Odaimoko
Odaimoko
If You have a shell on you phone you can manage it. write a little manage script is acceptable for me.
Hi. I have applied transfter learning by first loading the pretrained COCO weights and then initialize the last layer of the net.
@meetdave06 I only changed code in pose_estimation/train.py. That `init_weight` method only serves to init from pretrained model from **resnet** but not from the author's provided ones. If you step into...
> Hi @HuAndrew , same question here. > > I am playing with this code recently and was also wondering about how did you generate the detection part. > >...
> I am also interested in evaluating the model on posetrack data. @nikhilaravi Actually I removed the last layer of author-provided COCO model. I added random initialized layer and the...
> > > I am also interested in evaluating the model on posetrack data. > > > > > > @nikhilaravi > > Actually I removed the last layer of...
> > > > > I am also interested in evaluating the model on posetrack data. > > > > > > > > > > > > @nikhilaravi >...
> @hetong007 Thanks for you excellent work. > > I am busy for another project, so when I am free I will consider to release the tracking part. By the...
谢谢！我的微信号和GitHub账号是一样的，可以加我好友哈。我也是在3H上的课。
Wiki10-31k can be sufficient. I am working on a project to investigate how sota extreme classification methods perform on tail labels. It would be nice not to train models again...