# Image Classification Inference on 1 million 30m classes

Source: [Image Classification Inference on 1 million 30m classes](<https://www.sota2.com/research/sota/image-classification-inference-on-1-million-30m-classes>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-02T07:54:54.676Z

Evaluation of model performance for Image Classification Inference tasks on the '1 million 30m classes' dataset, measured using throughput and latency components (td, tf, tc, tn, Ks, Kt).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Image Classification Inference |
| Dataset (including any stated split) | 1 million 30m classes |
| Metric | td Component |
| Unit | TIME |
| Direction | Lower is better |
| Results loaded | 1 of 1 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [td Component](<https://www.sota2.com/research/sota/image-classification-inference-on-1-million-30m-classes.md?metric=td%20Component>): Lower is better; unit: TIME.

- [tf Component](<https://www.sota2.com/research/sota/image-classification-inference-on-1-million-30m-classes.md?metric=tf%20Component>): Lower is better; unit: TIME.

- [tc Component](<https://www.sota2.com/research/sota/image-classification-inference-on-1-million-30m-classes.md?metric=tc%20Component>): Lower is better; unit: TIME.

- [tn Component](<https://www.sota2.com/research/sota/image-classification-inference-on-1-million-30m-classes.md?metric=tn%20Component>): Lower is better; unit: TIME.

- [Ks Component](<https://www.sota2.com/research/sota/image-classification-inference-on-1-million-30m-classes.md?metric=Ks%20Component>): Higher is better; unit: SCALAR.

- [Kt Component](<https://www.sota2.com/research/sota/image-classification-inference-on-1-million-30m-classes.md?metric=Kt%20Component>): Lower is better; unit: TIME.

## Recorded results

| Method | td Component | Result date | Report paper |
| --- | --- | --- | --- |
| Proposed Method | 4334 | Not recorded | 69cdf80e0636e5bf4afcca74 |

### Proposed Method

td Component: 4334. Result ID: 69ce20bb47f34ce924b72b64.

[Reporting paper](<https://www.sota2.com/research/paper/69cdf80e0636e5bf4afcca74.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cdf80e0636e5bf4afcca74.md>)

Recorded evaluation configuration: {"ndim":"107","Batch size":"64"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
