I need an AI-powered image-recognition tool that focuses exclusively on identifying everyday household items. The core requirement is clear: when the model sees a photo, it should reliably detect and classify objects such as chairs, tables, kettles, lamps, and similar items that people typically keep at home. Here is how I picture the workflow and final hand-off: • Model: A well-trained neural network (TensorFlow, PyTorch, or a comparable framework) tuned for object detection/classification. • Dataset handling: Either you assemble and label a suitable open-source dataset or guide me on licensing a ready-made one; in either case, the final dataset or clear reproducibility steps must be included. • Inference pipeline: A simple script or lightweight API endpoint so I can feed in single images or batches and receive the detected household items with confidence scores. • Performance: Target real-time or near-real-time inference on a standard GPU laptop, with validation metrics demonstrating solid accuracy on unseen images. • Documentation: Brief, practical instructions covering setup, model retraining, and deploying the inference script. I’m open on the exact libraries you choose—OpenCV for preprocessing, ONNX for export, or similar tools are welcome—as long as installation remains straightforward. Let me know any questions or extra data you’ll need; I’m happy to provide sample images so you can start experimenting right away.