Repository for programming assignments of CS231n: Convolutional Neural Networks for Visual Recognition (2016 & 2017).

• Q1: k-Nearest Neighbor classifier (20 points)
• Q2: Training a Support Vector Machine (25 points)
• Q3: Implement a Softmax classifier (20 points)
• Q4: Two-Layer Neural Network (25 points)
• Q5: Higher Level Representations: Image Features (10 points)
• Q6: Cool Bonus: Do something extra! (+10 points) - Not done

• Q1: Fully-connected Neural Network (25 points)
• Q2: Batch Normalization (25 points)
• Q3: Dropout (10 points)
• Q4: Convolutional Networks (30 points)
• Q5: PyTorch / TensorFlow on CIFAR-10 (10 points) - Done both in Pytorch and Tensorflow
• Q6: Do something extra! (up to +10 points) - Done both in Pytorch and Tensorflow
  • Extra Credit: VGG-like networks which acheive 79.4% and 78.4% on CIFAR-10 test set in Pytorch and Tensorflow respectively

• Q1: Image Captioning with Vanilla RNNs (25 points)
• Q2: Image Captioning with LSTMs (30 points)
• Q3: Network Visualization: Saliency maps, Class Visualization, and Fooling Images (15 points) - Done both in Pytorch and Tensorflow
• Q4: Style Transfer (15 points) - Done both in Pytorch and Tensorflow
• Q5: Generative Adversarial Networks (15 points) - Done both in Pytorch and Tensorflow
  • Extra Credit: InfoGAN (TF), WGAN-GP (TF), WGAN-GP (Pytorch)

• Q1: k-Nearest Neighbor classifier (20 points)
• Q2: Training a Support Vector Machine (25 points)
• Q3: Implement a Softmax classifier (20 points)
• Q4: Two-Layer Neural Network (25 points)
• Q5: Higher Level Representations: Image Features (10 points)
• Q6: Cool Bonus: Do something extra! (+10 points) - Not done

• Q1: Fully-connected Neural Network (30 points)
• Q2: Batch Normalization (30 points)
• Q3: Dropout (10 points)
• Q4: ConvNet on CIFAR-10 (30 points)
• Q5: Do something extra! (up to +10 points) - Built a CNN network which acheives 73.5% on CIFAR-10 test set

• Q1: Image Captioning with Vanilla RNNs (40 points)
• Q2: Image Captioning with LSTMs (35 points)
• Q3: Image Gradients: Saliency maps and Fooling Images (10 points)
• Q4: Image Generation: Classes, Inversion, DeepDream (15 points)
• Q5: Do something extra! (up to +10 points) - Not done

• Course Home
• Syllabus
• Lecture Note