This is your work, valued
portfolio-optimization. Python
104reinforce. Implementing REINFORCE algorithm on Pong, Lunar Lander and Cartplot + Medium Article
23Pytorch-FaceNet-DogDataset. Paper To Code implementation of Facenet in native pytorch on Dog Dataset
22dashcam-object-detection. Label images with LabelImg; Object detection with detectron2
13ImageGeoLocation. Building a neural network that predicts that can geotag an outdoor image and how to catch a cheating neural network with grad-cam
13GauGanPytorch. Paper To Code implementation of NVIDIA's GauGan on a custom Landscape 's Dataset. Generating photorealistic-ish:p images from drawings
12MSPhi2-for-classification-LoRA. Training Microsoft Phi 2 LLM for sequence classification with LoRA and QLoRA
7webdevagent. Langchain Agent for Web Development With GPT-4o
7MidiTransformer. GPT transformer from scratch, training to generate midi music , using Pytorch
6Latent-Space-Interpolation. Using Autoencoders with keras and tensorflow.js
6pix2pix. Paper To Code implementation of pix2pix GAN
4signboard_text_detection. Generate synthetic dataset for object detection (Faster R-CNN)
3alphazeroTicTacToe. Coding AlphaZero algorithm from scratch to play the game of TicTacToe and it never loses!!
3neural_style_transfer. A CNN based approach to transfering "artistic style" from one image to another
3finetunegemmacolorpalette. finetune gemma 370m for generating color palettes
2langchainWorkshop. Jupyter Notebook
2qwenvlattention. Visualizing how Qwen3-VL attends to image regions during caption generation
2llm_sampling. Exploring Top p, greedy sampling and temperature on LLM generation
1wordFaceNet. Python
1flux-4bit-interpolation. flux-4bit for prompt interpolation
1ambigramPytorch. Generating Ambigram with PyTorch
1dubaistablediffusionvideo. Prompt interpolation and latent walk using Stable Diffusion.
1gemma4uncensor. hands-on study of how to reduce model refusals (“uncensor” in the sense of weight edits, not retraining) for Gemma 4 E2B IT by estimating a per-layer refusal-related direction from activations and projecting it out of o_proj and down_proj while preserving row norms
1dogvideodetector. Jupyter Notebook
1