I've started a machine learning project using TemsorFlow. The first thing I've learned is to start small, implement all the functionality and only then move to a real task.
I picked up Keras, so the code for the network itself is simple. Complexity is around: dataset preparation, evaluation and model selection.
Initially I worked on my laptop with an extremely small values, for example, images were resized to 128 by 128, which feels too small. However, I managed to get reasonable performance numbers.
When I moved my code to a much more powerful machine with lots of memory, cpus and gpus, I got a GPU enabled TemsorFlow binary. That speed up the things, but still CPU was a bottleneck.
@pixelCpu during training or during preprocessing/data manipulation?
@ksteimelTraining. I used PIL to resize images, so it's just CPU. Actually, Pillow-SIMD to get easy speedups.
A beta setup of a Mastodon instance primary for family and friends.