Open hungsing92 opened 6 years ago
@hungsing92 We set the batch size to 8 in training, and fine tune the model with 10^-3 learning rate for the first 120k iterations, then 10^-4 and 10^-5 for next two 30k iterations, respectively. We use SGD to optimize the training process where the weight decay is set to 0.0005, momentum is 0.9 and gamma is 0.1.
Hi,
想请问一下你训练时的weight_decay参数是多少? 我用weight_decay=0.0005 finetune做检测任务的时候, 网络很难收敛.
Best!