How rishikesh-2006/nns works
This is a collection of independent neural-network experiments, not a single application: users run a script or notebook to train a model on a standard dataset and inspect predictions or generated images. The README highlights ANN, CNN, GAN and DCGAN experiments; the tree also contains transformer and image-recovery notebooks. The sampled Python files show MNIST loading, training and prediction, but notebook contents were not sampled, so their internal wiring is left unspecified.
Main entry points: Mnist.py MNIST ANN · Pytorch Mnist.py MNIST ANN · neural network 4.py Small ANN · CNN Fashion MNIST.ipynb Fashion CNN
Components 15
Pytorch Vision
- MNIST ANN
Pytorch/Pytorch Mnist.py - Fashion CNN
Pytorch/CNN Fashion MNIST.ipynb - MNIST CNN
Pytorch/CNN Mnist.ipynb - Image Recovery
Pytorch/CNN image Recovery.ipynb
Image Generation
- DCGAN
Pytorch/DCGAN.ipynb - Fashion GAN
Pytorch/Fashion Mnist GAN.ipynb - Number to Image
Pytorch/Number to image.ipynb
Transformers
- Transformer
Pytorch/Transformer.ipynb - Complete Transformer
Pytorch/Transformer_Complete.ipynb
Other components
- Experimenter
- MNIST files
- Toy data
- Predictions / images
Connections 16
- Experimenter → MNIST ANN: runs
- Experimenter → Small ANN: runs
- Experimenter → MNIST ANN: runs
- Experimenter → Fashion CNN: runs
- Experimenter → MNIST CNN: runs
- Experimenter → Image Recovery: runs
- Experimenter → DCGAN: runs
- Experimenter → Fashion GAN: runs
- Experimenter → Number to Image: runs
- Experimenter → Transformer: runs
- Experimenter → Complete Transformer: runs
- MNIST files → MNIST ANN: loads
- MNIST files → MNIST ANN: loads
- Toy data → Small ANN: defines
- MNIST ANN → Predictions / images: plots prediction
- MNIST ANN → Predictions / images: plots prediction