BIGWangYuDong
commented
1 year ago FAQ have some solutions: https://github.com/open-mmlab/mmdetection/blob/master/docs/en/faq.md#training
Closed evaniajoycelin closed 1 year ago
BIGWangYuDong
commented
1 year ago FAQ have some solutions: https://github.com/open-mmlab/mmdetection/blob/master/docs/en/faq.md#training
Vishalkagade
commented
7 months ago param_scheduler = [
dict(
type='LinearLR', # Use linear policy to warmup learning rate
start_factor=0.001, # The ratio of the starting learning rate used for warmup
by_epoch=False, # The warmup learning rate is updated by iteration
begin=0, # Start from the first iteration
end=1000), # End the warmup at the 500th iteration
# The main LRScheduler
dict(
type='MultiStepLR', # Use multi-step learning rate policy during training
by_epoch=True, # The learning rate is updated by epoch
begin=0, # Start from the first epoch
end=12, # End at the 12th epoch
milestones=[8, 11], # Epochs to decay the learning rate
gamma=0.1) # The learning rate decay ratio] In learning rate scheduler,go into Linear learning rate warm-up scheduler, and change warm-up iteration to 1200. i.e. param_scheduler = [
dict(
type='LinearLR', # Use linear policy to warmup learning rate
start_factor=0.001, # The ratio of the starting learning rate used for warmup
by_epoch=False, # The warmup learning rate is updated by iteration
begin=0, # Start from the first iteration
end=1200), # End the warmup at the 500th iteration
Error when training SSD300 with customize dataset. Am I missing something?