OliverGrace / Deep-Learning-Computer-Vision

Personal implementation for Stanford CS231n / Umich: Deep Learning for Computer Vision (by Justin Johnson)

1. PyTorch & KNN

The goals of this assignment are as follows:

• Develop proficiency with PyTorch tensors
• Gain experience using notebooks on Google Colab
• Understand the basic Image Classification pipeline and the data-driven approach (train/predict stages)
• Understand the train/val/test splits and the use of validation data for hyperparameter tuning
• Implement and apply a k-Nearest Neighbor (kNN) classifier

Notebooks:

pytorch101.ipynb

kNN.ipynb

2. SVM & Neural Network

The goals of this assignment are as follows:

• Implement and apply a Multiclass Support Vector Machine (SVM) classifier
• Implement and apply a Two layer neural network classifier
• Understand the differences and tradeoffs between these classifiers
• Practice implementing vectorized gradient code by checking against naive implementations, and using numeric gradient checking

Notebooks:

linear_classifier.ipynb

two_layer_net.ipynb

3. Backpropagation & BN &Dropout

The goals of this assignment are as follows:

• Understand Neural Networks and how they are arranged in layered architectures
• Understand and be able to implement modular backpropagation
• Implement various update rules used to optimize Neural Networks
• Implement Batch Normalization for training deep networks
• Implement Dropout to regularize networks
• Understand the architecture of Convolutional Neural Networks and get practice with training these models on data

Notebooks:

fully_connected_networks.ipynb

convolutional_networks.ipynb

4. PyTorch Modules & RNN & Image Captioning & Attention & Style Transfer

The goals of this assignment are:

• Understand how autograd can help automate gradient computation
• See how to use PyTorch Modules to build up complex neural network architectures
• Understand and implement recurrent neural networks
• See how recurrent neural networks can be used for image captioning
• Understand how to augment recurrent neural networks with attention
• Use image gradients to synthesize saliency maps, adversarial examples, and perform class visualizations
• Combine content and style losses to perform artistic style transfer

Notebooks:

pytorch_autograd_and_nn.ipynb

rnn_lstm_attention_captioning.ipynb

network_visualization.ipynb

style_transfer.ipynb

5. Single/Two Stage Object Detection

The goals of this assignment are:

• Learn about the object detection pipeline
• Understand how to build an anchor-based single-stage object detectors
• Understand how to build a two-stage object detector that combines a region proposal network with a recognition network

Notebooks:

single_stage_detector_yolo.ipynb

two_stage_detector_faster_rcnn.ipynb

6. Generative Adversarial Networks (GANs)

The goals of this assignment are:

• Understand Generative Adversarial Networks (GANs)
• Implement Vanila GAN, LS-GAN, DC-GAN

Notebooks:

generative_adversarial_networks.ipynb

Reference:

EECS 498-007 / 598-005 Deep Learning for Computer Vision Fall 2019