Update README.md
Browse filesAdded speedup numbers
README.md
CHANGED
|
@@ -40,6 +40,8 @@ This results in a model that is natively **smaller, faster, and reduces FLOPs**
|
|
| 40 |
|
| 41 |
> **Note:** "FLOPs" measures the number of floating-point operations required for a single inference pass. Lower is better for latency and battery life.
|
| 42 |
|
|
|
|
|
|
|
| 43 |
## ⚠️ Critical Note on Preprocessing & Accuracy
|
| 44 |
|
| 45 |
**Please Read Before Evaluating:** This model was trained and evaluated using standard PyTorch `torchvision.transforms`. The Hugging Face `pipeline` uses `PIL` (Pillow) for image resizing by default.
|
|
|
|
| 40 |
|
| 41 |
> **Note:** "FLOPs" measures the number of floating-point operations required for a single inference pass. Lower is better for latency and battery life.
|
| 42 |
|
| 43 |
+
On the hardware we test on (detailed in our [Paper](https://arxiv.org/abs/2511.19566)) we observe speedups of 2.42x on CPUs and 2.38x on GPUs.
|
| 44 |
+
|
| 45 |
## ⚠️ Critical Note on Preprocessing & Accuracy
|
| 46 |
|
| 47 |
**Please Read Before Evaluating:** This model was trained and evaluated using standard PyTorch `torchvision.transforms`. The Hugging Face `pipeline` uses `PIL` (Pillow) for image resizing by default.
|