KAIWANG comments

Repositories
Issues
Comments

Results 3 comments of


                                            KAIWANG

mAP of s2anet under different batchsizes

For the same epoch, batch8 needs twice the number of iterations as batch16. Can this gap be directly bridged by linear increase or decrease of lr? `batchsize = samples_per_gpu *...

ERROR - tf2onnx.tfonnx: Failed to convert node 'Mean'

My Model: https://drive.google.com/file/d/1wnq9nCyOePdY7d4q3b3NJfcP4HIIREJ5/view?usp=sharing

Results are not good for dota dataset

Reference there: https://github.com/DetectionTeamUCAS/FPN_Tensorflow/issues/59. @WhiteSheep250