Part 1, online study group

[msivanes (Manikandan Sivanesan)]

Meeting Minutes (14/12/2019)

• Participants shared & discussed their Kaggle Kernel submission for Kannada MNIST competition along with Q&A
• Discussion about lesson 1-pets

Advice

• Make it work and try to make the first submission before shooting for higher scores.
• Optimize for iterating faster so that you can test your ideas quickly.

Common mistakes to avoid for Kannada MNIST

Databunch creation

• Not setting the batch size
• Not setting the normalize part to imagenet_stats when you are using pretrained model
• Not setting the random seed

Model

• Start with the simplest model like restnet18, resnet34 if you are using pretrained models before trying with larger models.

Evaluation

• learn.recorder.plot(suggestion=True) after learn.lr_find for setting the learning rate.
• Train a bit longer (increase the epochs) if the training loss is much higher than the validation loss

Resources

• Introduction to Image Augmentation(Credit: @init_27 ) - Link
• DF to Custom Image List. Borrowed from AlexKCT (Shared by @shahnoza) Link
• Concise lecture notes: Lesson 1 & Lesson 2
• Jovian for code review & feedback jovian.ml