I’m ready to turn a labelled image dataset into a production-ready machine learning model that reliably classifies each photo into the correct category. Your job is to design, train, and evaluate the full image-classification pipeline. You may build from scratch or fine-tune a proven architecture such as ResNet, EfficientNet, MobileNet, or a vision transformer—as long as the final model meets the accuracy targets we set together. Feel free to work in PyTorch or TensorFlow/Keras; I’m comfortable deploying either. What I’ll provide • A structured folder of training, validation, and test images • Category labels and a brief data dictionary • Access to a GPU instance if you need it What I need back 1. Clean, well-commented code (Jupyter notebook or Python scripts) that handles preprocessing, augmentation, training, and evaluation. 2. Trained weights plus an inference script that loads one or more images and returns the predicted class with confidence scores. 3. A concise report (Markdown or PDF) covering model architecture, key hyper-parameters, training curves, confusion matrix, and top-k accuracy. 4. Recommendations for further improvement or transfer-learning options. Acceptance criteria • Top-1 accuracy on my hold-out set meets or exceeds the agreed benchmark. • All code executes end-to-end on a fresh environment using only the requirements.txt file you deliver. • Model size and latency are suitable for deployment on a standard cloud instance. If this aligns with your expertise in machine learning model development for image data, I’d love to see how you would approach it and an estimated timeline to hit the first milestone.