ssds.pytorch These nets support only GPU mode？？

Mar 27 '18 03:03 VisionZQ

Currently, it checks whether the gpu can be detected, so it should be work for cpu model. But we still do not have time to test it.

Mar 27 '18 03:03 foreverYoungGitHub

I'll test it in this week and make sure this repo can be work fine for the cpu model.

Mar 27 '18 03:03 foreverYoungGitHub

Thank you very much.

Mar 27 '18 04:03 VisionZQ

Hi, Some nets can work fine for gpu mode, but others not, such as 'fssd_lite_mobilenetv2_train_voc.yml' . because the code 'x = torch.autograd.Variable(x, volatile=True).cuda()' in model_builder.py if I modify the code for cpu mode , the error 'Fan in and fan out can not be computed for tensor with less than 2 dimensions' in ssds_train.py", line 189, in initialize getattr(self.model, module).apply(self.weights_init) happened。

Mar 27 '18 08:03 VisionZQ

Do you mean fssd_lite_mobilenetv2_train_voc.yaml has problem in cpu model rather than gpu model?

Yes, that part is used to infer the featuremap size. Let me try whether it could work fine in cpu model.

Mar 27 '18 16:03 foreverYoungGitHub

I just commit a update for cpu model in infer. I test it by running sh time_benchmark.sh. This script can test the speed in cpu model and gpu model.

It seems that all the model is ok, I'll keep this issue open. Please let me know if you have any questions.

Mar 27 '18 17:03 foreverYoungGitHub

Thanks a lot for you kindness and efforts.. I do the same work by run 'sh time_benchmark.sh',all is ok. But , the error happened again when I running 'python train --cfg=./experiments/cfgs/fssd_lite_mobilenetv2_train_voc.yml ' . The error reminder 'Fan in and fan out can not be computed for tensor with less than 2 dimensions ' , it seems that error occur in /lib/ssds_train.py ,in initialize getattr(self.model, module).apply(self.weights_init)

Mar 28 '18 01:03 VisionZQ

OK, thanks for that, I'll take a look for that in this week.

Mar 28 '18 14:03 foreverYoungGitHub

It's weird, I do not meet this problem neither in gpu nor cpu model. Could you share you error?

Mar 29 '18 17:03 foreverYoungGitHub

ok..firstly, I don't have COCO datasets, VOC datasets is available for me.. Step1. I run 'python train.py --cfg=./experiments/cfgs/fssd_lite_mobilenetv2_train_voc.yml '
No module named 'lib.utils.pycocotools._mask' qq20180330-090906 2x So, I shield some code in dataset_factory.py wx20180330-151307 2x Then ,run 'python train.py --cfg=./experiments/cfgs/fssd_lite_mobilenetv2_train_voc.yml '