Spaces:
Runtime error
Runtime error
File size: 4,763 Bytes
3e99b05 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 |
# Copyright (c) Facebook, Inc. and its affiliates.
# Modified by Bowen Cheng from https://github.com/facebookresearch/detr/blob/master/util/misc.py
"""
Misc functions, including distributed helpers.
Mostly copy-paste from torchvision references.
"""
from typing import List, Optional
import torch
import torch.distributed as dist
import torchvision
from torch import Tensor
def _max_by_axis(the_list):
# type: (List[List[int]]) -> List[int]
maxes = the_list[0]
for sublist in the_list[1:]:
for index, item in enumerate(sublist):
maxes[index] = max(maxes[index], item)
return maxes
class NestedTensor(object):
def __init__(self, tensors, mask: Optional[Tensor]):
self.tensors = tensors
self.mask = mask
def to(self, device):
# type: (Device) -> NestedTensor # noqa
cast_tensor = self.tensors.to(device)
mask = self.mask
if mask is not None:
assert mask is not None
cast_mask = mask.to(device)
else:
cast_mask = None
return NestedTensor(cast_tensor, cast_mask)
def decompose(self):
return self.tensors, self.mask
def __repr__(self):
return str(self.tensors)
def nested_tensor_from_tensor_list(tensor_list: List[Tensor]):
# TODO make this more general
if tensor_list[0].ndim == 3:
if torchvision._is_tracing():
# nested_tensor_from_tensor_list() does not export well to ONNX
# call _onnx_nested_tensor_from_tensor_list() instead
return _onnx_nested_tensor_from_tensor_list(tensor_list)
# TODO make it support different-sized images
max_size = _max_by_axis([list(img.shape) for img in tensor_list])
# min_size = tuple(min(s) for s in zip(*[img.shape for img in tensor_list]))
batch_shape = [len(tensor_list)] + max_size
b, c, h, w = batch_shape
dtype = tensor_list[0].dtype
device = tensor_list[0].device
tensor = torch.zeros(batch_shape, dtype=dtype, device=device)
mask = torch.ones((b, h, w), dtype=torch.bool, device=device)
for img, pad_img, m in zip(tensor_list, tensor, mask):
pad_img[: img.shape[0], : img.shape[1], : img.shape[2]].copy_(img)
m[: img.shape[1], : img.shape[2]] = False
else:
raise ValueError("not supported")
return NestedTensor(tensor, mask)
# _onnx_nested_tensor_from_tensor_list() is an implementation of
# nested_tensor_from_tensor_list() that is supported by ONNX tracing.
@torch.jit.unused
def _onnx_nested_tensor_from_tensor_list(tensor_list: List[Tensor]) -> NestedTensor:
max_size = []
for i in range(tensor_list[0].dim()):
max_size_i = torch.max(
torch.stack([img.shape[i] for img in tensor_list]).to(torch.float32)
).to(torch.int64)
max_size.append(max_size_i)
max_size = tuple(max_size)
# work around for
# pad_img[: img.shape[0], : img.shape[1], : img.shape[2]].copy_(img)
# m[: img.shape[1], :img.shape[2]] = False
# which is not yet supported in onnx
padded_imgs = []
padded_masks = []
for img in tensor_list:
padding = [(s1 - s2) for s1, s2 in zip(max_size, tuple(img.shape))]
padded_img = torch.nn.functional.pad(img, (0, padding[2], 0, padding[1], 0, padding[0]))
padded_imgs.append(padded_img)
m = torch.zeros_like(img[0], dtype=torch.int, device=img.device)
padded_mask = torch.nn.functional.pad(m, (0, padding[2], 0, padding[1]), "constant", 1)
padded_masks.append(padded_mask.to(torch.bool))
tensor = torch.stack(padded_imgs)
mask = torch.stack(padded_masks)
return NestedTensor(tensor, mask=mask)
def is_dist_avail_and_initialized():
if not dist.is_available():
return False
if not dist.is_initialized():
return False
return True
def masks_to_boxes(masks):
"""Compute the bounding boxes around the provided masks
The masks should be in format [N, H, W] where N is the number of masks, (H, W) are the spatial dimensions.
Returns a [N, 4] tensors, with the boxes in xyxy format
"""
if masks.numel() == 0:
return torch.zeros((0, 4), device=masks.device)
h, w = masks.shape[-2:]
y = torch.arange(0, h, dtype=torch.float)
x = torch.arange(0, w, dtype=torch.float)
y, x = torch.meshgrid(y, x)
x_mask = masks * x.unsqueeze(0)
x_max = x_mask.flatten(1).max(-1)[0]
x_min = x_mask.masked_fill(~(masks.bool()), 1e8).flatten(1).min(-1)[0]
y_mask = masks * y.unsqueeze(0)
y_max = y_mask.flatten(1).max(-1)[0]
y_min = y_mask.masked_fill(~(masks.bool()), 1e8).flatten(1).min(-1)[0]
return torch.stack([x_min, y_min, x_max, y_max], 1) |