在自己数据集下运行preview.py报错 ValueError: Expected y_max for bbox

[TIMEXue]

信息如下：
Traceback (most recent call last):24493 .........] ETA: 41m
File "preview.py", line 33, in
for i, sample in enumerate(preview):
File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 345, in next
data = self._next_data()
File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 385, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/lungchi/easy_detection/dataloader/list_dataset.py", line 21, in getitem
return dataset[index - total]
File "/home/lungchi/easy_detection/dataloader/voc.py", line 213, in getitem
'labels': labels
File "/opt/conda/lib/python3.7/site-packages/albumentations/core/composition.py", line 188, in call
p.preprocess(data)
File "/opt/conda/lib/python3.7/site-packages/albumentations/core/utils.py", line 84, in preprocess
data[data_name] = self.check_and_convert(data[data_name], rows, cols, direction="to")
File "/opt/conda/lib/python3.7/site-packages/albumentations/core/utils.py", line 92, in check_and_convert
return self.convert_to_albumentations(data, rows, cols)
File "/opt/conda/lib/python3.7/site-packages/albumentations/augmentations/bbox_utils.py", line 51, in convert_to_albumentations
return convert_bboxes_to_albumentations(data, self.params.format, rows, cols, check_validity=True)
File "/opt/conda/lib/python3.7/site-packages/albumentations/augmentations/bbox_utils.py", line 306, in convert_bboxes_to_albumentations
return [convert_bbox_to_albumentations(bbox, source_format, rows, cols, check_validity) for bbox in bboxes]
File "/opt/conda/lib/python3.7/site-packages/albumentations/augmentations/bbox_utils.py", line 306, in
return [convert_bbox_to_albumentations(bbox, source_format, rows, cols, check_validity) for bbox in bboxes]
File "/opt/conda/lib/python3.7/site-packages/albumentations/augmentations/bbox_utils.py", line 254, in convert_bbox_to_albumentations
check_bbox(bbox)
File "/opt/conda/lib/python3.7/site-packages/albumentations/augmentations/bbox_utils.py", line 333, in check_bbox
"to be in the range [0.0, 1.0], got {value}.".format(bbox=bbox, name=name, value=value)
ValueError: Expected y_max for bbox (0.19440914866581957, 0.14192139737991266, 0.7903430749682337, 1.0087336244541485, 1) to be in the range [0.0, 1.0], got 1.0087336244541485.

[misads]

可能是数据集格式有问题 boundind box的范围超出了图像的宽高，可以分别尝试以下方法：

1. 修改preview.py Line31
   

   easy_detection/preview.py

   Line 31 in 7eee2bf

   preview = train_dataloader # train_dataloader, val_dataloader

   
   改为

preview = val_dataloader 

2. 修改 dataloader/voc.py
   

   easy_detection/dataloader/voc.py

   Lines 111 to 112 in 7eee2bf

   	width = int(size.find('width').text)
   	height = int(size.find('height').text)

   
   改为

image = cv2.imread(abspath)
height, width, _ = image.shape

3. preview报错时打印出文件路径sample['path']，检查数据集Annotations中该图像的标注，width与height是否与图像对应，以及目标框是否超出图像长宽范围。

[TIMEXue]

数据格式的问题，昨天解决了，谢谢