Build the first working 3x3 plus-sign classifier

Build only what the claim requires: plus fixtures score positive; blank/noise fixtures do not. Prefer boring, deterministic code over frameworks you cannot yet explain. Run the path twice; identical output on this fixture is a feature, not a lack of creativity.

def classify(img):
 flat=[p for row in img for p in row]; score=sum(flat[i] for i in [1,3,4,5,7])
 return ('plus' if score>=4 else 'other',score)
print(classify([[0,1,0],[1,1,1],[0,1,0]]))

Expected evidence: fragile pixel classifier. Read each printed intermediate as part of the argument that the path works—not as decoration.

Narrate the journey from raw input to result for a single example from plus, blank, and distractor 3×3 grids. If you cannot name an intermediate, the implementation is still too opaque for this lab. Only after this path is solid should you generalize data sources or UI.

While implementing the 3x3 plus-sign classifier, print or log at least three intermediates that map to the claim (plus fixtures score positive; blank/noise fixtures do not). Good intermediates are values a teammate could recompute with a calculator or diff. Bad intermediates are framework traces you cannot explain.

Re-run with plus, blank, and distractor 3×3 grids twice. If the second run differs, either the path is nondeterministic (document the seed) or you have hidden global state—both are lab bugs until named.

Stop adding features once the path supports classify tiny binary images as plus vs not-plus with inspectable features. Extra UI, extra tools, or extra models belong in later chapters. The mastery bar for this page is simply: a deterministic end-to-end path with intermediates.

At the implementation stage for computer-sees, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about plus, blank, and distractor 3×3 grids that later pages inherit without redefining success. Keep that fixture small enough to inspect by hand, keep outputs copy-pasteable as text, and refuse to narrate this baseline as if it were a production SLA: pixel-sum threshold accuracy on the same four images.

For this page specifically, success looks like a deterministic path with printed intermediates while still centering the user decision to classify tiny binary images as plus vs not-plus with inspectable features. If you cannot point to a file, command, or assertion that proves that for the 3x3 plus-sign classifier, stay on this page instead of advancing.

Glossary: computer vision · Glossary: convolutional neural network

Previous · Next