BruceWang issues

Repositories
Issues
Comments

Results 1 issues of


                                            BruceWang

The loss on COCO dataset of training stage1 dosen't decrease

Hi, I run the train_coco_word2_1_pool.m, but after more than 10 epochs, I found the train result is still bad(as below). I didn't change any hyper parameters but I don't know...