This repository focuses on Optical Character Recognition (OCR), specifically on processing a custom image dataset, training OCR models, and evaluating their performance. The project includes scripts for data preprocessing (cropping text from images), experiments with both pre-trained models (like TrOCR) and a custom-built CRNN model
Better multi-class confusion matrix plots for Scikit-Learn, incorporating per-class and overall evaluation measures.
my implementation calculate precision, recall, f1, accuracy, and GLEU score
Compare all binary classifiers in one place without coding. Simply upload your CSV file to get started.
Official implementation for the MSc Thesis: "Performance Evaluation of Vector Databases on RecSys and IR Data".
Information Retrival and Text Mining Mini Project
Bu çalışmamda "Makine Öğrenmesi" algoritmaları üzerine çalıştım. Bu algoritmaları veri seti üzerinde uygulayarak tahminlerde bulundum ve sonuçları analiz ettim.
Machine Learning Model to predict student graduation grade
Complementary residue arithmetic — 0.1 + 0.2 = 0.3, exactly.
🛰️ Python tool for land-cover classification accuracy assessment builds a full confusion matrix ✅ with Accuracy, Precision 🎯, Recall 🔍, F1-score ⚖️ by comparing ground-truth vs predicted shapefiles. Support 🔗 id-based & 🗺️ area-weighted polygon matching, auto label-cleaning 🧹 and heatmap export 📊. Powered by GeoPandas, scikit-learn & QGIS 🌍
Explore direct neighbors and limits of IEEE floating-point values.
A target that looks vulnerable and is not. Sixteen routes shaped like classic findings, none of which do the thing they appear to do, so every finding reported against it is a false positive by construction. The precision control for scanner benchmarking.
jsondiff is a json diff utility. It can compare two JSON files, using strings, prefixes, or regex to filter required/optional fields, and apply relative or absolute precision tolerance per each numeric field or globally; prints the diff between 2 json files. It can optionally accept a config with required or optional fields.
Evaluation and agreement scripts for the DISCOSUMO project. Each evaluation script takes both manual annotations as automatic summarization output. The formatting of these files is highly project-specific. However, the evaluation functions for precision, recall, ROUGE, Jaccard, Cohen's kappa and Fleiss' kappa may be applicable to other domains too.
A high-precision Python CLI damage calculator for Seven Knights Rebirth, leveraging Decimal arithmetic for exact in-game parity, with Castle simulation and multi-scenario analysis.
Python module providing an easy way to set the precision of a floating-point number to the desired amount of decimal places, or total amount of significant digits.
Script to compute Precision, Recall, AvP and MAP and to plot PR curves in the context of Information Retrieval evaluation.
🩺 BodyScope: Your AI Health Companion is an advanced Streamlit-based web application that predicts obesity risk and delivers hyper-personalized health advice using your basic lifestyle inputs. Powered by a machine learning model and Google Gemini Pro, BodyScope calculates your BMI, categorizes your health status like Underweight, Healthy, Obese
Compute with granular precision only when necessary in a integral/fractaline sense
To associate your repository with the precision topic, visit your repo's landing page and select "manage topics."