v0.34.0
Browse filesSee https://github.com/quic/ai-hub-models/releases/v0.34.0 for changelog.
- README.md +54 -63
- Segformer-Base_w8a16.dlc +1 -1
- Segformer-Base_w8a8.dlc +1 -1
- precompiled/qualcomm-qcs6490-proxy/sdk_versions.yml +3 -0
- precompiled/qualcomm-snapdragon-x-elite/Segformer-Base.onnx.zip +1 -1
- precompiled/qualcomm-snapdragon-x-elite/Segformer-Base_w8a16.onnx.zip +2 -2
- precompiled/qualcomm-snapdragon-x-elite/Segformer-Base_w8a8.onnx.zip +2 -2
- precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml +5 -0
README.md
CHANGED
|
@@ -24,6 +24,7 @@ More details on model performance across various devices, can be found
|
|
| 24 |
[here](https://aihub.qualcomm.com/models/segformer_base).
|
| 25 |
|
| 26 |
|
|
|
|
| 27 |
### Model Details
|
| 28 |
|
| 29 |
- **Model Type:** Model_use_case.semantic_segmentation
|
|
@@ -38,84 +39,84 @@ More details on model performance across various devices, can be found
|
|
| 38 |
|
| 39 |
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|
| 40 |
|---|---|---|---|---|---|---|---|---|
|
| 41 |
-
| Segformer-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 218.
|
| 42 |
| Segformer-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 214.118 ms | 3 - 47 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 43 |
-
| Segformer-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 112.
|
| 44 |
| Segformer-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 111.857 ms | 3 - 59 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 45 |
-
| Segformer-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 111.
|
| 46 |
| Segformer-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 107.503 ms | 3 - 19 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 47 |
-
| Segformer-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 114.
|
| 48 |
| Segformer-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 110.089 ms | 3 - 49 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 49 |
-
| Segformer-Base | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 218.
|
| 50 |
| Segformer-Base | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 214.118 ms | 3 - 47 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 51 |
-
| Segformer-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 111.
|
| 52 |
| Segformer-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 107.559 ms | 4 - 25 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 53 |
-
| Segformer-Base | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 124.
|
| 54 |
| Segformer-Base | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 121.413 ms | 2 - 50 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 55 |
-
| Segformer-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 111.
|
| 56 |
| Segformer-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 108.177 ms | 2 - 18 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 57 |
-
| Segformer-Base | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 114.
|
| 58 |
| Segformer-Base | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 110.089 ms | 3 - 49 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 59 |
-
| Segformer-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 111.
|
| 60 |
| Segformer-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 107.49 ms | 3 - 17 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 61 |
| Segformer-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 110.766 ms | 19 - 52 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
|
| 62 |
-
| Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 83.
|
| 63 |
| Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 82.171 ms | 3 - 57 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 64 |
| Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 83.613 ms | 23 - 82 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
|
| 65 |
-
| Segformer-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 96.
|
| 66 |
| Segformer-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 91.582 ms | 3 - 55 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 67 |
| Segformer-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 94.185 ms | 26 - 73 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
|
| 68 |
| Segformer-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 115.101 ms | 3 - 3 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 69 |
| Segformer-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 118.39 ms | 33 - 33 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
|
| 70 |
| Segformer-Base | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 21.798 ms | 2 - 36 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 71 |
-
| Segformer-Base | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 14.
|
| 72 |
-
| Segformer-Base | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC |
|
| 73 |
-
| Segformer-Base | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 12.
|
| 74 |
-
| Segformer-Base | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC |
|
| 75 |
| Segformer-Base | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 21.798 ms | 2 - 36 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 76 |
-
| Segformer-Base | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 12.
|
| 77 |
-
| Segformer-Base | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 14.
|
| 78 |
-
| Segformer-Base | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 12.
|
| 79 |
-
| Segformer-Base | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 12.
|
| 80 |
-
| Segformer-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 12.
|
| 81 |
| Segformer-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 39.266 ms | 28 - 107 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
|
| 82 |
-
| Segformer-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 7.
