CS231n: Deep Learning for Computer Vision

This project includes various assignments and projects that are part of the Stanford CS231n: Deep Learning for Computer Vision course [1]. The initial code is from CS231n assignments [2]. Each folder corresponds to a different assignment within the course.

Note

This was solved as a project for a course called Computer Vision at Politehnica University of Timisoara [3]. Because of that, the cs231n folder inside each assignment was renamed to cv. Also, it was run in Google Colaboratory and I chose to complete the PyTorch files (instead of Tensorflow).

Content

Assignment 1

• Q1: k-Nearest Neighbor classifier - knn.ipynb
• Q2: Training a Support Vector Machine - svm.ipynb
• Q3: Implement a Softmax classifier - softmax.ipynb
• Q4: Two-Layer Neural Network - two_layer_net.ipynb
• Q5: Higher Level Representations: Image Features - features.ipynb

Assignment 2

• Q1: Fully-connected Neural Network - FullyConnectedNets.ipynb
• Q2: Batch Normalization - BatchNormalization.ipynb
• Q3: Dropout - Dropout.ipynb
• Q4: Convolutional Networks - ConvolutionalNetworks.ipynb
• Q5: PyTorch / TensorFlow on CIFAR-10 - PyTorch.ipynb

Assignment 3

• Q1: Image Captioning with Vanilla RNNs - RNN_Captioning.ipynb
• Q2: Image Captioning with LSTMs - LSTM_Captioning.ipynb
• Q3: Network Visualization: Saliency maps, Class Visualization, and Fooling Images - NetworkVisualization-TensorFlow.ipynb
• Q4: Style Transfer - StyleTransfer-TensorFlow.ipynb
• Q5: Generative Adversarial Networks - Generative_Adversarial_Networks_PyTorch.ipynb

Reference list

1. CS231n course page. https://cs231n.stanford.edu/
2. CS231n assignments. https://cs231n.stanford.edu/assignments.html
3. Computer Vision Course, Dr. Eng. Cosmin CERNAZANU-GLAVAN, 2024