Images are data contracts
Use images are data contracts to move the vision production brief toward a defensible release.
A factory has few positive examples of costly visual defects.
This lesson isolates images are data contracts as one decision inside that system. The people affected are product users and operators; the learning data must carry event time, availability time, ownership, and version; and the operating envelope is one shift for inference and review.
Choose whether and how to use NCHW tensors at a declared prediction cutoff.
Measure decision utility alongside calibration, slice reliability, and system latency—not model score alone.
A factory has few positive examples of costly visual defects. An unsafe release must degrade to a named baseline or the last known-good version.
Build the mental model before the machinery.
The core move is to treat images are data contracts as a contract between data, a computation, and an action. Version color, resize, orientation, normalization, class map, and threshold; monitor camera/site slices. The implementation becomes easier to debug once you can state which inputs exist, which state is learned, what output means, and what must remain invariant after serialization.
NCHW tensors
Define it in a hand-checkable form and name the prediction-time inputs.
convolution
Connect it to the production metric and identify what it cannot guarantee.
receptive fields
Stress it with a slice, a temporal boundary, and a failure-safe alternative.
augmentation
Stress it with a slice, a temporal boundary, and a failure-safe alternative.
Neural networks
Name every symbol. Check every shape.
Convolution output size is the central invariant for this lesson. The formula is useful only when its inputs match the production cutoff and its output maps to an action.
Convolution output size
| Symbol | Meaning / shape / unit |
|---|---|
in, out | spatial input/output size |
k | kernel size |
s | stride |
p | padding |
d | dilation |
Open derivation and numerical substitution
Start from the production quantity being optimized, substitute the observed values with their declared units, then isolate the model-controlled term. Preserve shape annotations at each step so broadcasting or aggregation cannot silently change the result.
- Write the named inputs: in, out, k, s, p, d.
- Substitute one small, hand-checkable batch before vectorizing.
- Calculate an independent reference value and compare within a declared tolerance.
# equation → code contract
inputs = validate_shapes_and_units(batch)
value = compute_c10(inputs)
assert is_finite(value)Calculate it small. Shape it realistically. Break it on purpose.
A result you can reproduce on paper
Apply vertical and horizontal edge kernels to a 5×5 image and change stride and padding.
- Write every input and unit.
- Substitute values into the convolution output size equation above.
- Compare the result to one simple baseline and explain the direction of the difference.
The same reasoning under real constraints
Fine-tune a pretrained CNN for rare defects, then compare a detector when localization becomes necessary.
The production record includes the data snapshot, transformation state, artifact identity, cutoff, score, decision, and the version of the policy that consumed it.
The attractive result you should reject
Random burst-frame splitting puts near-duplicates of one product in train and validation.
Diagnostic: replay the smallest failing slice from immutable inputs, then compare each boundary rather than retuning the model.
Change one assumption and make the tradeoff visible.
This lab runs predefined TypeScript only. It never executes learner code. Use the slider, numeric input, reset, live text, or table—the computation is the same.
Receptive-field assembler
Stack kernels and see receptive field, parameter count, and output size.
Assumption: 3×3 stride-one convolutions, 32 channels, 64×64 input, no dilation.
Open nonvisual data table
| Item | Computed state | Interpretation |
|---|---|---|
| layer 1 | 3×3 | 62×62 |
| layer 2 | 5×5 | 60×60 |
| layer 3 | 7×7 | 58×58 |
| layer 4 | 9×9 | 56×56 |
Trace the complete operating path.
- 01
Validate and version NCHW tensors.
- 02
Compute images are data contracts from prediction-time-safe inputs.
- 03
Persist model, feature, and configuration identities together.
- 04
Serve or materialize behind explicit one shift for inference and review.
- 05
Join telemetry to mature outcomes and retain a rollback path.
Observability
Join service health, input quality, prediction distributions, slice behavior, and mature outcomes by exact version.
Cost
Measure storage, preprocessing, compute, queueing, and human review under a representative arrival pattern.
Failure modes
Random burst-frame splitting puts near-duplicates of one product in train and validation. Add a detector, owner, mitigation, and stop condition for this class of failure.
Alternatives
Compare a rule, a simpler statistical baseline, and a different system boundary before adding model complexity.
Explain the contract, not just the vocabulary.
Rare-defect vision system
Design grouped evaluation, transfer learning, calibration, batch-one export, and camera-drift monitoring.
- Grouped split and audit
- Transfer-learning ablations
- PR and calibration report
- Export/latency/monitoring
Read primary material with a purpose.
Return to the opening failure.
Version color, resize, orientation, normalization, class map, and threshold; monitor camera/site slices.
For this lesson, the release evidence is a hand-checked formal result, deterministic simulation output, a ≥80% checkpoint, the production rubric, and a named fallback. The course resolves when the system can produce cnn and transfer-learning baselines with augmentation, calibration, and monitoring.