DBNet eval.py 运行

DBNet eval.py:
运行的时候：TypeError: forward() missing 1 required positional argument: ‘data’

Solution:
changed model.py(line:56) to
if self.training:
pred = self.model(data, training=self.training)
else:
pred = self.model(data)

docker run --gpus all -v /..... -w /.....  dbnet:v2 python eval.py experiments/seg_detector/td500_resnet50_deform_thre.yaml --resume models/td500_resnet50 --box_thresh 0.5

Downloading: “https://download.pytorch.org/models/resnet50-19c8e357.pth” to /root/.cache/torch/checkpoints/resnet50-19c8e357.pth
100%|██████████| 97.8M/97.8M [00:23<00:00, 4.34MB/s]
[INFO] [2020-05-12 06:05:31,983] Resuming from models/td500_resnet50
[INFO] [2020-05-12 06:05:32,257] Resumed from models/td500_resnet50
100%|██████████| 200/200 [00:40<00:00, 4.90it/s]
[INFO] [2020-05-12 06:06:13,116] precision : 0.910853 (200)
[INFO] [2020-05-12 06:06:13,117] recall : 0.807560 (200)
[INFO] [2020-05-12 06:06:13,117] fmeasure : 0.856102 (1)
./datasets/TD_TR/TD500/