Cnn Python Packages

ultralytics-thop

PyTorch model profiler for computing MACs and parameter counts to measure deep learning model complexity.

easyocr

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

tsai

Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai

flac-detective

Catches music sold as lossless that was secretly compressed. It accuses only when independent lines of evidence agree, because a false accusation costs more than a miss.

omlt

Represent trained machine learning models as Pyomo optimization formulations

torchcam

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM, Finer-CAM, LeGrad, RefineCAM)

attacut

A Fast and Accurate Neural Thai Word Segmenter

hypercube-cnn

A CNN that operates on Boolean hypercubes — XOR-addressed topology, Hamming-distance kernels, end-to-end backprop in pure C++23.

hypercube-etalon

HypercubeCNN with a hypercube preprocessor for static fields (spectra, images). A vertex and its antipode form an etalon; one reflection walk, then a thin readout. Not a reservoir. C++23.

neuralnetlib

🧠 A flexible machine & deep learning framework built from scratch using only NumPy

keras-hexagdly

Keras 3 hexagonal CNN layers (HexagDLy port) for hexagonally-sampled data — IACT/Cherenkov cameras, etc. — Support for hls4ml in progress

melpy

A NumPy-based deep learning library for building neural networks. It features an automatic differentiation engine and supports training architectures like LSTM, CNN, and FNN.

mist-medical

MIST: A simple and scalable end-to-end framework for 3D medical imaging segmentation.

continual-inference

A Python library for Continual Inference Networks in PyTorch

diploshic

feature-based deep learning for the identification of selective sweeps

efficientword-net

OneShot Learning-based hotword detection.

indexedconv

Code for the indexed convolution

topaz-em

Pipeline for particle picking in cryo-electron microscopy images using convolutional neural networks trained from positive and unlabeled examples. Also featuring micrograph and tomogram denoising with DNNs.

netra-ocr

A Squeeze-and-Excitation Transformer Network for Khmer Optical Character Recognition

efficient-polling-lr-scheduler

This repository replicates the Polling Method of Tan et al. on CIFAR-10 and introduces Efficient Polling, a novel extension that recovers the same learning-rate schedule — and almost the same accuracy — while polling only 5% of batches, cutting optimizer steps by 75% and per-epoch wall-clock time by 3.3×.

maldideepkit

Catalog of sklearn-compatible deep learning classifiers for MALDI-TOF binned spectra

pytorch-hexagdly

Process hexagonally sampled data with PyTorch

moai-mdk

moai is a PyTorch-based AI Model Development Kit (MDK) created to improve data-driven model workflows, design and reproducibility.

nano-ocr

A Lightweight OCR model and Engine for low computation devices, edge applications and embedded system