Card: add a measured Performance table (Pixel 8a, benchmark_model GPU+CPU), naming the runtime for each row
Browse files
README.md
CHANGED
|
@@ -78,6 +78,18 @@ Result: banned ops NONE, all tensors ≤4D, tflite-vs-torch corr **1.0**, device
|
|
| 78 |
Center-crop to square, resize to 224×224, /255, ImageNet mean/std, NCHW. Output 365-class scene logits;
|
| 79 |
softmax + argmax for top-k.
|
| 80 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
## License
|
| 82 |
|
| 83 |
[MIT](https://github.com/CSAILVision/places365/blob/master/LICENSE). Upstream:
|
|
|
|
| 78 |
Center-crop to square, resize to 224×224, /255, ImageNet mean/std, NCHW. Output 365-class scene logits;
|
| 79 |
softmax + argmax for top-k.
|
| 80 |
|
| 81 |
+
## Performance
|
| 82 |
+
|
| 83 |
+
Measured on a **Pixel 8a** (Tensor G3, Android 16) with the standard TFLite [`benchmark_model`](https://ai.google.dev/edge/litert/models/measurement) tool — 10 warm-up runs then 50 timed runs, reported as the tool's mean.
|
| 84 |
+
|
| 85 |
+
| Runtime | Backend | Graph on GPU | Latency |
|
| 86 |
+
|---|---|---|---|
|
| 87 |
+
| LiteRT `CompiledModel` (`LITERT_CL`) | GPU | 61 / 61 | ~2 ms |
|
| 88 |
+
| TFLite `benchmark_model` (`TfLiteGpuDelegateV2`) | GPU (OpenCL) | 61 / 61 | 12.5 ms |
|
| 89 |
+
| TFLite `benchmark_model` | CPU (XNNPACK, 4 threads) | — | 62.0 ms |
|
| 90 |
+
|
| 91 |
+
**The two GPU rows are different runtimes, not a contradiction.** The `LITERT_CL` figure is the one recorded when this model shipped, taken through LiteRT's own `CompiledModel` accelerator — the path the Kotlin sample app and the LiteRT API use. The `TfLiteGpuDelegateV2` figure is the classic TFLite OpenCL delegate, measured with a tool anyone can download and re-run. They agree on how much of the graph the GPU takes; they disagree on speed, and the classic delegate is the slower of the two here. Read the `TfLiteGpuDelegateV2` row as a reproducible floor, not as this model's speed on LiteRT.
|
| 92 |
+
|
| 93 |
## License
|
| 94 |
|
| 95 |
[MIT](https://github.com/CSAILVision/places365/blob/master/LICENSE). Upstream:
|