Quantization
التكميم
Definition
Reducing the numeric precision of weights and activations (for example from 32 bits to 8 or 4 bits) to make the model smaller and faster.
Definition
Quantization lowers the numeric precision of weights and activations, such as from 32-bit floats to 8- or 4-bit integers, shrinking model size and speeding inference.
Practical examples
import numpy as np
x = np.array([-1.0, 0.0, 0.5, 1.0])
s = np.abs(x).max() / 127
q = np.round(x / s).astype(int)
print(q.tolist())Expected output
[-127, 0, 64, 127]
