HanYuanyuaner comments

Repositories
Issues
Comments

Results 2 comments of


                                            HanYuanyuaner

Did any one use 2017 coco dataset to run this model successful?

I solve this problem, add "img_url = imgs[i][1]['coco_url']" and change "split = img_name.split('_')[1]" to "split = img_url.split('/')[3]"

nan output

I am sorry, the output is like this epoch: 1/100, train_loss: nan, train_acc: 0.1018, test_loss: nan, test_acc: 0.1000 epoch: 1/100, train_loss: nan, train_acc: 0.0023, test_loss: nan, test_acc: 0.1000 epoch: 1/100,...