python3 eval.py Error:NotImplementedError

[mhliao]

python3 eval.py Error:NotImplementedError

[MhLiao]

@pomelo93 Have you followed the Readme document?

[MhLiao]

@pomelo93 You should not use python3 eval.py without passing a config file. Please see the specific parameters of this command

[pomelo93]

@MhLiao Sorry, I simplify my description. I ran python3 eval.py experiments/seg_detector/totaltext_resnet18_deform_thre.yaml --resume models/totaltext_resnet18 --polygon --box_thresh 0.6. And it told me NotImplementedError. Here is the releated error information.Thanks!
./datasets/total_text/ [INFO] [2019-12-09 14:32:07,396] Resuming from models/totaltext_resnet18 [INFO] [2019-12-09 14:32:07,429] Resumed from models/totaltext_resnet18 0%| | 0/300 [00:00<?, ?it/s] Traceback (most recent call last): File "eval.py", line 193, in <module> main() File "eval.py", line 79, in main Eval(experiment, experiment_args, cmd=args, verbose=args['verbose']).eval(args['visualize']) File "eval.py", line 176, in eval pred = model.forward(batch, training=False) File "/media/zdyd/data/swf/Github/DB/structure/model.py", line 56, in forward pred = self.model(data, training=self.training) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in __call__ result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.6/dist-packages/torch/nn/parallel/data_parallel.py", line 140, in forward return self.module(*inputs, **kwargs) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in __call__ result = self.forward(*input, **kwargs) File "/media/zdyd/data/swf/Github/DB/structure/model.py", line 19, in forward return self.decoder(self.backbone(data), *args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in __call__ result = self.forward(*input, **kwargs) File "/media/zdyd/data/swf/Github/DB/backbones/resnet.py", line 240, in forward x3 = self.layer2(x2) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in __call__ result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/container.py", line 92, in forward input = module(input) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in __call__ result = self.forward(*input, **kwargs) File "/media/zdyd/data/swf/Github/DB/backbones/resnet.py", line 88, in forward out = self.conv2(out, offset, mask) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in __call__ result = self.forward(*input, **kwargs) File "/media/zdyd/data/swf/Github/DB/assets/ops/dcn/modules/deform_conv.py", line 128, in forward self.groups, self.deformable_groups) File "/media/zdyd/data/swf/Github/DB/assets/ops/dcn/functions/deform_conv.py", line 131, in forward raise NotImplementedError NotImplementedError

[MhLiao]

@pomelo93 As indicated in DB/assets/ops/dcn/functions/deform_conv.py", line 131, the DCN is not implemented with the CPU mode. Thus, you must use GPU to run the model currently. Otherwise, you should remove the DCN in the model.