search

Caleydo / confusionflow-ui

Visualize learning dynamics in multi-class image classifiers (e.g., convolutional neural networks) 💬 @gfrogat @thinkh
https://confusionflow.org
BSD 3-Clause "New" or "Revised" License
1 stars 0 forks source link

use case: transfer learning / finetuning #157

Open gfrogat opened 6 years ago

gfrogat commented 6 years ago

Most people don't train models from scratch but fine-tune a pretrained model instead.

The resulting dynamics of the model might therefore be different. On a different note: is not completely clear whether the observed oscillations are due to changes in the convnet filters or in the fully connected parts of the network

gfrogat commented 6 years ago

In this context it might be interesting to compare the learning / fine tuning of an image classifier on summer and winter images.

thinkh commented 6 years ago

We would need a dataset with summer and winter images for this use case.

gfrogat commented 6 years ago

we can illustrate similar effects by experimenting on different random folds, i.e. cross validation.