|
| 83 |
| Segformer-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 28.437 ms | 30 - 290 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
|
| 84 |
-
| Segformer-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 7.
|
| 85 |
| Segformer-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 28.693 ms | 27 - 239 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
|
| 86 |
-
| Segformer-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 13.
|
| 87 |
| Segformer-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 44.478 ms | 58 - 58 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
|
| 88 |
-
| Segformer-Base | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 23.
|
| 89 |
-
| Segformer-Base | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 12.
|
| 90 |
-
| Segformer-Base | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 13.
|
| 91 |
-
| Segformer-Base | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC |
|
| 92 |
-
| Segformer-Base | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 12.
|
| 93 |
-
| Segformer-Base | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 6.
|
| 94 |
-
| Segformer-Base | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 13.
|
| 95 |
-
| Segformer-Base | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 7.
|
| 96 |
-
| Segformer-Base | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE |
|
| 97 |
-
| Segformer-Base | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC |
|
| 98 |
-
| Segformer-Base | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE |
|
| 99 |
-
| Segformer-Base | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 23.
|
| 100 |
-
| Segformer-Base | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 12.
|
| 101 |
-
| Segformer-Base | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 12.
|
| 102 |
-
| Segformer-Base | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 6.
|
| 103 |
-
| Segformer-Base | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 15.
|
| 104 |
-
| Segformer-Base | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 8.
|
| 105 |
-
| Segformer-Base | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 12.
|
| 106 |
-
| Segformer-Base | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 6.
|
| 107 |
-
| Segformer-Base | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 13.
|
| 108 |
-
| Segformer-Base | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 7.
|
| 109 |
-
| Segformer-Base | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 12.
|
| 110 |
-
| Segformer-Base | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 6.
|
| 111 |
| Segformer-Base | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 53.658 ms | 19 - 43 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
|
| 112 |
-
| Segformer-Base | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 8.
|
| 113 |
-
| Segformer-Base | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 4.
|
| 114 |
| Segformer-Base | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 40.405 ms | 22 - 87 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
|
| 115 |
-
| Segformer-Base | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 9.
|
| 116 |
-
| Segformer-Base | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC |
|
| 117 |
| Segformer-Base | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 39.888 ms | 21 - 82 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
|
| 118 |
-
| Segformer-Base | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 7.
|
| 119 |
| Segformer-Base | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 59.784 ms | 29 - 29 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
|
| 120 |
|
| 121 |
|
|
@@ -174,17 +175,7 @@ device. This script does the following:
|
|
| 174 |
```bash
|
| 175 |
python -m qai_hub_models.models.segformer_base.export
|
| 176 |
```
|
| 177 |
-
|
| 178 |
-
Profiling Results
|
| 179 |
-
------------------------------------------------------------
|
| 180 |
-
Segformer-Base
|
| 181 |
-
Device : cs_8275 (ANDROID 14)
|
| 182 |
-
Runtime : TFLITE
|
| 183 |
-
Estimated inference time (ms) : 218.1
|
| 184 |
-
Estimated peak memory usage (MB): [7, 56]
|
| 185 |
-
Total # Ops : 544
|
| 186 |
-
Compute Unit(s) : npu (544 ops) gpu (0 ops) cpu (0 ops)
|
| 187 |
-
```
|
| 188 |
|
| 189 |
|
| 190 |
## How does this work?
|
|
|
|
| 24 |
[here](https://aihub.qualcomm.com/models/segformer_base).
