NeuroCraft
PyTorchFlaskReactTypeScriptPythonTailwindCSSNeural NetworkDeep Learning
The problem
Beginners need to experiment with neural-network layers without building an entire training application.
How I solved it
A web app for deep learning beginners to design neural networks without coding. Explore fundamentals like dense layers, batch-normalization, activation functions, and dropout while testing on MNIST and Fashion-MNIST datasets.
- No-code neural network design web app
- Explore dense layers and batch-normalization
- Test activation functions and dropout layers
- Practice with MNIST and Fashion-MNIST datasets
The results
- MNIST and Fashion-MNIST
- 2 datasets
- network layer choices
- 5 controls
Exposed two image datasets and five layer controls, backed by a Flask/PyTorch training API with CPU/CUDA selection and timestamped model export.
Evaluation context. Learning prototype. Softmax before cross-entropy and training/evaluation mode handling are known limitations; production deployment was not verified.