maskrcnn_benchmark 报错 target = target.resize(image.size)---＞‘list‘ object has no attribute ‘resize‘

原创已于 2024-01-15 22:02:27 修改 · 819 阅读

4 ·

CC 4.0 BY-SA版权

文章标签：

#python #pytorch #深度学习

于 2022-07-07 11:20:20 首次发布

在maskrcnn_benchmark执行train_net.py时出现‘list’ object has no attribute ‘resize’错误，经定位是类COCODataset中声明的self.transforms覆盖父类的同名属性，推测是torchvision升级所致。解决方法是将类COCODataset中self.transforms重命名为self.transforms_，并修改__getitem__函数中的变量。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

在maskrcnn_benchmark执行train_net.py的时候报了一个错误：‘list’ object has no attribute ‘resize’。
具体错误信息如下：

  File "/root/wh/PyCharm_Project/FCOS_PLUS-master/tools/train_net.py", line 182, in <module>
    main()
  File "/root/wh/PyCharm_Project/FCOS_PLUS-master/tools/train_net.py", line 173, in main
    model = train(cfg, args.local_rank, args.distributed)
  File "/root/wh/PyCharm_Project/FCOS_PLUS-master/tools/train_net.py", line 79, in train
    arguments,
  File "/root/wh/PyCharm_Project/FCOS_PLUS-master/maskrcnn_benchmark/engine/trainer.py", line 57, in do_train
    for iteration, (images, targets, _) in enumerate(data_loader, start_iter):
  File "/root/miniconda3/envs/OD_wh/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 521, in __next__
    data = self._next_data()
  File "/root/miniconda3/envs/OD_wh/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 1203, in _next_data
    return self._process_data(data)
  File "/root/miniconda3/envs/OD_wh/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data
    data.reraise()
  File "/root/miniconda3/envs/OD_wh/lib/python3.6/site-packages/torch/_utils.py", line 434, in reraise
    raise exception
AttributeError: Caught AttributeError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/root/miniconda3/envs/OD_wh/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
    data = fetcher.fetch(index)
  File "/root/miniconda3/envs/OD_wh/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/root/miniconda3/envs/OD_wh/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 49, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/root/wh/PyCharm_Project/FCOS_PLUS-master/maskrcnn_benchmark/data/datasets/coco.py", line 67, in __getitem__
    img, anno = super(COCODataset, self).__getitem__(idx)
  File "/root/miniconda3/envs/OD_wh/lib/python3.6/site-packages/torchvision/datasets/coco.py", line 49, in __getitem__
    image, target = self.transforms(image, target)
  File "/root/wh/PyCharm_Project/FCOS_PLUS-master/maskrcnn_benchmark/data/transforms/transforms.py", line 15, in __call__
    image, target = t(image, target)
  File "/root/wh/PyCharm_Project/FCOS_PLUS-master/maskrcnn_benchmark/data/transforms/transforms.py", line 60, in __call__
    target = target.resize(image.size)
AttributeError: 'list' object has no attribute 'resize'

后经定位发现是

maskrcnn_benchmark/data/datasets/coco.py

中定义的类COCODataset中声明的self.transforms覆盖掉了父类torchvision.datasets.coco.CocoDetection中的self.transforms
PS:应该是torchvision升级导致的问题
**

解决方法：

**
将类COCODataset中声明的self.transforms重命名为self.transforms_即可（__getitem__函数中的变量也要修改）

原代码为：

class COCODataset(torchvision.datasets.coco.CocoDetection):
    def __init__(
        self, ann_file, root, remove_images_without_annotations, transforms=None
    ):
        super(COCODataset, self).__init__(root, ann_file)
        # sort indices for reproducible results
        self.ids = sorted(self.ids)

