search

ascust / SEC-MXNet

MXNet implementation of SEC
MIT License
21 stars 4 forks source link

train resnet50 miou became lower #17

Closed 14281057 closed 4 years ago

14281057 commented 4 years ago

first i follow the readme training voc for vgg16, val miou = 0.5005 , result is ok. then i training voc for resnet50 ,i only change the core.config.py file params for these : conf.BASE_NET = "resnet50", conf.LOG_FOLDER = "log_resnet50" conf.SNAPSHOT_FOLDER = "snapshots_resnet50" conf.OUTPUT_FOLDER = "outputs_resnet50" val miou = 0.4883, result even became lower than vgg16, i did not know why? hope you can help me! there are some final loss for vgg16 resnet50 log, first is vgg16,second is resnet50 //train_bg_cue_net.log Train-MultiLogisticLoss= 0.008143 0.027573 //train_fg_cue_net.log Train-MultiLogisticLoss= 0.057217 0.065230 //train_sec_model.log final loss Train-SEC_seed_loss=0.246602 0.336656 Train-SEC_constrain_loss=0.226370 0.324345 Train-SEC_expand_loss=0.861525 0.847647

14281057 commented 4 years ago

i solve this for add --savemask --crf --flip . the final result val miou = 0.5526