This is the repository for the group 4 for the seminar of Deep Learning for Computer Vision in ETSETB:

https://github.com/imatge-upc/telecombcn-2016-dlcv/

And the group is formed by:

Manel Baradad, Míriam Bellver, Martí Cervià, Hector Esteban, Carlos Roig

The slides of the project can be seen here:

https://docs.google.com/presentation/d/1daS4M7e5Grk6Ytqk2kdapNonDVCPKwiv5HxscIA8UQI/edit?usp=sharing

We have performed 5 different tasks, described in the following lines:

TASK 1: ARCHITECTURE

1. Build network for classification problem
2. Study memory requirements and computational loads for different layers

Main idea: use MNIST and start with small network, test different layers and architectures

TASK 2: TRAINING

1. Study impact in performance of DATA AUGMENTATION, batches size, batch normalization
2. Training validation curves
3. Overfitting

TASK 3: VISUALIZATION

1. Visualize filter responses from own and also pretrained net
2. t-SNE
3. Off-the-shelf AlexNet

TASK 4: TRANSFER LEARNING

1. Train network on CIFAR10 and fine-tune for Terrassa Buildings 900
2. Off-the-shelf convnet

TASK 5: OPEN PROJECT

1. We have played with neural style, changing the features that encode the style and see the results.

DATASETS:

We have worked with three different Datasets:

MNIST CIFAR10 Terrassa-building-900 (https://imatge.upc.edu/web/resources/terrassa-buildings-900)