def upsampling(data,
scale_h,
scale_w,
layout="NCHW",
method='nearest_neighbor',
align_corners=False):
"""Perform upsampling on the data.
Nearest neighbor and bilinear upsampling are supported.
Parameters
----------
inputs : tvm.Tensor
inputs is a 4-D tensor with shape
[batch, channel, in_height, in_width]
or [batch, in_height, in_width, channel]
scale_h : float
Scaling factor for height
scale_w : float
Scaling factor for width
layout : string, optional
either "NCHW" or "NHWC"
method : {"bilinear", "nearest_neighbor", "bicubic"}
Method to be used for upsampling.
Returns
-------
output : tvm.Tensor
4-D with shape [batch, channel, in_height*scale_h, in_width*scale_w]
or [batch, in_height*scale, in_width*scale, channel]
"""
base_layout = layout[0:4]
if base_layout == "NCHW":
out_shape = (simplify(
topi.cast(tvm.round(data.shape[2] * scale_h),
data.shape[2].dtype)),
simplify(
topi.cast(tvm.round(data.shape[3] * scale_w),
data.shape[3].dtype)))
elif layout == "NHWC":
out_shape = (simplify(
topi.cast(tvm.round(data.shape[1] * scale_h),
data.shape[1].dtype)),
simplify(
topi.cast(tvm.round(data.shape[2] * scale_w),
data.shape[2].dtype)))
else:
raise ValueError("not support this layout {} yet".format(layout))
coord_trans = "align_corners" if align_corners else "asymmetric"
return topi.image.resize(data,
out_shape,
layout=layout,
method=method,
coordinate_transformation_mode=coord_trans)
def test_upsampling_infer_type():
n, c , h, w = tvm.var("n"), tvm.var("c"), tvm.var("h"), tvm.var("w")
scale = tvm.const(2.0, "float64")
x = relay.var("x", relay.TensorType((n, c, h, w), "float32"))
y = relay.nn.upsampling(x, scale_h=2, scale_w=2, layout="NCHW", method="bilinear")
"method=\"BINLINEAR\"" in y.astext()
yy = run_infer_type(y)
assert yy.checked_type == relay.TensorType((n, c, tvm.expr.Cast("int32", tvm.round(h*scale)),
tvm.expr.Cast("int32", tvm.round(w*scale))),
"float32")
n, c = tvm.var("n"), tvm.var("c")
x = relay.var("x", relay.TensorType((n, c, 100, 200), "float32"))
y = relay.nn.upsampling(x, scale_h=2, scale_w=2, layout="NCHW", method="bilinear")
yy = run_infer_type(y)
assert yy.checked_type == relay.TensorType((n, c, 200, 400), "float32")
def _nearest_neighbor(*indices):
n, c, y, x, cc = _get_indices(*indices)
in_y = y_ratio * y
in_x = x_ratio * x
if align_corners:
yint = tvm.round(in_y).astype('int32')
xint = tvm.round(in_x).astype('int32')
else:
# Add epsilon to floor to prevent gpu rounding errors.
epsilon = 1e-5
yint = tvm.floor(in_y + epsilon).astype('int32')
xint = tvm.floor(in_x + epsilon).astype('int32')
return _cast_output(_get_pixel(n, c, yint, xint, cc))
def test_upsampling3d_infer_type():
n, c, d, h, w = tvm.var("n"), tvm.var("c"), tvm.var("d"), tvm.var("h"), tvm.var("w")
scale = tvm.const(2.0, "float64")
x = relay.var("x", relay.TensorType((n, c, d, h, w), "float32"))
y = relay.nn.upsampling3d(x, scale_d=2, scale_h=2, scale_w=2, layout="NCDHW", method="trilinear")
yy = run_infer_type(y)
assert yy.checked_type == relay.TensorType((n, c, tvm.expr.Cast("int32", tvm.round(d*scale)),
tvm.expr.Cast("int32", tvm.round(h*scale)),
tvm.expr.Cast("int32", tvm.round(w*scale))),
"float32")
n, c = tvm.var("n"), tvm.var("c")
x = relay.var("x", relay.TensorType((n, c, 100, 100, 200), "float32"))
y = relay.nn.upsampling3d(x, scale_d=2, scale_h=2, scale_w=2, layout="NCDHW", method="trilinear")
yy = run_infer_type(y)
assert yy.checked_type == relay.TensorType((n, c, 200, 200, 400), "float32")
def _pool(i, c, ph, pw):
roi = rois[i]
batch_index = roi[0].astype('int32')
roi_start_w, roi_start_h, roi_end_w, roi_end_h = roi[1], roi[2], roi[
3], roi[4]
roi_start_h = tvm.round(roi_start_h * spatial_scale).astype('int32')