|
| 25 |
|
| 26 |
|
| 27 |
+
|
| 28 |
### Model Details
|
| 29 |
|
| 30 |
- **Model Type:** Model_use_case.semantic_segmentation
|
|
|
|
| 39 |
|
| 40 |
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|
| 41 |
|---|---|---|---|---|---|---|---|---|
|
| 42 |
+
| Segformer-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 218.079 ms | 9 - 58 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 43 |
| Segformer-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 214.118 ms | 3 - 47 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 44 |
+
| Segformer-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 112.493 ms | 9 - 64 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 45 |
| Segformer-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 111.857 ms | 3 - 59 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 46 |
+
| Segformer-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 111.635 ms | 9 - 27 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 47 |
| Segformer-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 107.503 ms | 3 - 19 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 48 |
+
| Segformer-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 114.354 ms | 9 - 58 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 49 |
| Segformer-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 110.089 ms | 3 - 49 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 50 |
+
| Segformer-Base | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 218.079 ms | 9 - 58 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 51 |
| Segformer-Base | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 214.118 ms | 3 - 47 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 52 |
+
| Segformer-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 111.53 ms | 9 - 22 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 53 |
| Segformer-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 107.559 ms | 4 - 25 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 54 |
+
| Segformer-Base | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 124.248 ms | 9 - 59 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 55 |
| Segformer-Base | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 121.413 ms | 2 - 50 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 56 |
+
| Segformer-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 111.782 ms | 10 - 27 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 57 |
| Segformer-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 108.177 ms | 2 - 18 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 58 |
+
| Segformer-Base | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 114.354 ms | 9 - 58 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 59 |
| Segformer-Base | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 110.089 ms | 3 - 49 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 60 |
+
| Segformer-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 111.94 ms | 9 - 22 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 61 |
| Segformer-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 107.49 ms | 3 - 17 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 62 |
| Segformer-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 110.766 ms | 19 - 52 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
|
| 63 |
+
| Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 83.418 ms | 23 - 84 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 64 |
| Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 82.171 ms | 3 - 57 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 65 |
| Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 83.613 ms | 23 - 82 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
|
| 66 |
+
| Segformer-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 96.694 ms | 8 - 60 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 67 |
| Segformer-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 91.582 ms | 3 - 55 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 68 |
| Segformer-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 94.185 ms | 26 - 73 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
|
| 69 |
| Segformer-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 115.101 ms | 3 - 3 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 70 |
| Segformer-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 118.39 ms | 33 - 33 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
|
| 71 |
| Segformer-Base | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 21.798 ms | 2 - 36 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 72 |
+
| Segformer-Base | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 14.257 ms | 2 - 44 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 73 |
+
| Segformer-Base | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 12.002 ms | 2 - 13 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 74 |
+
| Segformer-Base | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 12.753 ms | 2 - 43 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 75 |
+
| Segformer-Base | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 42.921 ms | 2 - 69 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 76 |
| Segformer-Base | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 21.798 ms | 2 - 36 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 77 |
+
| Segformer-Base | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 12.067 ms | 0 - 16 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 78 |
+
| Segformer-Base | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 14.388 ms | 1 - 38 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 79 |
+
| Segformer-Base | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 12.036 ms | 2 - 14 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 80 |
+
| Segformer-Base | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 12.753 ms | 2 - 43 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 81 |
+
| Segformer-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 12.033 ms | 2 - 18 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 82 |
| Segformer-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 39.266 ms | 28 - 107 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
|
| 83 |
+
| Segformer-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 7.925 ms | 2 - 48 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 84 |
| Segformer-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 28.437 ms | 30 - 290 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
|
| 85 |
+
| Segformer-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 7.361 ms | 2 - 44 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 86 |
| Segformer-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 28.693 ms | 27 - 239 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
