- We can use pre-trained models for general image classification
- Convolutional layers let us turn an image into a vector
- Dense layers use the vector to make the predictions
- Instead of training a model from scratch, we can use transfer learning and re-use already trained convolutional layers
- First, train a small model (150x150) before training a big one (299x299)
- Learning rate - how fast the model trains. Fast learner aren't always best ones
- We can save the best model using callbacks and checkpointing
- To avoid overfitting, use dropout and augmentation
Add notes from the video (PRs are welcome)
|
The notes are written by the community. If you see an error here, please create a PR with a fix. |