roi_start_w = tvm.round(roi_start_w * spatial_scale).astype('int32')
roi_end_h = tvm.round(roi_end_h * spatial_scale).astype('int32')
roi_end_w = tvm.round(roi_end_w * spatial_scale).astype('int32')
# force malformed ROIs to be 1x1
roi_h = tvm.max(roi_end_h - roi_start_h + 1, tvm.const(1, 'int32'))
roi_w = tvm.max(roi_end_w - roi_start_w + 1, tvm.const(1, 'int32'))
bin_h = roi_h.astype(dtype) / pooled_size_h
bin_w = roi_w.astype(dtype) / pooled_size_w
# use epsilon to prevent floating point precision loss in floor/ceil
epsilon = tvm.const(0.00001, dtype)
hstart = tvm.floor(ph * bin_h + epsilon).astype('int32')
wstart = tvm.floor(pw * bin_w + epsilon).astype('int32')
hend = tvm.ceil((ph + 1) * bin_h - epsilon).astype('int32')
wend = tvm.ceil((pw + 1) * bin_w - epsilon).astype('int32')
hstart = tvm.min(tvm.max(hstart + roi_start_h, 0), height)
wstart = tvm.min(tvm.max(wstart + roi_start_w, 0), width)
hend = tvm.min(tvm.max(hend + roi_start_h, 0), height)
wend = tvm.min(tvm.max(wend + roi_start_w, 0), width)
non_empty = tvm.all(hstart < hend, wstart < wend)
min_value = lambda dtype: tvm.if_then_else(
non_empty, tvm.min_value(dtype), tvm.const(0.0, dtype))
# pylint: disable=unnecessary-lambda
_max = tvm.comm_reducer(lambda x, y: tvm.make._OpMax(x, y),
min_value,
name='max')
rh = tvm.reduce_axis((0, hend - hstart), 'rh')
rw = tvm.reduce_axis((0, wend - wstart), 'rw')
return _max(data[batch_index, c, hstart + rh, wstart + rw],
axis=[rh, rw])
def _nearest_neighbor(*indices):
n, c, z, y, x, cc = _get_indices(*indices)
in_z = z_ratio * z
in_y = y_ratio * y
in_x = x_ratio * x
if coordinate_transformation_mode == "align_corners":
zint = tvm.round(in_z).astype('int32')
yint = tvm.round(in_y).astype('int32')
xint = tvm.round(in_x).astype('int32')
elif coordinate_transformation_mode in ["asymmetric", "half_pixel"]:
# Add epsilon to floor to prevent gpu rounding errors.
epsilon = 1e-5
zint = tvm.floor(in_z + epsilon).astype('int32')
yint = tvm.floor(in_y + epsilon).astype('int32')
xint = tvm.floor(in_x + epsilon).astype('int32')
else:
raise ValueError("Unsupported coordinate_transformation_mode: {}".format(
coordinate_transformation_mode))
return _cast_output(_get_pixel(n, c, zint, yint, xint, cc))
def round(x):
"""Round elements of x to nearest integer.
Parameters
----------
x : tvm.Tensor
Input argument.
Returns
-------
y : tvm.Tensor
The result.
"""
return tvm.compute(x.shape, lambda *i: tvm.round(x(*i)))
def test_const_propagation():
x1 = tvm.const(4, "int32")
x2 = x1 + 5
assert isinstance(x2, tvm.expr.IntImm) and x2.value == 9
x3 = x2 / 3
assert isinstance(x3, tvm.expr.IntImm) and x3.value == 3
x4 = x3 + 0.5
assert isinstance(x4, tvm.expr.FloatImm) and x4.value == 3.5
x5 = tvm.ceil(x4)
assert isinstance(x5, tvm.expr.FloatImm) and x5.value == 4
x6 = x5.astype('int')
assert isinstance(x6, tvm.expr.IntImm) and x6.value == 4
y = (tvm.round((tvm.const(6.5, 'float32') - 1) / 1.5) + 2).astype('int')
assert isinstance(y, tvm.expr.IntImm) and y.value == 6
def test_const_propagation():
x1 = tvm.const(4, "int32")
x2 = x1 + 5
assert isinstance(x2, tvm.expr.IntImm) and x2.value == 9
x3 = x2 / 3
assert isinstance(x3, tvm.expr.IntImm) and x3.value == 3
x4 = x3 + 0.5
assert isinstance(x4, tvm.expr.FloatImm) and x4.value == 3.5
x5 = tvm.ceil(x4)
assert isinstance(x5, tvm.expr.FloatImm) and x5.value == 4
x6 = x5.astype('int')
assert isinstance(x6, tvm.expr.IntImm) and x6.value == 4
y = (tvm.round((tvm.const(6.5, 'float32') - 1) / 1.5) + 2).astype('int')
assert isinstance(y, tvm.expr.IntImm) and y.value == 6
def round(x):
"""Round elements of x to nearest integer.
