Quantization: Per-Tensor and Per-Channel Scales
Medium · Solved in PyTorch · Machine learning coding practice
Problem
Choose robust AbsMax scales and compare tensor-wide versus output-channel quantization.
Topics: quantization, inference, pytorch, numpy
The full statement, worked examples, hints and the test suite are available once you sign in. You can then solve Quantization: Per-Tensor and Per-Channel Scales in the browser and run it against the tests.