Designing neural network architectures is inherently a visual process. Every time I train a new model, I find myself sketching it out on paper before translating it into code (and still running into shape mismatches no matter how many networks I've built). I wanted a way to quickly ideate with creative designs. So I built BlockDL: an interactive platform that helps you understand and build neural networks by designing them visually. 1. It generates working Keras and PyTorch code instantly as you build 2. You get live shape validation (catch mismatched layer shapes early) 3. It supports advanced structures like skip connections and multi-input/output models 4. It also includes a full learning system with 5 courses and multiple interactive lessons and challenges. BlockDL is free and open-source! Try it out: https://blockdl.com

BlockDL

Build & learn neural networks visually

Build & learn neural networks visually