Search Results for "facerecognitiondelphi/pascal"

...It reproduces the influential FCN approach that converts classification networks into dense, pixel-level predictors. The package includes FCN32s, FCN16s, FCN8s, and FCN8s-at-once variants with progressively finer output reconstruction. Training code and a PASCAL VOC example are provided so users can reproduce baseline experiments. The repository reports mean intersection-over-union results alongside the original implementation for comparison. Pretrained model links and validation visualizations support evaluation and demonstrations. It can be installed from source or through the torchfcn package and is primarily useful for research, education, and legacy segmentation baselines.

Mask R-CNN Benchmark is a PyTorch-based framework that provides high-performance implementations of object detection, instance segmentation, and keypoint detection models. Originally built to benchmark Mask R-CNN and related models, it offers a clean, modular design to train and evaluate detection systems efficiently on standard datasets like COCO. The framework integrates critical components—region proposal networks (RPNs), RoIAlign layers, mask heads, and backbone architectures such as...

...The repository includes the major components needed for an object detection workflow, including training scripts, evaluation scripts, demos, and utility modules. It supports commonly used benchmark datasets such as PASCAL VOC and MS COCO, and it also provides scripts to simplify downloading and setting up those datasets. For training visibility, the project includes support for Visdom so users can monitor loss in real time through a browser-based interface. Its structure makes it useful both as a reference implementation for learning SSD and as a base for custom experimentation in detection research or practical computer vision projects.

...It was created to simplify the process of building and experimenting with deep learning models capable of identifying objects within images. Luminoth includes support for popular object detection architectures such as Faster R-CNN and SSD, enabling developers to train models on datasets like COCO and Pascal VOC. The toolkit provides command-line utilities for dataset management, training, and inference, making it easier to integrate into research workflows and production systems. Although the project is no longer actively maintained, it remains a useful educational and experimental platform for studying object detection pipelines and deep learning workflows.

Lascer liefert zu einer Menge binär klassifizierter Attribut-Vektoren eine Menge von Regeln zur Beschreibung der Klassen. Die Regeln können auch mathematische Funktionen enthalten, deren Art vorgegeben werden kann.

Ghost is an artificial intelligence which can chat with you (in slovak language) in console or on the web. It is similar to Eliza, ALICE or Jabberwacky. It is writen in object pascal.

Analytical information system based on methods of an artificial intellect

TabuMusic is a simple program that generates music based on a Tabu Search Metaheuristic. The parameters are given in an input.txt file and the output is an ABC file, which can easily be converted in a MIDI file. Shows promissing results... E-mail me if y

TGPopulation is a genetic programming library for Borland Delphi, C++ Builder, Kylix and Free Pascal. Symbolic Regression and GP Robots are two example applications for it.

MEDDAC is the seeding point for designing a new approach to Operating System design itself. It is an Open Source project with roots in mainframe design and development the author began in 1979. Monitor Editor Disassembler Decompiler Assembler Compiler

Modernizing the sentential and predicate logic programs, Bertie and Twootie, by cleaning up the code, rewritting the code to conform to the standard Pascal defination, and developing a graphical user interface for both X and MS Windows.

The interesting thing about this is the artificial intelligence. You probably do not want to play Tetris AI. It survives for more than 1000 lines and beats every human in multiplayer mode (due to its speed). Two differnt AIs can play against each other.