First of all, Do you have?:
[ ] Initial Test set
[ ] A single metric to improve
[ ] Target performance based on baseline
Choose a simple architecture
Use sensible defaults
Normalize inputs
Simplify the problem
Get your model to run ➡️ ****
Overfit a single batch ➡️
Compare to a known result
Build Unit Tests for:
# Recommended for debugging
import ipdb; ipdb.set_trace()
<aside> 💡 Lightweight implementation. Use of the shell components. Build complicated data pipelines later.
</aside>