search

hezhangsprinter / DCPDN

Densely Connected Pyramid Dehazing Network (CVPR'2018)
405 stars 112 forks source link

Do Testing and Training (Fine-tuning) use the same model? #43

Open angleboy8 opened 5 years ago

angleboy8 commented 5 years ago

1.Training (Fine-tuning) python train.py --dataroot ./facades/train512 --valDataroot ./facades/test512 --exp ./checkpoints_new --netG ./demo_model/netG_epoch_8.pth

2.Testing python demo.py --dataroot ./your_dataroot --valDataroot ./your_dataroot --netG ./pre_trained/netG_epoch_9.pth

Hi, Phd Zhang. I want to test your program,but there is no "netG_epoch_9.pth" model. In your github website, it only provides "netG_epoch_8.pth" model in google cloud. Please how to get "netG_epoch_9.pth"? Thank you for your help.

sunxiangs commented 5 years ago

because you did not training ! after you train the model,you will find many new net model like netG_epoch_9.pth........netG_epoch_300.pth....，you just need choose the best of them.

hust-kevin commented 5 years ago

if epoch 8 can achive good result, why need train 400 epoch?

what's more, the code is really dirty, not clearly at all