Python torch.nn.modules.utils._ntuple() Examples
The following are 22
code examples of torch.nn.modules.utils._ntuple().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
torch.nn.modules.utils
, or try the search function
.
.
Example #1
| Source File: misc.py From FreeAnchor with MIT License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #2
| Source File: misc.py From TinyBenchmark with MIT License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #3
| Source File: misc.py From maskscoring_rcnn with MIT License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #4
| Source File: misc.py From DF-Traffic-Sign-Identification with MIT License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #5
| Source File: misc.py From RRPN_pytorch with MIT License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #6
| Source File: misc.py From NAS-FCOS with BSD 2-Clause "Simplified" License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #7
| Source File: misc.py From training with Apache License 2.0 | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #8
| Source File: wrappers.py From detectron2 with Apache License 2.0 | 5 votes |
|
def interpolate(input, size=None, scale_factor=None, mode="nearest", align_corners=None):
"""
A wrapper around :func:`torch.nn.functional.interpolate` to support zero-size tensor.
"""
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners=align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #9
| Source File: wrappers.py From detectron2 with Apache License 2.0 | 5 votes |
|
def interpolate(input, size=None, scale_factor=None, mode="nearest", align_corners=None):
"""
A wrapper around :func:`torch.nn.functional.interpolate` to support zero-size tensor.
"""
if TORCH_VERSION > (1, 4) or input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners=align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #10
| Source File: misc.py From retinamask with MIT License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #11
| Source File: misc.py From DSGN with MIT License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #12
| Source File: misc.py From Res2Net-maskrcnn with MIT License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #13
| Source File: misc.py From EmbedMask with MIT License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #14
| Source File: misc.py From maskrcnn-benchmark with MIT License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #15
| Source File: misc.py From HRNet-MaskRCNN-Benchmark with MIT License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #16
| Source File: misc.py From sampling-free with MIT License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #17
| Source File: utils.py From training_results_v0.5 with Apache License 2.0 | 5 votes |
|
def interpolate(input, size=None, scale_factor=None, mode='nearest', align_corners=None):
if input.numel() > 0:
return torch.nn.functional.interpolate(input, size, scale_factor, mode, align_corners)
from torch.nn.modules.utils import _ntuple
import math
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError('either size or scale_factor should be defined')
if size is not None and scale_factor is not None:
raise ValueError('only one of size or scale_factor should be defined')
if scale_factor is not None and isinstance(scale_factor, tuple)\
and len(scale_factor) != dim:
raise ValueError('scale_factor shape must match input shape. '
'Input is {}D, scale_factor size is {}'.format(dim, len(scale_factor)))
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #18
| Source File: misc.py From remote_sensing_object_detection_2019 with MIT License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #19
| Source File: misc.py From DetNAS with MIT License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #20
| Source File: misc.py From Clothing-Detection with GNU General Public License v3.0 | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #21
| Source File: misc.py From R2CNN.pytorch with MIT License | 5 votes |
|
def interpolate(
input, size=None, scale_factor=None, mode="nearest", align_corners=None
):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(input.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = input.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(input, output_shape)
Example #22
| Source File: misc.py From Parsing-R-CNN with MIT License | 5 votes |
|
def interpolate(x, size=None, scale_factor=None, mode="nearest", align_corners=None):
if x.numel() > 0:
return torch.nn.functional.interpolate(
x, size, scale_factor, mode, align_corners
)
def _check_size_scale_factor(dim):
if size is None and scale_factor is None:
raise ValueError("either size or scale_factor should be defined")
if size is not None and scale_factor is not None:
raise ValueError("only one of size or scale_factor should be defined")
if (
scale_factor is not None
and isinstance(scale_factor, tuple)
and len(scale_factor) != dim
):
raise ValueError(
"scale_factor shape must match input shape. "
"Input is {}D, scale_factor size is {}".format(dim, len(scale_factor))
)
def _output_size(dim):
_check_size_scale_factor(dim)
if size is not None:
return size
scale_factors = _ntuple(dim)(scale_factor)
# math.floor might return float in py2.7
return [
int(math.floor(x.size(i + 2) * scale_factors[i])) for i in range(dim)
]
output_shape = tuple(_output_size(2))
output_shape = x.shape[:-2] + output_shape
return _NewEmptyTensorOp.apply(x, output_shape)
