Planning.md

APTOS 2019 Blindness Detection - Planning

Working cycle:

1. Read competition information and relevant content to feel comfortable with the problem. Create a hypothesis based on the problem.
2. Initial data exploration to feel comfortable with the problem and the data.
3. Build the first implementation (baseline).
4. Loop through [Analyze -> Approach(model) -> Implement -> Evaluate].

1. Literature review (read some kernels and relevant content related to the competition).

• Relevant content:

  • Diabetic Retinopathy search on Papers with coded
  • Paper: Automated Detection of Diabetic Retinopathy using Deep Learning
  • Competition: Diabetic Retinopathy Detection
  • Competition: Histopathologic Cancer Detection

• Kernels:

  • Color transformation on images
  • APTOS Simple Preprocessing - Decoloring & Cropping
  • APTOS [updated] Albumentation meets Grad-CAM
  • process test images parallelly
  • APTOS Preprocessing

• Discussion:

  • Some Tips
  • Discrepancies between CV/LB
  • Public EfficientNet Keras Weights and Utility Script
  • Competition Metric
  • How far can 256x256 image size go?
  • Rethink image size

• Related datasets:

  • Diabetic Retinopathy (resized)
  • Diabetic Rateinopathy Resized
  • retinopathy_train_2015
  • Diabetic Retinopathy Detection