Skip to content

Instantly share code, notes, and snippets.

@Diyago

Diyago/training.py

Created August 11, 2019 10:39
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save Diyago/efe84b0d68efac1aed23be11ecb42b04 to your computer and use it in GitHub Desktop.
Save Diyago/efe84b0d68efac1aed23be11ecb42b04 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
training.py
model = Unet(backbone_name = 'efficientnetb0', encoder_weights='imagenet', encoder_freeze = False)
model.compile(optimizer = Adam(), loss=bce_jaccard_loss, metrics=[iou_score])
history = model.fit_generator(train_generator, shuffle =True,
epochs=50, workers=4, use_multiprocessing=True,
validation_data = test_generator,
verbose = 1, callbacks=callbacks)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment