#Overview I built an Image Classifier that attained 96% accuracy by implementing PyTorch fundamental modules from scratch listed below. After building the fundamentals In addition, I enhanced 25% computation efficiency through parallel programming on GPU with NumbaJit and CUDA.
- Auto Differentiation
- Back-Propagation
- Tensor Broadcasting
- Derivative and Scalar programming.
NLP and CV training scripts in project/run_sentiment.py and project/run_mnist_multiclass.py. This script has the same basic training setup as :doc:module3, but now adapted to sentiment and image classification. You need to implement Conv1D, Conv2D, and Network for both files. Use Streamlit for visualization.
Xor Data Set:
Simple Data Set:
Split Data Set:
Diag Data Set:
My guidance:
-
Overview: https://minitorch.github.io/module4.html
