search

Peterisfar / YOLOV3

yolov3 by pytorch
MIT License
195 stars 53 forks source link

Why do you set epoch >= 20 in train.py ? #23

Closed XiangqianMa closed 4 years ago

XiangqianMa commented 4 years ago 

            if epoch >= 20:
                print('*'*20+"Validate"+'*'*20)
                with torch.no_grad():
                    APs = Evaluator(self.yolov3).APs_voc()
                    for i in APs:
                        print("{} --> mAP : {}".format(i, APs[i]))
                        mAP += APs[i]
                    mAP = mAP / self.train_dataset.num_classes
                    print('mAP:%g'%(mAP))

            self.__save_model_weights(epoch, mAP)
            print('best mAP : %g' % (self.best_mAP))