训练自己的数据集时报错IndexError: index 5 is out of bounds for axis 0 with size 1

[plantplant]

作者你好，我的数据集里有多张图片，且图片尺寸是不一样的，有的尺寸是1551512，有的是1192512，以前使用darknet可以放在一起训练，将darknet的.cfg文件配置为“‘’”width=1280 height=512”。 使用tensorflow-yolov3训练时，报错：
=> Now it starts to train YOLOV3 from scratch ...
0%| | 0/2 [00:00<?, ?it/s]
Traceback (most recent call last):
File "train.py", line 184, in
if name == 'main': YoloTrain().train()
File "train.py", line 144, in train
for train_data in pbar:
File "D:\install\anaconda\envs\pycharm\lib\site-packages\tqdm\std.py", line 11
66, in iter
for obj in iterable:
File "F:\tensorflow-yolov3-master\core\dataset.py", line 82, in next
label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes, lbboxes = self.prep
rocess_true_boxes(bboxes)
File "F:\tensorflow-yolov3-master\core\dataset.py", line 224, in preprocess_tr
ue_boxes
onehot[bbox_class_ind] = 1.0
IndexError: index 5 is out of bounds for axis 0 with size 1
该怎么解决这个error？需要到哪里修改什么吗？