 1)
max_x = int(im_shape[2] - 1)
# [-1,1] -> [0, width-1]
x_temp = topi.multiply(topi.add(x, tvm.const(1, dtype=dtype)),
width / tvm.const(2, dtype=dtype))
y_temp = topi.multiply(topi.add(y, tvm.const(1, dtype=dtype)),
height / tvm.const(2, dtype=dtype))
# do sampling
dim3 = out_height * out_width * num_batch
x_zero = topi.cast(topi.floor(x_temp), 'int32')
y_zero = topi.cast(topi.floor(y_temp), 'int32')
x_one = topi.add(x_zero, tvm.const(1, dtype="int32"))
y_one = topi.add(y_zero, tvm.const(1, dtype="int32"))
x_zero = topi.clip(x_zero, 0, max_x)
x_one = topi.clip(x_one, 0, max_x)
y_zero = topi.clip(y_zero, 0, max_y)
y_one = topi.clip(y_one, 0, max_y)
dim2 = width
base = tvm.compute((dim3, ),
lambda i:
(i // (out_height * out_width)) * width * height,
name='base')
base_y0 = topi.add(base, topi.multiply(y_zero, dim2))
base_y1 = topi.add(base, topi.multiply(y_one, dim2))
idx_a = topi.add(base_y0, x_zero)
idx_b = topi.add(base_y1, x_zero)
idx_c = topi.add(base_y0, x_one)
idx_d = topi.add(base_y1, x_one)
im_flat = topi.reshape(im, (num_batch * height * width, channels))
im_flat = topi.cast(im_flat, dtype)
i_a = tvm.compute((dim3, channels),
lambda i, j: im_flat[idx_a[i], j],
name='Ia')
i_b = tvm.compute((dim3, channels),
lambda i, j: im_flat[idx_b[i], j],
name='Ib')
i_c = tvm.compute((dim3, channels),
lambda i, j: im_flat[idx_c[i], j],
name='Ic')
i_d = tvm.compute((dim3, channels),
lambda i, j: im_flat[idx_d[i], j],
name='Id')
x0_f = topi.cast(x_zero, dtype)
x1_f = topi.cast(x_one, dtype)
y0_f = topi.cast(y_zero, dtype)
y1_f = topi.cast(y_zero, dtype)
w_a = topi.expand_dims(
topi.multiply(topi.subtract(x1_f, x_temp),
topi.subtract(y1_f, y_temp)), 1)
w_b = topi.expand_dims(
topi.multiply(topi.subtract(x1_f, x_temp),
topi.subtract(y_temp, y0_f)), 1)
w_c = topi.expand_dims(
topi.multiply(topi.subtract(x_temp, x0_f),
topi.subtract(y1_f, y_temp)), 1)
w_d = topi.expand_dims(
topi.multiply(topi.subtract(x_temp, x0_f),
topi.subtract(y_temp, y0_f)), 1)
output = topi.add(
topi.add(
topi.add(topi.multiply(w_a, i_a), topi.multiply(w_b, i_b)),
topi.multiply(w_c, i_c)), topi.multiply(w_d, i_d))
return output
def clip_compute(attrs, inputs, output_type, target):
assert len(inputs) == 1
return [topi.clip(inputs[0], attrs.a_min, attrs.a_max)]