        # filter images without detection annotations
        if remove_images_without_annotations:
            ids = []
            for img_id in self.ids:
                ann_ids = self.coco.getAnnIds(imgIds=img_id, iscrowd=None)
                anno = self.coco.loadAnns(ann_ids)
                if has_valid_annotation(anno):
                    ids.append(img_id)
            self.ids = ids

        self.json_category_id_to_contiguous_id = {
            v: i + 1 for i, v in enumerate(self.coco.getCatIds())
        }
        self.contiguous_category_id_to_json_id = {
            v: k for k, v in self.json_category_id_to_contiguous_id.items()
        }
        self.id_to_img_map = {k: v for k, v in enumerate(self.ids)}
        self.transforms = transforms

    def __getitem__(self, idx):
        img, anno = super(COCODataset, self).__getitem__(idx)

        # filter crowd annotations
        # TODO might be better to add an extra field
        anno = [obj for obj in anno if obj["iscrowd"] == 0]

        boxes = [obj["bbox"] for obj in anno]
        boxes = torch.as_tensor(boxes).reshape(-1, 4)  # guard against no boxes
        target = BoxList(boxes, img.size, mode="xywh").convert("xyxy")

        classes = [obj["category_id"] for obj in anno]
        classes = [self.json_category_id_to_contiguous_id[c] for c in classes]
        classes = torch.tensor(classes)
        target.add_field("labels", classes)

        masks = [obj["segmentation"] for obj in anno]
        masks = SegmentationMask(masks, img.size, mode='poly')
        target.add_field("masks", masks)

        if anno and "keypoints" in anno[0]:
            keypoints = [obj["keypoints"] for obj in anno]
            keypoints = PersonKeypoints(keypoints, img.size)
            target.add_field("keypoints", keypoints)

        target = target.clip_to_image(remove_empty=True)
        if self.transforms is not None:
            img, target = self.transforms(img, target)

        return img, target, idx

    def get_img_info(self, index):
        img_id = self.id_to_img_map[index]
        img_data = self.coco.imgs[img_id]
        return img_data

修改后为：

class COCODataset(torchvision.datasets.coco.CocoDetection):
    def __init__(
        self, ann_file, root, remove_images_without_annotations, transforms=None
    ):
        super(COCODataset, self).__init__(root, ann_file)
        # sort indices for reproducible results
        self.ids = sorted(self.ids)

        # filter images without detection annotations
        if remove_images_without_annotations:
            ids = []
            for img_id in self.ids:
                ann_ids = self.coco.getAnnIds(imgIds=img_id, iscrowd=None)
                anno = self.coco.loadAnns(ann_ids)
                if has_valid_annotation(anno):
                    ids.append(img_id)
            self.ids = ids

        self.json_category_id_to_contiguous_id = {
            v: i + 1 for i, v in enumerate(self.coco.getCatIds())
        }
        self.contiguous_category_id_to_json_id = {
            v: k for k, v in self.json_category_id_to_contiguous_id.items()
        }
        self.id_to_img_map = {k: v for k, v in enumerate(self.ids)}
        self.transforms_ = transforms

    def __getitem__(self, idx):
        img, anno = super(COCODataset, self).__getitem__(idx)

        # filter crowd annotations
        # TODO might be better to add an extra field
        anno = [obj for obj in anno if obj["iscrowd"] == 0]

        boxes = [obj["bbox"] for obj in anno]
        boxes = torch.as_tensor(boxes).reshape(-1, 4)  # guard against no boxes
        target = BoxList(boxes, img.size, mode="xywh").convert("xyxy")

        classes = [obj["category_id"] for obj in anno]
        classes = [self.json_category_id_to_contiguous_id[c] for c in classes]
        classes = torch.tensor(classes)
        target.add_field("labels", classes)

        masks = [obj["segmentation"] for obj in anno]
        masks = SegmentationMask(masks, img.size, mode='poly')
        target.add_field("masks", masks)

        if anno and "keypoints" in anno[0]:
            keypoints = [obj["keypoints"] for obj in anno]
            keypoints = PersonKeypoints(keypoints, img.size)
            target.add_field("keypoints", keypoints)

        target = target.clip_to_image(remove_empty=True)
        if self.transforms_ is not None:
            img, target = self.transforms_(img, target)

        return img, target, idx

    def get_img_info(self, index):
        img_id = self.id_to_img_map[index]
        img_data = self.coco.imgs[img_id]
        return img_data