Deeper Networks for Image Classification: Performing and evaluating image classification tasks with deep CNN networks
Module Code: ECS795P
Module Leader: Shaogang Gong
Semester: 2
Submission Date: 12th May 2022
- You shall use at least two of VGG, ResNet, or GoogleNet networks. You can use more than two including other networks.
- You MUST use MNIST dataset for the image classification task. Moreover, we encourage you to use extra datasets (such as CIFAR, Tiny-Imagenet) to further evaluate your chosen networks.
- You shall submit a 6-page report (a research paper) including
- Critical analysis of the models;
- Implementation of model training and test settings, including the model training/testing process (the loss changing during training period, the train/test accuracy, etc.), to support your experimental results;
- Quantitative evaluation on your experimental results;
- Run-time screenshots.
- Report format: Please use the same LaTeX style as required for your MSc final project report (double-column, 11pt font size)
- You should submit (a) your code for model building, data loading & processing, training, evaluation, and visualisation; (b) evidence of model training and inference/test including text logs, tensorboard logs, run-time screenshots, any other logs demonstrating the training process with explicit timestamps recorded in a file/files (no need to submit the trained weights); (c) your six pages report.