Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -35,39 +35,39 @@ More details on model performance across various devices, can be found
|
|
| 35 |
|
| 36 |
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|
| 37 |
|---|---|---|---|---|---|---|---|---|
|
| 38 |
-
| Swin-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 62.
|
| 39 |
-
| Swin-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 59.
|
| 40 |
-
| Swin-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 29.
|
| 41 |
-
| Swin-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 39.
|
| 42 |
-
| Swin-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 22.
|
| 43 |
-
| Swin-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 21.
|
| 44 |
-
| Swin-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 25.
|
| 45 |
-
| Swin-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 24.
|
| 46 |
-
| Swin-Base | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 62.
|
| 47 |
-
| Swin-Base | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 59.
|
| 48 |
-
| Swin-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 22.
|
| 49 |
-
| Swin-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 21.
|
| 50 |
-
| Swin-Base | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 32.
|
| 51 |
-
| Swin-Base | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 30.
|
| 52 |
-
| Swin-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 22.
|
| 53 |
-
| Swin-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 21.
|
| 54 |
-
| Swin-Base | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 25.
|
| 55 |
-
| Swin-Base | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 24.
|
| 56 |
-
| Swin-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 22.
|
| 57 |
-
| Swin-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 21.
|
| 58 |
-
| Swin-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 19.
|
| 59 |
-
| Swin-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 15.
|
| 60 |
-
| Swin-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 15.
|
| 61 |
-
| Swin-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 13.
|
| 62 |
-
| Swin-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 14.
|
| 63 |
-
| Swin-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 13.
|
| 64 |
-
| Swin-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 12.
|
| 65 |
-
| Swin-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 22.
|
| 66 |
-
| Swin-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 23.
|
| 67 |
-
| Swin-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX |
|
| 68 |
-
| Swin-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX |
|
| 69 |
-
| Swin-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX |
|
| 70 |
-
| Swin-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX |
|
| 71 |
|
| 72 |
|
| 73 |
|
|
@@ -132,7 +132,7 @@ Swin-Base
|
|
| 132 |
Device : cs_8275 (ANDROID 14)
|
| 133 |
Runtime : TFLITE
|
| 134 |
Estimated inference time (ms) : 62.2
|
| 135 |
-
Estimated peak memory usage (MB): [0,
|
| 136 |
Total # Ops : 1568
|
| 137 |
Compute Unit(s) : npu (1568 ops) gpu (0 ops) cpu (0 ops)
|
| 138 |
```
|
|
|
|
| 35 |
|
| 36 |
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|
| 37 |
|---|---|---|---|---|---|---|---|---|
|
| 38 |
+
| Swin-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 62.23 ms | 0 - 373 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 39 |
+
| Swin-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 59.666 ms | 0 - 9 MB | NPU | Use Export Script |
|
| 40 |
+
| Swin-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 29.254 ms | 0 - 376 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 41 |
+
| Swin-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 39.504 ms | 0 - 459 MB | NPU | Use Export Script |
|
| 42 |
+
| Swin-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 22.158 ms | 0 - 27 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 43 |
+
| Swin-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 21.675 ms | 1 - 3 MB | NPU | Use Export Script |
|
| 44 |
+
| Swin-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 25.848 ms | 0 - 372 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 45 |
+
| Swin-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 24.659 ms | 1 - 10 MB | NPU | Use Export Script |
|
| 46 |
+
| Swin-Base | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 62.23 ms | 0 - 373 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 47 |
+
| Swin-Base | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 59.666 ms | 0 - 9 MB | NPU | Use Export Script |
|
| 48 |
+
| Swin-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 22.431 ms | 0 - 34 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 49 |
+
| Swin-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 21.575 ms | 1 - 3 MB | NPU | Use Export Script |
|
| 50 |
+
| Swin-Base | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 32.143 ms | 0 - 361 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 51 |
+
| Swin-Base | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 30.635 ms | 1 - 18 MB | NPU | Use Export Script |
|
| 52 |
+
| Swin-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 22.379 ms | 2 - 27 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 53 |
+
| Swin-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 21.679 ms | 1 - 4 MB | NPU | Use Export Script |
|
| 54 |
+
| Swin-Base | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 25.848 ms | 0 - 372 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 55 |
+
| Swin-Base | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 24.659 ms | 1 - 10 MB | NPU | Use Export Script |
|
| 56 |
+
| Swin-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 22.509 ms | 0 - 26 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 57 |
+
| Swin-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 21.694 ms | 0 - 40 MB | NPU | Use Export Script |
|
| 58 |
+
| Swin-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 19.727 ms | 0 - 350 MB | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx) |
|
| 59 |
+
| Swin-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 15.762 ms | 0 - 381 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 60 |
+
| Swin-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 15.096 ms | 1 - 376 MB | NPU | Use Export Script |
|
| 61 |
+
| Swin-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 13.65 ms | 0 - 372 MB | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx) |
|
| 62 |
+
| Swin-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 14.649 ms | 0 - 373 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 63 |
+
| Swin-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 13.519 ms | 1 - 329 MB | NPU | Use Export Script |
|
| 64 |
+
| Swin-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 12.482 ms | 1 - 330 MB | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx) |
|
| 65 |
+
| Swin-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 22.08 ms | 1 - 1 MB | NPU | Use Export Script |
|
| 66 |
+
| Swin-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 23.174 ms | 175 - 175 MB | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx) |
|
| 67 |
+
| Swin-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 164.529 ms | 642 - 924 MB | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx) |
|
| 68 |
+
| Swin-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 131.523 ms | 661 - 957 MB | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx) |
|
| 69 |
+
| Swin-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 126.776 ms | 638 - 908 MB | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx) |
|
| 70 |
+
| Swin-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 174.936 ms | 985 - 985 MB | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx) |
|
| 71 |
|
| 72 |
|
| 73 |
|
|
|
|
| 132 |
Device : cs_8275 (ANDROID 14)
|
| 133 |
Runtime : TFLITE
|
| 134 |
Estimated inference time (ms) : 62.2
|
| 135 |
+
Estimated peak memory usage (MB): [0, 373]
|
| 136 |
Total # Ops : 1568
|
| 137 |
Compute Unit(s) : npu (1568 ops) gpu (0 ops) cpu (0 ops)
|
| 138 |
```
|