I have two trainings one after another.
First training:
config.yaml contains:
Second training starts from first training pretrained_ckpt.
config.yaml contains:
epoch_learning_rate tensorboard plot:
I didn't specify lr_decay_method in both trainigns so it was 'cosine' by default.
Question:
How to setup 'cosine' learning rate schedule so that training would start with the learning_rate value at the top of cosine wave and deacrease to 0 at the end of training?
In the same way as
learning_rate: {
cosine_decay_learning_rate {
learning_rate_base: 0.005
total_steps: 115200
warmup_learning_rate: 0.0
warmup_steps: 5000
}
}
Version automl/efficientdet/keras/ tag: 1.2
I have two trainings one after another. First training:
config.yaml contains:
Second training starts from first training pretrained_ckpt.
config.yaml contains:
epoch_learning_rate tensorboard plot:
I didn't specify lr_decay_method in both trainigns so it was 'cosine' by default.
Question:
How to setup 'cosine' learning rate schedule so that training would start with the learning_rate value at the top of cosine wave and deacrease to 0 at the end of training? In the same way as learning_rate: { cosine_decay_learning_rate { learning_rate_base: 0.005 total_steps: 115200 warmup_learning_rate: 0.0 warmup_steps: 5000 } }
from TensorFlow Object Detection API does.