Chenfeng Liu comments

Results 8 comments of


                                            Chenfeng Liu

trafficstars

Error on installing: pip install horovod[pytorch] in Virtualbox ubuntu 18.04

have any solution ?

error when train by myself with "./experiments/scripts/train_faster_rcnn.sh 0 pascal_voc res101"

> @zwbdmm Sorry, I mean I have the same issue when I am using the latest tensorboardX. But tensorflowboard==1.2 solves the problem. Thanks, it works for me ! Just change...

The optflow results of Pretrained weights is all zeros

> I have the same questions as llltttppp said,even when i used the pretrained flownet model to train my own data,the flow result turns out to be all zeros. >...

The optflow results of Pretrained weights is all zeros

> > > I have the same questions as llltttppp said,even when i used the pretrained flownet model to train my own data,the flow result turns out to be all...

The optflow results of Pretrained weights is all zeros

> > > > > I have the same questions as llltttppp said,even when i used the pretrained flownet model to train my own data,the flow result turns out to...

The optflow results of Pretrained weights is all zeros

> I have the same questions as llltttppp said,even when i used the pretrained flownet model to train my own data,the flow result turns out to be all zeros. >...

Command terminated by signal 11

I met the same error, nor is it an error caused by limit of memory problems. Did anyone solve this problem ?

Custom Dataset Evaluation either 0.0 or nan

> I believe that the problem is that I did not include any marking for 'difficult' in my annotations. I think I need to change the customdataset_eval.py function to no...