utils/misc.py

# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
"""
Misc functions, including distributed helpers.
Mostly copy-paste from torchvision references.
this file is borrowed from DETR repo: https://github.com/facebookresearch/detr/blob/main/util/misc.py
"""
import os
import subprocess
import time
from collections import defaultdict, deque
import datetime
import pickle
from packaging import version
from typing import Optional, List

import torch
import torch.distributed as dist
from torch import Tensor

# needed due to empty tensor bug in pytorch and torchvision 0.5
import torchvision
if version.parse(torchvision.__version__) < version.parse('0.7'):
    from torchvision.ops import _new_empty_tensor
    from torchvision.ops.misc import _output_size


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)


def add_mask(tracklets):
    '''
        input the pieces of tracklets, add the mask overit, the padded 
        positions are set to be True, False for where box exists
    '''
    p, l = tracklets.shape[:2]
    sum_cord = torch.sum(tracklets[:,:,1:4], dim=2)
    mask = (sum_cord==0)
    return NestedTensor(tracklets, mask)