Image Classification Machine Learning Model

I need a hands-on partner to turn a folder of labelled pictures into a production-ready image-classification model. This project sits squarely in machine learning: the main task is to build, train, and validate a solution that can correctly place each incoming image into its predefined category with solid, measurable accuracy.

Here is how I see the work unfolding:

• Prepare and clean the image dataset, applying sensible augmentation so the network generalises well.
• Select or design a CNN architecture (transfer-learning with ResNet, EfficientNet, or a custom model—whichever you believe will perform best) and implement it in Python using TensorFlow or PyTorch.
• Train, tune hyper-parameters, and track performance with clear metrics; I want the training notebook or script fully reproducible on my side.
• Deliver the trained model file, an inference script or API endpoint, and a brief report explaining your methodology, final accuracy, and any recommendations for future improvements.

I will supply the images and their class labels as soon as we start, and I’m happy to discuss target accuracy or class-imbalance strategies up front. The code should run on a standard GPU instance (CUDA 11.x). Once the model meets the agreed accuracy on my held-out validation set, the project is finished and paid in full.