KellerJordan

"""
sweep_casted.py

The base training here is a variant of clean_airbench which uses the renormalized optimizer,
which is optimal for CIFAR-10 training.
We also removed dirac initialization, for the purpose of casting experiments.

In full precision, attains 93.78 mean accuracy (n=50).

This code sweeps over a large number of number formats and widths, training 100

dougallj

# IDA (disassembler) and Hex-Rays (decompiler) plugin for Apple AMX
#
# WIP research. (This was edited to add more info after someone posted it to
# Hacker News. Click "Revisions" to see full changes.)
#
# Copyright (c) 2020 dougallj


# Based on Python port of VMX intrinsics plugin:
# Copyright (c) 2019 w4kfu - Synacktiv

lobrien

import numpy as np
from keras.models import Sequential
from keras.layers.core import Activation, Dense
from keras.optimizers import SGD

# Trains a neural net that recognizes the digit displayed by a 7-segment LED:
# "Lit segments" are indexed as:
#  -- 0 --
# |        |
# 1        2