The initialization in clr.py is:
def __init__(self, num_samples, batch_size, max_lr, end_percentage=0.1, scale_percentage=None, maximum_momentum=0.95, minimum_momentum=0.85, verbose=True)
The initialization in the documentation is:
lr_manager = OneCycleLR(num_samples, num_epoch, batch_size, max_lr end_percentage=0.1, scale_percentage=None, maximum_momentum=0.95, minimum_momentum=0.85)
This causes unexpected behaviour in the function compute_lr.
The initialization in clr.py is:
def __init__(self, num_samples, batch_size, max_lr, end_percentage=0.1, scale_percentage=None, maximum_momentum=0.95, minimum_momentum=0.85, verbose=True)The initialization in the documentation is:
lr_manager = OneCycleLR(num_samples, num_epoch, batch_size, max_lr end_percentage=0.1, scale_percentage=None, maximum_momentum=0.95, minimum_momentum=0.85)This causes unexpected behaviour in the function compute_lr.