The loss plateaus after 100 Epoch

BichenWuUCB / squeezeDet

A tensorflow implementation for SqueezeDet, a convolutional neural network for object detection.

BSD 2-Clause "Simplified" License

739 stars 306 forks source link

The loss plateaus after 100 Epoch #147

Open ROZBEH opened 2 years ago

ROZBEH commented 2 years ago

Hi there,

Using the original setting the loss starts at about 33 but plateaus at about 3.0. Any recommendations? I'm curious what's the ultimate loss that you get after 100 epochs.

Thank you.