-
Notifications
You must be signed in to change notification settings - Fork 383
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Training details about different sizes #27
Comments
my own training method: when end of training, copy the best saved weights file(.h5) to initials the training of size 384, modify cfg.train_task_id = '2T384' and cfg.initial_epoch="the ending epoch" and cfg.load_weights=True and continue train. then train 512 and so on. You could try this method, maybe there are better ways. |
@huoyijie whether the network still remembers what they learned in 256 while training 736? |
Hi, Epoch 00008: val_loss improved from 0.43569 to 0.42750, saving model to model/weights_3T256.008-0.427.h5 Epoch 00009: val_loss did not improve from 0.42750 Epoch 00010: val_loss did not improve from 0.42750 Epoch 00011: val_loss did not improve from 0.42750 Epoch 00012: val_loss did not improve from 0.42750 Epoch 00013: val_loss did not improve from 0.42750 |
@globalmaster it isn't error. The training is stopped early(early stopping) to avoid overfit. Looks like the model is not converging and this is still my problem. @globalmaster, Can you share for me dataset with google driver link? |
I am kinda confused the meaning of train respectively?
Does this mean to train the network in a coarse-to-fine process, which initals the network from 256x256 and then finetunes it on larger sizes?
Does this accelerate the converge of the network than train it on size 736x736 directly?
The text was updated successfully, but these errors were encountered: