可以进行一般的test，但是多尺度test的时候就有问题，是不是模型出错了呢，希望作者能帮我看一下，感谢

[CPF-314127]

执行代码：python tools/test.py configs/ReDet/ReDet_re50_refpn_1x_dota15_ms.py work_dirs/ReDet_re50_refpn_1x_dota15_ms/ReDet_re50_refpn_1x_dota15_ms-9d1a523c.pth --out work_dirs/ReDet_re50_refpn_1x_dota15_ms/results.pkl

报错如下：File "tools/test.py", line 208, in main() File "tools/test.py", line 168, in main checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu') File "/home/anaconda3/envs/redet/lib/python3.7/site-packages/mmcv-0.2.13-py3.7-linux-x86_64.egg/mmcv/runner/checkpoint.py", line 172, in load_checkpoint checkpoint = torch.load(filename, map_location=map_location) File "/home/anaconda3/envs/redet/lib/python3.7/site-packages/torch/serialization.py", line 426, in load return _load(f, map_location, pickle_module, **pickle_load_args) File "/home/anaconda3/envs/redet/lib/python3.7/site-packages/torch/serialization.py", line 603, in _load magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: invalid load key, '?'.

[csuhan]

建议重新下载checkpoint