Closed rytisss closed 5 years ago
Hi, glad that the implementation is helping you. As for your questions:
Thank you for answers :)
I have noticed that when i have increased feature_root to 32, network trains more evenly, i mean in every epoch you can see on training batch prediction that feature comes more strong.
In general, it does all the work nicely!
Hi, thank you for UNet implementation. I have tried it and it trained quite well. I am writing regards of my results. There is few of my result: epoch_1 epoch_2 epoch_3 epoch_4 epoch_5 epoch_6 epoch_7 epoch_8 epoch_9 epoch_10
I have ~1200 image with defects of one class that i want to recognize. For the training (the picture with prediction of epochs are seen above) i used UNet with 4 layers and feature_root=16. Kept my minibatch at 2 and training_iters=600 to cover all dataset at single epoch.
P.S. I implemented fix mentioned in #228 in code that i used