← Back to all products

Computer Vision Toolkit

$39

Image classification, object detection, and segmentation pipelines with data augmentation and evaluation frameworks.

46 files
PythonYAMLMarkdownJSON

Product Preview

Try the interactive reader and demo tools below, or get the full product with all content unlocked.

Interactive Reader (Free Preview) ⚙ Try Demo Tools Download Free Sample

File Structure 46 files

computer-vision-toolkit/ ├── LICENSE ├── README.md ├── configs/ │ ├── augmentation_config.yaml │ └── training_config.yaml ├── free-sample.zip ├── guide/ │ ├── 01-evaluation-guide.md │ └── 02-training-guide.md ├── guides/ │ ├── evaluation-guide.md │ └── training-guide.md ├── index.html ├── interactive.html ├── requirements.txt ├── src/ │ └── cv_toolkit/ │ ├── __init__.py │ ├── __pycache__/ │ │ ├── __init__.cpython-312.pyc │ │ ├── augmentation.cpython-312.pyc │ │ ├── classification.cpython-312.pyc │ │ ├── datasets.cpython-312.pyc │ │ ├── detection.cpython-312.pyc │ │ ├── evaluation.cpython-312.pyc │ │ ├── inference.cpython-312.pyc │ │ ├── segmentation.cpython-312.pyc │ │ └── training.cpython-312.pyc │ ├── augmentation.py │ ├── classification.py │ ├── datasets.py │ ├── detection.py │ ├── evaluation.py │ ├── inference.py │ ├── models/ │ │ ├── __init__.py │ │ ├── __pycache__/ │ │ │ ├── __init__.cpython-312.pyc │ │ │ ├── backbones.cpython-312.pyc │ │ │ └── heads.cpython-312.pyc │ │ ├── backbones.py │ │ └── heads.py │ ├── segmentation.py │ └── training.py └── tests/ ├── __pycache__/ │ ├── test_augmentation.cpython-312-pytest-9.0.2.pyc │ ├── test_augmentation.cpython-312.pyc │ ├── test_detection.cpython-312-pytest-9.0.2.pyc │ ├── test_detection.cpython-312.pyc │ ├── test_evaluation.cpython-312-pytest-9.0.2.pyc │ └── test_evaluation.cpython-312.pyc ├── test_augmentation.py ├── test_detection.py └── test_evaluation.py

Documentation Preview README excerpt

Computer Vision Toolkit

End-to-end computer vision framework for image classification, object detection, and semantic segmentation — with real mAP/IoU math, PyTorch training loops, data augmentation, and model export.

Train, evaluate, and deploy CV models using a single coherent codebase. Every evaluation metric is implemented with real math (no black-box library calls), every training loop supports mixed precision and gradient accumulation, and the augmentation pipeline composes transforms the way you'd compose functions.

What You Get

  • Image classification — build classification pipelines with pre-trained ResNet/EfficientNet/ViT backbones, custom heads, and label management
  • Object detection — anchor-based detection with configurable anchor scales, multi-scale feature maps, and NMS post-processing
  • Semantic segmentation — UNet and FPN decoder architectures on any backbone, with per-pixel loss computation and boundary refinement
  • Data augmentation library — composable transforms (flip, rotate, crop, color jitter, blur, grayscale) with Compose, OneOf, and per-transform probability control
  • Dataset loaders — ImageFolderDataset for classification, DetectionDataset for COCO/VOC/YOLO-format annotations, with lazy loading and caching
  • Training loops — full PyTorch training with mixed precision (AMP), gradient accumulation, cosine/step/plateau LR scheduling, warmup, and automatic checkpointing
  • Evaluation framework — real implementations of IoU, [email protected], mAP@[.5:.95] (COCO-style), precision-recall curves, confusion matrices, and segmentation mIoU — all using stdlib math
  • Inference engine — batch inference, confidence thresholding, NMS, and ONNX export
  • Model architectures — backbone library (ResNet, EfficientNet, MobileNet, ViT) and task-specific heads (classification, detection, segmentation)

File Tree


computer-vision-toolkit/
├── README.md
├── LICENSE
├── requirements.txt
├── src/
│   └── cv_toolkit/
│       ├── __init__.py              # Package exports
│       ├── classification.py        # Classification pipeline and models
│       ├── detection.py             # Object detection with anchor configs
│       ├── segmentation.py          # Semantic/instance segmentation
│       ├── augmentation.py          # Composable augmentation transforms
│       ├── datasets.py              # Dataset loaders (ImageFolder, COCO, VOC)
│       ├── training.py              # Training loop with AMP and scheduling
│       ├── evaluation.py            # mAP, IoU, classification metrics (real math)
│       ├── inference.py             # Batch inference and model export
│       └── models/
│           ├── __init__.py          # Model registry
│           ├── backbones.py         # ResNet, EfficientNet, MobileNet, ViT
│           └── heads.py             # Classification, detection, segmentation heads
├── configs/
│   ├── training_config.yaml         # Training hyperparameter presets
│   └── augmentation_config.yaml     # Augmentation pipeline configurations
├── tests/
│   ├── test_evaluation.py           # mAP, IoU, classification metric tests
│   ├── test_augmentation.py         # Augmentation pipeline tests
│   └── test_detection.py            # Detection model and anchor tests
└── guides/
    ├── training-guide.md            # Training workflow walkthrough
    └── evaluation-guide.md          # Metrics explained with decision guidance

Quick Start

1. Install Dependencies


pip install -r requirements.txt

*... continues with setup instructions, usage examples, and more.*

Code Sample .py preview

src/cv_toolkit/augmentation.py """ Data Augmentation — Computer Vision Toolkit ============================================== Composable image augmentation pipeline with both PIL-based transforms (stdlib-compatible) and OpenCV/albumentations backends. The PIL backend works without any extra dependencies beyond Pillow. The albumentations backend provides GPU-accelerated, bounding-box-aware augmentations for detection and segmentation tasks. By Datanest Digital — [email protected] """ from __future__ import annotations import logging import math import random from dataclasses import dataclass, field from typing import Any, Callable, Dict, List, Optional, Sequence, Tuple, Union logger = logging.getLogger(__name__) try: from PIL import Image, ImageEnhance, ImageFilter, ImageOps HAS_PIL = True except ImportError: HAS_PIL = False # --------------------------------------------------------------------------- # Transform base and composition # --------------------------------------------------------------------------- class Transform: """Base class for image transforms. Subclasses implement __call__ with the actual transformation. Each transform has a probability of being applied. """ def __init__(self, p: float = 1.0) -> None: self.p = p def __call__(self, image: "Image.Image") -> "Image.Image": if random.random() < self.p: return self.apply(image) return image # ... 363 more lines ...