My solutions to assignments of CS231n: Convolutional Neural Networks for Visual Recognition course.

Thanks to people at Stanford for making all the course resources available online. There are lot of repos already with the solutions but very few are there with PyTorch 0.4 and I hope this will be helpful. I have filled in the inline questions at all places to the best of my knowledge. If there are any mistakes anywhere please let me know, thanks.

• Q1: k-Nearest Neighbor classifier. (Done)
• Q2: Training a Support Vector Machine. (Done)
• Q3: Implement a Softmax classifier. (Done)
• Q4: Two-Layer Neural Network. (Done)

• Q1: Fully-connected Neural Network. (Done)
• Q2: Batch Normalization. (Done)
• Q3: Dropout. (Done)
• Q4: Convolutional Networks. (Done)
• Q5: PyTorch / TensorFlow on CIFAR-10. (Done in Pytorch0.4)

• Q1: Image Captioning with Vanilla RNNs. (Done)
• Q2: Image Captioning with LSTMs. (Done)
• Q3: Network Visualization: Saliency maps, Class Visualization, and Fooling Images. (Done in Pytorch0.4)
• Q4: Style Transfer. (Done in Pytorch0.4)
• Q5: Generative Adversarial Networks. (Done in Pytorch0.4)