Collection of my work related to deep learning in a single place.
https://kushajveersingh.github.io/blog/
-
- what_can_neural_networks_reason_about - Implementation of paper What can Neural Networks Reason About. Check my blog post for the paper summary. Results from one of the experiments presented in the paper are reproduced. twitter-card
-
- Semi-supervised parking lot detection -> My submission for Techgig Code Gladiators 2019 AI theme competition that won 1st place at the final.
- Waste Seggregation using trashnet -> Contains the code to train models for trashnet and then export them using ONNX. It was part of a bigger project where we ran these models on Rasberry Pi, which controlled wooden planks to classify the waste into different categories (code for rasberry pi not included here).
- Human 3D Reconstruction -> Uses Insetgan and Pifuhd models to generate 3D full body images of people.
-
- Photorealistic Style Transfer - Implementation of High Resolution Network for Photorealistic Style Transfer
- SPADE-PyTorch - Implementation of Semantic Image Synthesis with Spatially-Adaptive Normalization (SPADE)
- Weight Standardization - Implementation of Weight Standardization. Tested using cyclic learning.
- Training AlexNet with tips and checks on how to train CNNs - A PyTorch tutorial on how to create an image classifier.
- Study of Mish activation function in transfer learning with code and discussion - Implementation of Mish: A Self Regularized Non-Monotonic Neural Activation Function.
- Number of bins of a Histogram - Notebook discussing three techniques of choosing the bin size in histograms.
- Multi Sample Dropout - Implementation of Multi-Sample Dropout for Accelerated Training and Better Generalization.
- Data Augmentation in Computer Vision - Notebook implementing single image data augmentation techniques using just Python.
- How to deal with outlier - Notebook discussing ways to deal with outliers.
- Leslie N. Smith papers notebook - Jupyter notebook discussing cyclic learning and ways by which we can choose hyperparameter values by looking at valid loss graph.
-
notes - My notes when learning some things.
-
random - Random scripts and os setup instructions.
- os_setup_instructions - My setup guide for Windows 10 and Ubuntu 20.04 (needs to be updated a bit).
- cifar10_data_script.py - To convert CIFAR10 data to numpy array
- save_torchvision_models_to_disk -> a quick script to download all pytorch models
- unscramble_android_game -> Python script to solve the unscramble android game. Complexity is exponential to generate all the substrings, and a dictionary is used to check for valid words.
- download_conference_papers -> Python scripts to download conference papers as PDFs (like CVPR, ICLR, ECCV) with utility functions what can be used to download papers from any conference.
- dash_cdc_jhu_visualization -> Python program to download CDC and JHU covid data, and then visualize the discrepencies between the two sources of data using Dash.