Resource Restrictions

Your solutions for this challenge must be able to function in a resource-limited setting i.e. it should run on a low-resource smartphone. As such, we are imposing the following restrictions on resources:

• T4 GPU, maximum 9h training, maximum 3h inference
• Model frameworks must be appropriate for use on edge devices (e.g. ONNX, TensorFlow Lite)

As long as it fits this description you are good to go. Just remember if it is too big and takes long to run on an edge device especially a mobile phone, it is not ideal to use it. If otherwise, you are good to go. It should also support these format (ONNX and Tensorflow Lite). Check for the Speed CPU ONNX(ms). If it surpasses 100ms, it might not be ideal. If all is good, then why not.