I would like to check how bit precision impacts DNN's accuracy. Do you know any C/C++/Python libraries that wouldn't require huge rework for supporting inference with quantized types? For example, I would like to set all the operands (weights, activations, errors and gradients) to 8/16/32 bit precision and check accuracy for each precision after testing.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.