RetinaNet.ipynb，训练模型这一步报错了

[toolgood]

日志如下

2020-12-15 22:49:44.533073: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cudart64_101.dll
Traceback (most recent call last):
File "keras-retinanet/keras_retinanet/bin/train.py", line 34, in
from .. import layers # noqa: F401
File "keras-retinanet/keras_retinanet/bin....\keras_retinanet\layers_init_.py", line 1, in
from ._misc import RegressBoxes, UpsampleLike, Anchors, ClipBoxes # noqa: F401
File "keras-retinanet/keras_retinanet/bin....\keras_retinanet\layers_misc.py", line 20, in
from ..utils import anchors as utils_anchors
File "keras-retinanet/keras_retinanet/bin....\keras_retinanet\utils\anchors.py", line 20, in
from ..utils.compute_overlap import compute_overlap
ImportError: DLL load failed while importing compute_overlap: 参数错误。

[KungWanyi]

请问你现在解决了么？我也遇到了这个问题，最后提示升级Tensorflow到2.2.3，升级后提示train_data.csv的字段有问题

Traceback (most recent call last):
File "keras-retinanet/keras_retinanet/bin/train.py", line 553, in
main()
File "keras-retinanet/keras_retinanet/bin/train.py", line 483, in main
train_generator, validation_generator = create_generators(args, backbone.preprocess_image)
File "keras-retinanet/keras_retinanet/bin/train.py", line 303, in create_generators
**common_args
File "keras-retinanet/keras_retinanet/bin/../../keras_retinanet/preprocessing/csv_generator.py", line 158, in init
raise_from(ValueError('invalid CSV annotations file: {}: {}'.format(csv_data_file, e)), None)
File "", line 3, in raise_from
ValueError: invalid CSV annotations file: data/baijiu/train_data.csv: line 1: unknown class name: 'box' (classes: OrderedDict([('\ufeffbox', 0), ('others', 1), ('bottle', 2), ('jar', 3), ('bag', 4), ('bucket', 5)]))

[nacayu]

我也遇到这个问题了