Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -34,38 +34,38 @@ More details on model performance across various devices, can be found
|
|
| 34 |
|
| 35 |
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|
| 36 |
|---|---|---|---|---|---|---|---|---|
|
| 37 |
-
| ConvNext-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 41.
|
| 38 |
-
| ConvNext-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 41.
|
| 39 |
-
| ConvNext-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 19.
|
| 40 |
-
| ConvNext-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 22.
|
| 41 |
-
| ConvNext-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.
|
| 42 |
-
| ConvNext-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 8.
|
| 43 |
-
| ConvNext-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 11.
|
| 44 |
-
| ConvNext-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 11.
|
| 45 |
-
| ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 7.
|
| 46 |
-
| ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 8.
|
| 47 |
-
| ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 7.
|
| 48 |
-
| ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.
|
| 49 |
-
| ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 6.
|
| 50 |
-
| ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX |
|
| 51 |
-
| ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 5.
|
| 52 |
-
| ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 5.
|
| 53 |
-
| ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 5.
|
| 54 |
-
| ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 8.
|
| 55 |
-
| ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 7.
|
| 56 |
-
| ConvNext-Base | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 14.
|
| 57 |
-
| ConvNext-Base | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 10.
|
| 58 |
-
| ConvNext-Base | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 5.
|
| 59 |
-
| ConvNext-Base | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 6.
|
| 60 |
-
| ConvNext-Base | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN |
|
| 61 |
-
| ConvNext-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 5.
|
| 62 |
-
| ConvNext-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX |
|
| 63 |
-
| ConvNext-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 4.
|
| 64 |
-
| ConvNext-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX |
|
| 65 |
-
| ConvNext-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 3.
|
| 66 |
-
| ConvNext-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX |
|
| 67 |
-
| ConvNext-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 6.
|
| 68 |
-
| ConvNext-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX |
|
| 69 |
|
| 70 |
|
| 71 |
|
|
@@ -130,7 +130,7 @@ ConvNext-Base
|
|
| 130 |
Device : cs_8275 (ANDROID 14)
|
| 131 |
Runtime : TFLITE
|
| 132 |
Estimated inference time (ms) : 41.8
|
| 133 |
-
Estimated peak memory usage (MB): [0,
|
| 134 |
Total # Ops : 598
|
| 135 |
Compute Unit(s) : npu (598 ops) gpu (0 ops) cpu (0 ops)
|
| 136 |
```
|
|
|
|
| 34 |
|
| 35 |
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|
| 36 |
|---|---|---|---|---|---|---|---|---|
|
| 37 |
+
| ConvNext-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 41.836 ms | 0 - 259 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
|
| 38 |
+
| ConvNext-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 41.709 ms | 1 - 10 MB | NPU | Use Export Script |
|
| 39 |
+
| ConvNext-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 19.132 ms | 0 - 274 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
|
| 40 |
+
| ConvNext-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 22.92 ms | 0 - 277 MB | NPU | Use Export Script |
|
| 41 |
+
| ConvNext-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.451 ms | 0 - 22 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
|
| 42 |
+
| ConvNext-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 8.032 ms | 1 - 4 MB | NPU | Use Export Script |
|
| 43 |
+
| ConvNext-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 11.536 ms | 0 - 257 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
|
| 44 |
+
| ConvNext-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 11.899 ms | 1 - 11 MB | NPU | Use Export Script |
|
| 45 |
+
| ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 7.468 ms | 0 - 21 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
|
| 46 |
+
| ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 8.068 ms | 0 - 19 MB | NPU | Use Export Script |
|
| 47 |
+
| ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 7.875 ms | 0 - 441 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
|
| 48 |
+
| ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.563 ms | 0 - 269 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
|
| 49 |
+
| ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 6.112 ms | 1 - 276 MB | NPU | Use Export Script |
|
| 50 |
+
| ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.981 ms | 1 - 284 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
|
| 51 |
+
| ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 5.05 ms | 0 - 262 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
|
| 52 |
+
| ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 5.187 ms | 1 - 268 MB | NPU | Use Export Script |
|
| 53 |
+
| ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 5.278 ms | 0 - 267 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
|
| 54 |
+
| ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 8.118 ms | 1 - 1 MB | NPU | Use Export Script |
|
| 55 |
+
| ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 7.874 ms | 176 - 176 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
|
| 56 |
+
| ConvNext-Base | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 14.534 ms | 0 - 10 MB | NPU | Use Export Script |
|
| 57 |
+
| ConvNext-Base | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 10.036 ms | 0 - 129 MB | NPU | Use Export Script |
|
| 58 |
+
| ConvNext-Base | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 5.94 ms | 0 - 3 MB | NPU | Use Export Script |
|
| 59 |
+
| ConvNext-Base | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 6.152 ms | 0 - 12 MB | NPU | Use Export Script |
|
| 60 |
+
| ConvNext-Base | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 40.077 ms | 0 - 15 MB | NPU | Use Export Script |
|
| 61 |
+
| ConvNext-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 5.918 ms | 0 - 30 MB | NPU | Use Export Script |
|
| 62 |
+
| ConvNext-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 243.99 ms | 573 - 976 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
|
| 63 |
+
| ConvNext-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 4.168 ms | 0 - 130 MB | NPU | Use Export Script |
|
| 64 |
+
| ConvNext-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 181.977 ms | 684 - 1280 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
|
| 65 |
+
| ConvNext-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 3.611 ms | 0 - 122 MB | NPU | Use Export Script |
|
| 66 |
+
| ConvNext-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 180.001 ms | 695 - 1260 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
|
| 67 |
+
| ConvNext-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 6.253 ms | 0 - 0 MB | NPU | Use Export Script |
|
| 68 |
+
| ConvNext-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 231.81 ms | 924 - 924 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
|
| 69 |
|
| 70 |
|
| 71 |
|
|
|
|
| 130 |
Device : cs_8275 (ANDROID 14)
|
| 131 |
Runtime : TFLITE
|
| 132 |
Estimated inference time (ms) : 41.8
|
| 133 |
+
Estimated peak memory usage (MB): [0, 259]
|
| 134 |
Total # Ops : 598
|
| 135 |
Compute Unit(s) : npu (598 ops) gpu (0 ops) cpu (0 ops)
|
| 136 |
```
|