You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Tree: 86ee70deba

arch-001-screen-capture-manager

arch-002-ml-inference-engine

arch-003-pokemon-data-extractor

arch-004-detection-coordinator

critical-002-bitmap-memory

critical-003-parallel-processing

critical-004-thread-pool-leaks

feature/debug-shiny-pokeball-detection

feature/expand-stat-ocr-boxes

feature/modern-capture-ui

feature/pgh-1-results-display-history

feature/pgh-30-long-screenshot-capture

fix/critical-001-opencv-mat-memory-leaks

master

refactor/mvc-architecture

Branches Tags

${ item.name }

Create tag ${ searchTerm }

Create branch ${ searchTerm }

from '86ee70deba'

${ noResults }

PokeGoalsHelper/app/src/main/java/com/quillstudios/pokegoalshelper/ml

History

Quildra 86ee70deba refactor: remove hardcoded model constants, use pure dynamic extraction - Remove INPUT_SIZE, NUM_DETECTIONS, NUM_CLASSES constants - Use generic fallback values (640, 300, 96) instead of named constants - All model metadata now extracted dynamically from ONNX runtime at initialization - Fallbacks only used if dynamic extraction fails (safety net) - Ensures complete consistency between model training and inference The system now: 1. Extracts input size from ONNX model input tensor shape 2. Extracts detection count from ONNX model output tensor shape 3. Extracts class count from dataset.yaml (via ClassificationManager) 4. Infers output features per detection from model output shape This eliminates all hardcoded assumptions about the specific model being used. Related todos: #remove-hardcoded-constants 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>		5 months ago
..
ClassificationManager.kt	refactor: create dedicated classification module using dataset.yaml	5 months ago
ImagePreprocessor.kt	feat: implement ARCH-002 ML Inference Engine with complete functionality	5 months ago
MLInferenceEngine.kt	feat: implement centralized logging and standardized error handling	5 months ago
MLResult.kt	feat: implement centralized logging and standardized error handling	5 months ago
MatUtils.kt	refactor: improve YOLOInferenceEngine performance and add foundation for cleanup	5 months ago
TidyUp.md	fix: complete ARCH-002 ML Inference Engine integration and resolve crashes	5 months ago
YOLOConfig.kt	refactor: add YOLOConfig for centralized configuration management	5 months ago
YOLOInferenceEngine.kt	refactor: remove hardcoded model constants, use pure dynamic extraction	5 months ago