dlspit 1.0.3

A collection of Deep Learning experiments: MLP, CNN, ResNet, RNN, LSTM, Transformer, GAN, VAE, Transfer Learning.

dlspit — DL Experiments

A pip-installable collection of Deep Learning experiment modules covering McCulloch-Pitts neurons, MLP, backpropagation, CNN, ResNet, RNN, LSTM, Transformer, GAN, VAE, and Transfer Learning.

Installation

# Core (NumPy only — Exp 1aMP_Xor works without extras)
pip install dlspit

# With TensorFlow (required for Exp 1bMP_Binary through 10Transfer)
pip install "dlspit[tensorflow]"

# With scikit-learn (required for Exp 7Lstm MinMaxScaler)
pip install "dlspit[sklearn]"

# Everything
pip install "dlspit[all]"

Usage

Python API

import dl_experiments

# Print the source code of an experiment (default behaviour)
dl_experiments.main("1aMP_Xor")           # McCulloch-Pitts
dl_experiments.main("4CNN", "5Resnet")    # CNN + ResNet
dl_experiments.main()                     # all experiments

# Actually execute an experiment
dl_experiments.run_experiment("4CNN")

# Print source directly
dl_experiments.show_source("7Lstm")

# List all valid keys
print(dl_experiments.list_experiments())

CLI

# Print source code (default)
dlspit 1aMP_Xor
dlspit 4CNN 5Resnet 6RNN

# List all valid experiment keys
dlspit --list

# Execute an experiment
dlspit --run 4CNN
dlspit --run                    # execute all

# As a module
python -m dl_experiments 1aMP_Xor
python -m dl_experiments --run 4CNN

Experiment Index

Key	Description
1aMP_Xor	McCulloch-Pitts neuron — XOR & XNOR gates
1bMP_Binary	MLP binary classifier (XNOR via backprop)
2aLoss_Activation	Activation & loss function comparison on MNIST
2bBPN	Backpropagation on MNIST (SGD feedforward NN)
3regularization	L2 regularisation + Dropout on MNIST
4CNN	Convolutional Neural Network on MNIST
5Resnet	ResNet50 transfer learning on CIFAR-10
6RNN	Simple RNN for IMDB sentiment analysis
7Lstm	Stacked LSTM for time-series prediction
8Transform	Transformer encoder for IMDB text classification
9aVAE	Variational Autoencoder on MNIST
9bGAN	Generative Adversarial Network on MNIST
10Transfer	MobileNetV2 transfer learning on CIFAR-10

Requirements

• Python ≥ 3.10
• numpy ≥ 1.24
• (Optional) tensorflow ≥ 2.12 — for Exp 1bMP_Binary through 10Transfer
• (Optional) scikit-learn ≥ 1.3 — for Exp 7Lstm (MinMaxScaler)

License

MIT