Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -1,7 +1,4 @@
|
|
1 |
---
|
2 |
-
datasets:
|
3 |
-
- imagenet-1k
|
4 |
-
- imagenet-22k
|
5 |
library_name: pytorch
|
6 |
license: bsd-3-clause
|
7 |
pipeline_tag: image-classification
|
@@ -38,27 +35,29 @@ More details on model performance across various devices, can be found
|
|
38 |
|
39 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
40 |
|---|---|---|---|---|---|---|---|---|
|
41 |
-
| Swin-Small | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 18.
|
42 |
-
| Swin-Small | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 21.
|
43 |
-
| Swin-Small | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 34.
|
44 |
-
| Swin-Small | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 12.
|
45 |
-
| Swin-Small | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 14.
|
46 |
-
| Swin-Small | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 23.
|
47 |
-
| Swin-Small |
|
48 |
-
| Swin-Small |
|
49 |
-
| Swin-Small |
|
50 |
-
| Swin-Small |
|
51 |
-
| Swin-Small |
|
52 |
-
| Swin-Small |
|
53 |
-
| Swin-Small |
|
54 |
-
| Swin-Small |
|
55 |
-
| Swin-Small |
|
56 |
-
| Swin-Small |
|
57 |
-
| Swin-Small |
|
58 |
-
| Swin-Small |
|
59 |
-
| Swin-Small |
|
60 |
-
| Swin-Small |
|
61 |
-
| Swin-Small |
|
|
|
|
|
62 |
|
63 |
|
64 |
|
@@ -123,7 +122,7 @@ Swin-Small
|
|
123 |
Device : Samsung Galaxy S23 (13)
|
124 |
Runtime : TFLITE
|
125 |
Estimated inference time (ms) : 18.7
|
126 |
-
Estimated peak memory usage (MB): [0,
|
127 |
Total # Ops : 1563
|
128 |
Compute Unit(s) : NPU (1563 ops)
|
129 |
```
|
|
|
1 |
---
|
|
|
|
|
|
|
2 |
library_name: pytorch
|
3 |
license: bsd-3-clause
|
4 |
pipeline_tag: image-classification
|
|
|
35 |
|
36 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
37 |
|---|---|---|---|---|---|---|---|---|
|
38 |
+
| Swin-Small | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 18.651 ms | 0 - 3 MB | FP16 | NPU | [Swin-Small.tflite](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.tflite) |
|
39 |
+
| Swin-Small | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 21.479 ms | 0 - 41 MB | FP16 | NPU | [Swin-Small.so](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.so) |
|
40 |
+
| Swin-Small | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 34.608 ms | 1 - 4 MB | FP16 | NPU | [Swin-Small.onnx](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.onnx) |
|
41 |
+
| Swin-Small | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 12.878 ms | 0 - 530 MB | FP16 | NPU | [Swin-Small.tflite](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.tflite) |
|
42 |
+
| Swin-Small | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 14.308 ms | 0 - 159 MB | FP16 | NPU | [Swin-Small.so](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.so) |
|
43 |
+
| Swin-Small | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 23.516 ms | 1 - 787 MB | FP16 | NPU | [Swin-Small.onnx](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.onnx) |
|
44 |
+
| Swin-Small | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 11.718 ms | 0 - 235 MB | FP16 | NPU | [Swin-Small.tflite](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.tflite) |
|
45 |
+
| Swin-Small | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 12.458 ms | 1 - 161 MB | FP16 | NPU | Use Export Script |
|
46 |
+
| Swin-Small | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 20.34 ms | 0 - 312 MB | FP16 | NPU | [Swin-Small.onnx](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.onnx) |
|
47 |
+
| Swin-Small | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 18.679 ms | 0 - 3 MB | FP16 | NPU | [Swin-Small.tflite](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.tflite) |
|
48 |
+
| Swin-Small | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 20.284 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
|
49 |
+
| Swin-Small | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 18.703 ms | 0 - 2 MB | FP16 | NPU | [Swin-Small.tflite](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.tflite) |
|
50 |
+
| Swin-Small | SA8255 (Proxy) | SA8255P Proxy | QNN | 20.488 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
|
51 |
+
| Swin-Small | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 18.696 ms | 0 - 3 MB | FP16 | NPU | [Swin-Small.tflite](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.tflite) |
|
52 |
+
| Swin-Small | SA8775 (Proxy) | SA8775P Proxy | QNN | 20.631 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
|
53 |
+
| Swin-Small | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 18.789 ms | 0 - 3 MB | FP16 | NPU | [Swin-Small.tflite](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.tflite) |
|
54 |
+
| Swin-Small | SA8650 (Proxy) | SA8650P Proxy | QNN | 20.64 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
|
55 |
+
| Swin-Small | SA8295P ADP | SA8295P | TFLITE | 27.079 ms | 0 - 215 MB | FP16 | NPU | [Swin-Small.tflite](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.tflite) |
|
56 |
+
| Swin-Small | SA8295P ADP | SA8295P | QNN | 28.916 ms | 1 - 6 MB | FP16 | NPU | Use Export Script |
|
57 |
+
| Swin-Small | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 24.173 ms | 0 - 510 MB | FP16 | NPU | [Swin-Small.tflite](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.tflite) |
|
58 |
+
| Swin-Small | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 25.787 ms | 0 - 153 MB | FP16 | NPU | Use Export Script |
|
59 |
+
| Swin-Small | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 21.288 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
|
60 |
+
| Swin-Small | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 38.045 ms | 118 - 118 MB | FP16 | NPU | [Swin-Small.onnx](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.onnx) |
|
61 |
|
62 |
|
63 |
|
|
|
122 |
Device : Samsung Galaxy S23 (13)
|
123 |
Runtime : TFLITE
|
124 |
Estimated inference time (ms) : 18.7
|
125 |
+
Estimated peak memory usage (MB): [0, 3]
|
126 |
Total # Ops : 1563
|
127 |
Compute Unit(s) : NPU (1563 ops)
|
128 |
```
|