Rows are actual labels and columns are predicted labels. Trace each sample into its cell, including mistakes hidden by accuracy.

matrix = [[0, 0], [0, 0]]
matrix[0][1] += 1
print(matrix)

Rows are actual labels and columns are predicted labels. Trace each sample into its cell, including mistakes hidden by accuracy. The trace reads the local variables of your function as it executes. Change one input or parameter, predict the result, then run the checks again. A small deterministic example makes arithmetic mistakes easier to locate than a long training run. State the shape and meaning of the returned value before coding. Keep preprocessing, evaluation and model updates in their proper order, and examine the boundary case in each check. The companion lab lets you replay intermediate values while the same algorithm runs.

confusion(actual, predicted, classes) returns a classes by classes count matrix. Labels are integers from 0 to classes-1; input lengths match.

The explanation opens here once every check passes.