Register
Login
Resources
Docs Blog Datasets Glossary Case Studies Tutorials & Webinars
Product
Data Engine LLMs Platform Enterprise
Pricing Explore
Connect to our Discord channel

protocol.md 1.4 KB

You have to be logged in to leave a comment. Sign In

Training Protocol

Model

The main segmentation model is an EfficientUnet++ with a EfficientNet-b5 encoder.

Losses

The model was trained using a combination of three losses and a loss weighting scheme.L_{total} = L_{dice} + \alpha * L_{boundary} + L_{focal}

and ɑ (ramped on over the first 100 epochs) is defined as:\alpha = min(0.01*epoch, 0.99)

Generaliced Dice Loss

...

Boundary loss

...

Focal Loss

...

Training

The following pytorch lightning settings and training tricks were used:

  • batch_size: 32
  • ADAM optimizer with learning_rate of 0.0003 (altered using CosineAnnealingLR with T_max=10)
  • mixed precision training
  • gradient clipping enabled (mode: norm, 0.5)
  • stochastic weight averaging

Data

  • Data samples of size 4x256x256 (CxWxH; channels: R,G,B,NIR), normalized
  • Data augmentation:- HorizontalFlip or VerticalFlip, p=0.5- RandomRotate90, p=0.5- RandomBrightnessContrast, brightness_limit=0.2, contrast_limit=0.15, brightness_by_max=False- Normalize
  • Normalization: 4-channel mean/ std for all data from 2017-2020
Tip!

Press p or to see the previous file or, n or to see the next file

Comments

Loading...