Got error when testing without "--cuda"

[LevineYang]

Hi Ouyang,

Great work! Now I've finished the training on Pascal VOC and begin to do the testing job. I got some questions here that 1) the snet_146 model can only run 90FPS+ on RTX2060; 2) when I test without "--cuda", errors pop up...

Any help is appreciated!

Shun

[Guzaiwang]

How much is your final snet_146 model on VOC_2007 ? I have trained the model for 2 hours and the model achieves a mean AP of 0.6082.

[DayBreak-u]

hi,levine! Your MAP is 0.81?That's impossible，Did you change anything？My result is only 0.62，It's still in the works！

[Guzaiwang]

hi,levine! Your MAP is 0.81?That's impossible，Did you change anything？My result is only 0.62，It's still in the works！

Me too~, my final MAP score is also 0.62.

[DayBreak-u]

yes！ I'm still working on the Data Augmentation

[Guzaiwang]

How much is your final snet_146 model on VOC_2007 ? I have trained the model for 2 hours and the model achieves a mean AP of 0.6082.

Well, Guzai, the final MAP is about 0.81. I trained the model using RTX2060 for 22 hours.

Hi, Levine. Could you show me more training details? Thx.

[LevineYang]

Sorry buddy, I found it impossible. After thinking about the whole training process, I found I made mistake when splitting dataset and there is overlap between training validation and testing. Sorry for this and can you help me with my issue @ouyanghuiyu

[AileenXie]

I have the same problem when I test without "--cuda". How can I run the test in cpu? @ouyanghuiyu

[Guzaiwang]

I have the same problem when I test without "--cuda". How can I run the test in cpu? @ouyanghuiyu How much is your final snet_146 model on VOC_2007 ?

[XinYangDong]

I ran the test in the CPU with the following error:

load checkpoint weights/snet_146/pascal_voc_0712/thundernet_epoch_6.pth load model successfully! load checkpoint weights/snet_146/pascal_voc_0712/thundernet_epoch_6.pth Loaded Photo: 0 images. /home/silence/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/functional.py:1351: UserWarning: nn.functional.sigmoid is deprecated. Use torch.sigmoid instead. warnings.warn("nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.") Traceback (most recent call last): File "demo.py", line 328, in rois_label = _RCNN(im_data, im_info, gt_boxes, num_boxes) File "/home/silence/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 541, in call result = self.forward(*input, **kwargs) File "/home/silence/cvdata/Thundernet_Pytorch-master/lib/model/faster_rcnn/faster_rcnn.py", line 126, in forward pooled_feat = self._roi_align_layer(base_feat, rois.view(-1, 5)) File "/home/silence/cvdata/Thundernet_Pytorch-master/lib/model/faster_rcnn/faster_rcnn.py", line 68, in _roi_align_layer return self.psroiAlign.forward(bottom, rois) File "/home/silence/cvdata/Thundernet_Pytorch-master/lib/psroialign/psroialign.py", line 19, in forward pooled_feat = self.psroialign(feat, rois) File "/home/silence/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 541, in call result = self.forward(*input, **kwargs) File "/home/silence/cvdata/Thundernet_Pytorch-master/lib/psroialign/PSROIAlign/model/roi_layers/ps_roi_align.py", line 77, in forward self.pooled_dim # 10 File "/home/silence/cvdata/Thundernet_Pytorch-master/lib/psroialign/PSROIAlign/model/roi_layers/ps_roi_align.py", line 33, in forward raise NotImplementedError NotImplementedError