Custom Deep Learning
- Create a customized Feedforward Neural Network
- Available options:
- Weight initialization: Random, Xavier, He
- Activation functions: Identity, Sigmoid, Softmax, Tanh, ReLU
- Loss functions: MSE, Cross Entropy
- Optimizers: GD, Momentum based GD, Nesterov accerelated GD
- Learning mode: online, mini-batch, batch
- Available options:
- Refer to the documentation of any class/method by using help(class/method) Eg: help(FNN), help(FNN.compile)
- For a high-level overview of the underlying theory refer:
Installation
$ [sudo] pip3 install customdl
Development Installation
$ git clone https://github.com/Taarak9/Custom-DL.git
Usage
>>> from customdl import FNN
Handwritten Digit Recognition example
import numpy as np
from matplotlib import pyplot as plt
from mnist_loader import load_data_wrapper
from customdl import FNN
# MNIST data split
training_data, validation_data, test_data = load_data_wrapper()
# Loss function: Cross Entropy
hdr = FNN(784, "ce")
hdr.add_layer(80, "sigmoid")
hdr.add_layer(10, "sigmoid")
hdr.compile()
hdr.fit(training_data, validation_data)
hdr.accuracy(test_data)
The mnist_loader used could be found here.
Features to be added
- Plots for monitoring loss and accuracy over epochs
- Regularization techniques: L1, L2, dropout
- Optimizers: Adam, RMSProp
- RBF NN
Metadata
Release files for customdl 1.0.15
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| customdl-1.0.15.tar.gz | 8.7 kB | Without provenance | Details for customdl-1.0.15.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| customdl-1.0.15-py3-none-any.whl | Python 3 | none | any | Details for customdl-1.0.15-py3-none-any.whl |
Total release size: 17.4 kB
Release files / customdl-1.0.15.tar.gz
| Download URL | customdl-1.0.15.tar.gz |
|---|---|
| Size | 8.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
30258ed7836967a42d82e609b8196bcb24ae4d6dba69be817d0908b81c16ec96
|
|
BLAKE2b-256 checksum How to use checksums |
1537c3575302c5750cba1c68425e2477fee65c22c0f2002c9c08581f920330fb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.1 importlib_metadata/4.3.1 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.0 CPython/3.6.9
|
Release files / customdl-1.0.15-py3-none-any.whl
| Download URL | customdl-1.0.15-py3-none-any.whl |
|---|---|
| Size | 8.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b9c269480041f4c1307f17d38d70746065ad496ccd509de4fa67888f8f1f3550
|
|
BLAKE2b-256 checksum How to use checksums |
819c0f45a54e63949db5ed4b75366c0d0c86950ed644b1dbe6ab72d7dac4bd15
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.1 importlib_metadata/4.3.1 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.0 CPython/3.6.9
|
Security for customdl 1.0.15
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.