search

GXYM / TextBPN-Plus-Plus

Arbitrary Shape Text Detection via Boundary Transformer；The paper at: https://arxiv.org/abs/2205.05320, which has been accepted by IEEE Transactions on Multimedia (T-MM 2023).
177 stars 38 forks source link

python demo.py --net resnet18 --scale 2 --exp_name Totaltext --checkepoch 570 --test_size 640 960 --dis_threshold 0.35 --cls_threshold 0.9 --gpu 0 --img_root E:\TextBPN-Plus-Plus-main\data\T otal-Text\Images\Test #40

Open rebornone1 opened 5 months ago

rebornone1 commented 5 months ago

当我输入python demo.py --net resnet18 --scale 2 --exp_name Totaltext --checkepoch 570 --test_size 640 960 --dis_threshold 0.35 --cls_threshold 0.9 --gpu 0 --img_root E:\TextBPN-Plus-Plus-main\data\T otal-Text\Images\Test 出现报错Traceback (most recent call last): self.load_state_dict(state_dict['model'], strict=(not self.is_training)) File "D:\Anaconda3\envs\TextBPN++\lib\site-packages\torch\nn\modules\module.py", line 1224, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for TextNet: Missing key(s) in state_dict: "fpn.merge2.deconv.weight", "fpn.merge2.deconv.bias". 谢谢

lyysl commented 2 months ago

I have a similar problem using the trained model from the github. But it runs when using the pretrained model. Did you train your model or use the trained model?