Sieun ParkA late review of OpenAI’s “Training Verifiers to Solve Math Word Problems”Solving math problems with GPT. Verifiers, GSM-8K dataset, mathematical reasoningMar 141Mar 141
Sieun ParkinCodeXSentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text…The tokenization method for Alpaca, LLaMA, T5, XLNetMay 19, 20231May 19, 20231
Sieun ParkinCodeXAn Introduction to Multiprocessing Using PythonIs multithreading or multiprocessing faster than another?Apr 16, 2023Apr 16, 2023
Sieun ParkSubword RegularizationPrerequisite for understanding the commonly used `SentencePiece` tokenizer. Improve your tokenization using subword regularization!Mar 5, 2023Mar 5, 2023
Sieun ParkDetails of Faster, Mask, Cascade R-CNN 🔥WHY should you care? Faster R-CNN is an actively cited benchmark for comparing object detection performance of modern network…Jun 7, 2022Jun 7, 2022
Sieun ParkinCodeXConvMixer: Patches Are All You Need? Overview and thoughts 🤷CNNs don’t always have to progressively decrease resolution. A revolutionary idea that might shape the next-gen architectures for Computer…Nov 1, 20211Nov 1, 20211
Sieun ParkinCodeX7 Different Convolutions for designing CNNs that will Level-up your Computer Vision projectIn-depth review on Basic, Transposed, Dilated, Separable, Depthwise, and Pointwise convolutions and their applications.Oct 29, 2021Oct 29, 2021
Sieun ParkinCodeXR-Drop, a simple trick to improve DropOutThe method is simple, but results are significant. R-Drop achieves SOTA on NMT tasks even with the VANILLA Transformer architecture!Oct 27, 20211Oct 27, 20211
Sieun ParkinCodeXMaking VGG-style convnets great again with RepVGGVGGs are great! While they suck at training time, they are fast, flexible, and memory-efficient compared to modern CNNs. Let’s improve them.Oct 26, 2021Oct 26, 2021
Sieun ParkinCodeXImplementing R-CNN object detection on VOC2012 with PyTorchHow do we implement object detection from scratch? Let’s start from the basic R-CNN.Oct 22, 20212Oct 22, 20212