A collection of Deep Learning experiments: MLP, CNN, ResNet, RNN, LSTM, Transformer, GAN, VAE, Transfer Learning.
Project description
dl-experiments-ps07
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 1a, 1b, 2a, 3)
pip install dl-experiments-ps07
# With scikit-learn (Exp 2b MNIST loader)
pip install "dl-experiments-ps07[sklearn]"
# With PyTorch (Exp 4–10)
pip install "dl-experiments-ps07[torch]"
# Everything
pip install "dl-experiments-ps07[all]"
Usage
Python API
import dl_experiments
# Run ALL experiments
dl_experiments.main()
# Run specific experiments
dl_experiments.main("1a") # McCulloch-Pitts
dl_experiments.main("4", "5") # CNN + ResNet
# List available keys
print(dl_experiments.list_experiments())
# ['1a', '1b', '2a', '2b', '3', '4', '5', '6', '7', '8', '9', '9b', '10']
CLI
# Run all experiments
dl-experiments
# Run specific experiments
dl-experiments 1a 2a 3
# List available experiments
dl-experiments --list
# As a module
python -m dl_experiments 1a 1b
Experiment Index
| Key | Module | Description |
|---|---|---|
| 1a | McCulloch-Pitts | Binary threshold neuron, logic gates |
| 1b | MLP Binary | XOR with 2-layer MLP |
| 2a | Activations & Losses | Sigmoid, Tanh, ReLU, MSE, BCE |
| 2b | Backprop MNIST | NumPy backprop on MNIST |
| 3 | Regularisation | L2 + Dropout |
| 4 | CNN | Conv2d + MaxPool |
| 5 | ResNet | Skip connections |
| 6 | RNN | Vanilla RNN sequence prediction |
| 7 | LSTM | Long Short-Term Memory |
| 8 | Transformer | Multi-head self-attention |
| 9 | GAN | Generator + Discriminator |
| 9b | VAE | Variational Autoencoder |
| 10 | Transfer | Frozen backbone + custom head |
Requirements
- Python ≥ 3.10
- numpy ≥ 1.24
- (Optional) scikit-learn ≥ 1.3 — for Exp 2b
- (Optional) torch ≥ 2.0, torchvision ≥ 0.15 — for Exp 4–10
License
MIT
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
dlspit-1.0.0.tar.gz
(29.3 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
dlspit-1.0.0-py3-none-any.whl
(41.9 kB
view details)
File details
Details for the file dlspit-1.0.0.tar.gz.
File metadata
- Download URL: dlspit-1.0.0.tar.gz
- Upload date:
- Size: 29.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d0eb315f34b98b91b2f4ebdd1c94cca40ea6fad12601b80c31b8c7d436a4a073
|
|
| MD5 |
1c426748d9e0bf2db42d42110434673e
|
|
| BLAKE2b-256 |
9ab6042c01b03434dcd03f27085fd921f243f58295f1b86ac3c089d838a3cd20
|
File details
Details for the file dlspit-1.0.0-py3-none-any.whl.
File metadata
- Download URL: dlspit-1.0.0-py3-none-any.whl
- Upload date:
- Size: 41.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
88fce8e302c0d593512dd4b935b936ae0c97f48a53244b1d9c3edbeef35b0c38
|
|
| MD5 |
a935d8f23ef77cd13c5bba6961d075d1
|
|
| BLAKE2b-256 |
28f18d437d7f647aec1e06b9e8a83b449df6630bf4562015a4a667ed2f2fd409
|