Parameters
----------
x : tvm.Tensor
Input argument.
Returns
-------
y : tvm.Tensor
The result.
"""
return tvm.compute(x.shape, lambda *i: tvm.round(x(*i)))
def test_const_fold4():
x1 = tvm.const(4, "int32")
x2 = x1 + 5
assert isinstance(x2, tvm.expr.IntImm) and x2.value == 9
x3 = x2 / 3
assert isinstance(x3, tvm.expr.IntImm) and x3.value == 3
x4 = x3 + 0.55
assert isinstance(x4, tvm.expr.FloatImm) and abs(x4.value - 3.55) < 1e-6
x5 = tvm.ceil(x4)
assert isinstance(x5, tvm.expr.FloatImm) and x5.value == 4
x6 = x5.astype('int')
assert isinstance(x6, tvm.expr.IntImm) and x6.value == 4, "x6={}".format(x6)
y = (tvm.round((tvm.const(6.5, 'float32') - 1) / 1.5) + 2).astype('int')
assert isinstance(y, tvm.expr.IntImm) and y.value == 6
def resize_nearest_neighbor(indices, data, image_height, image_width,
target_height, target_width, boxes=None,
box_indices=None, extrapolation_value=None, layout='NCHW',
coordinate_transformation_mode="align_corners",
out_dtype=None):
"""Perform resize operation with nearest neighbor method on the data.
For details about Nearest-neighbor interpolation please refer to
https://en.wikipedia.org/wiki/Nearest-neighbor_interpolation.
Parameters
----------
indices : tuple
The indices of input data
data : tvm.Tensor
inputs is a 4-D tensor with shape
[batch, channel, in_height, in_width]
or [batch, in_height, in_width, channel]
image_height : integer
Input image height
image_width : integer
Input image width
target_height : integer
The target resized image height
target_width : integer
The target resized image width
boxes : tvm.Tensor, optional
A 2-D tensor of shape [num_boxes, 4]. Each row of the tensor specifies
the coordinates of a box.
box_indices : tvm.Tensor, optional
A 1-D tensor of shape [num_boxes], box_indices[i] specifies the data that
the i-th box refers to.
extrapolation_value: float, optional
Value used for extrapolation, when applicable.
layout: string, optional
"NCHW", "NHWC", or "NCHWc".
coordinate_transformation_mode: string, optional
Describes how to transform the coordinate in the resized tensor
to the coordinate in the original tensor.
Refer to the ONNX Resize operator specification for details.
Available options are "half_pixel", "align_corners" and "asymmetric".
out_dtype: string, optional
Type to return. If left None will be same as input type.
Returns
-------
output : out_dtype
The computed result with type out_dtype
"""
def _cast_output(value, data_dtype="float32", out_dtype=None):
if out_dtype:
dtype = out_dtype
else:
dtype = data_dtype
return value.astype(dtype)
def _get_indices(indices, layout='NCHW'):
if layout == 'NHWC':
n, y, x, c = indices
cc = None
elif layout == 'NCHW':
n, c, y, x = indices
cc = None
else:
n, c, y, x, cc = indices
return n, c, y, x, cc
def _get_pixel(data, layout, n, c, y, x, cc):
if boxes is None:
y = tvm.max(tvm.min(y, image_height - 1), 0)
x = tvm.max(tvm.min(x, image_width - 1), 0)
if layout == 'NHWC':
return data(n, y, x, c).astype('float')
if layout == 'NCHW':
return data(n, c, y, x).astype('float')
# else must be NCHWxc
return data(n, c, y, x, cc).astype('float')
n, c, y, x, cc = _get_indices(indices, layout)
box_idx = box_indices(n) if box_indices is not None else n
if boxes is not None:
y1, x1 = boxes(n, 0), boxes(n, 1)
y2, x2 = boxes(n, 2), boxes(n, 3)
in_h = (image_height - 1) * (y2 - y1)
in_w = (image_width - 1) * (x2 - x1)
h_scale = in_h.astype('float') / (target_height - 1)
w_scale = in_w.astype('float') / (target_width - 1)
in_y = y1 * (image_height - 1) + h_scale * y
in_x = x1 * (image_width - 1) + w_scale * x
else:
if coordinate_transformation_mode == "align_corners":
h_scale = (image_height - 1).astype('float') / (target_height - 1)
w_scale = (image_width - 1).astype('float') / (target_width - 1)
elif coordinate_transformation_mode in ["asymmetric", "half_pixel"]:
h_scale = image_height.astype('float') / target_height
w_scale = image_width.astype('float') / target_width
else:
raise ValueError("Unsupported coordinate_transformation_mode: {}".format(
coordinate_transformation_mode))
in_y = h_scale * y
in_x = w_scale * x
if coordinate_transformation_mode == "align_corners" or boxes is not None:
closest_x_index = tvm.round(in_x).astype("int32")
closest_y_index = tvm.round(in_y).astype("int32")
else:
# Add epsilon to floor to prevent gpu rounding errors.
epsilon = 1e-5
closest_y_index = tvm.floor(in_y + epsilon).astype('int32')
closest_x_index = tvm.floor(in_x + epsilon).astype('int32')
value = _get_pixel(data, layout, box_idx, c, closest_y_index, closest_x_index, cc)
if extrapolation_value is not None:
out = tvm.if_then_else(in_y < 0,
extrapolation_value,
tvm.if_then_else(in_y > image_height - 1,
extrapolation_value,
value))
# use extrapolation_value if in_x is out of boundary
value = tvm.if_then_else(in_x < 0,
extrapolation_value,
tvm.if_then_else(in_x > image_width - 1,
extrapolation_value,
out))
return _cast_output(value, data.dtype, out_dtype=out_dtype)
def upsampling3d(data,
scale_d,
scale_h,
scale_w,
layout="NCDHW",
method='nearest_neighbor',
coordinate_transformation_mode="half_pixel"):
"""Perform upsampling on the data.
Nearest neighbor and bilinear upsampling are supported.
Parameters
----------
inputs : tvm.Tensor
inputs is a 5-D tensor with shape
[batch, channel, in_depth, in_height, in_width]
or [batch, in_depth, in_height, in_width, channel]
scale_d : float
Scaling factor for depth
scale_h : float
Scaling factor for height
scale_w : float
Scaling factor for width
layout : string, optional
either "NCDHW" or "NDHWC"
method : {"trilinear", "nearest_neighbor"}
Method to be used for upsampling.
coordinate_transformation_mode: string, optional
Describes how to transform the coordinate in the resized tensor
to the coordinate in the original tensor.
Refer to the ONNX Resize operator specification for details.
Available options are "half_pixel", "align_corners" and "asymmetric".
Returns
-------
output : tvm.Tensor
5-D with shape [batch, channel, in_depth*scale, in_height*scale, in_width*scale]
or [batch, in_depth*scale, in_height*scale, in_width*scale, channel]
"""
base_layout = layout[0:5]
if base_layout == "NCDHW":
out_shape = (simplify(
topi.cast(tvm.round(data.shape[2] * scale_d),
data.shape[2].dtype)),
simplify(
topi.cast(tvm.round(data.shape[3] * scale_h),
data.shape[3].dtype)),
simplify(
topi.cast(tvm.round(data.shape[4] * scale_w),
data.shape[4].dtype)))
elif layout == "NDHWC":
out_shape = (simplify(
topi.cast(tvm.round(data.shape[1] * scale_d),
data.shape[1].dtype)),
simplify(
topi.cast(tvm.round(data.shape[2] * scale_h),
data.shape[2].dtype)),
simplify(
topi.cast(tvm.round(data.shape[3] * scale_w),
data.shape[3].dtype)))
else:
raise ValueError("not support this layout {} yet".format(layout))
return topi.image.resize3d(
data,
out_shape,
layout=layout,
method=method,
coordinate_transformation_mode=coordinate_transformation_mode)