|
| 87 |
+
| Segformer-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 13.085 ms | 0 - 0 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
|
| 88 |
| Segformer-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 44.478 ms | 58 - 58 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
|
| 89 |
+
| Segformer-Base | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 23.197 ms | 2 - 40 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 90 |
+
| Segformer-Base | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 12.531 ms | 1 - 33 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
|
| 91 |
+
| Segformer-Base | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 13.33 ms | 2 - 48 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 92 |
+
| Segformer-Base | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 7.891 ms | 1 - 42 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
|
| 93 |
+
| Segformer-Base | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 12.944 ms | 2 - 18 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 94 |
+
| Segformer-Base | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 6.918 ms | 1 - 12 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
|
| 95 |
+
| Segformer-Base | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 13.503 ms | 2 - 41 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 96 |
+
| Segformer-Base | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 7.56 ms | 1 - 35 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
|
| 97 |
+
| Segformer-Base | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 134.4 ms | 15 - 56 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 98 |
+
| Segformer-Base | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 25.991 ms | 1 - 48 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
|
| 99 |
+
| Segformer-Base | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 363.712 ms | 13 - 29 MB | CPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 100 |
+
| Segformer-Base | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 23.197 ms | 2 - 40 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 101 |
+
| Segformer-Base | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 12.531 ms | 1 - 33 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
|
| 102 |
+
| Segformer-Base | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 12.935 ms | 2 - 14 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 103 |
+
| Segformer-Base | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 6.906 ms | 1 - 10 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
|
| 104 |
+
| Segformer-Base | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 15.162 ms | 2 - 42 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 105 |
+
| Segformer-Base | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 8.718 ms | 1 - 35 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
|
| 106 |
+
| Segformer-Base | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 12.927 ms | 2 - 15 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 107 |
+
| Segformer-Base | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 6.92 ms | 1 - 10 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
|
| 108 |
+
| Segformer-Base | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 13.503 ms | 2 - 41 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 109 |
+
| Segformer-Base | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 7.56 ms | 1 - 35 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
|
| 110 |
+
| Segformer-Base | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 12.932 ms | 2 - 13 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 111 |
+
| Segformer-Base | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 6.919 ms | 1 - 11 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
|
| 112 |
| Segformer-Base | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 53.658 ms | 19 - 43 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
|
| 113 |
+
| Segformer-Base | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 8.887 ms | 2 - 51 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 114 |
+
| Segformer-Base | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 4.627 ms | 1 - 47 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
|
| 115 |
| Segformer-Base | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 40.405 ms | 22 - 87 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
|
| 116 |
+
| Segformer-Base | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 9.066 ms | 0 - 42 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 117 |
+
| Segformer-Base | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 4.222 ms | 1 - 39 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
|
| 118 |
| Segformer-Base | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 39.888 ms | 21 - 82 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
|
| 119 |
+
| Segformer-Base | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 7.782 ms | 1 - 1 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
|
| 120 |
| Segformer-Base | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 59.784 ms | 29 - 29 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
|
| 121 |
|
| 122 |
|
|
|
|
| 175 |
```bash
|
| 176 |
python -m qai_hub_models.models.segformer_base.export
|
| 177 |
```
|
| 178 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 179 |
|
| 180 |
|
| 181 |
## How does this work?
|
Segformer-Base_w8a16.dlc
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4756690
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c155f93eb5cc7982549a90e3da134e420ec3a1f50334edeec4f7de4869f94760
|
| 3 |
size 4756690
|
Segformer-Base_w8a8.dlc
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4744427
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7223cfba767666719b522bc4e04a88a3677173b68c0b637dfb1056d5f17d10b
|
| 3 |
size 4744427
|
precompiled/qualcomm-qcs6490-proxy/sdk_versions.yml
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
sdk_versions:
|
| 2 |
+
qnn_context_binary:
|
| 3 |
+
qairt: 2.34.2.250528164111_119506
|
precompiled/qualcomm-snapdragon-x-elite/Segformer-Base.onnx.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7274034
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72ab1040db81dab355f471f9336b95f16495a2a77cb59644479555129cb3208a
|
| 3 |
size 7274034
|
precompiled/qualcomm-snapdragon-x-elite/Segformer-Base_w8a16.onnx.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce2f0125128c7615e8c73e5a316476716c60fbd433c4257b17336a6496cb7699
|
| 3 |
+
size 3993257
|
precompiled/qualcomm-snapdragon-x-elite/Segformer-Base_w8a8.onnx.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d8c27adab76ab6098b11cedfdd293511dd731fff4211a4fc14c4fc48e012ba3
|
| 3 |
+
size 3732516
|
precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
sdk_versions:
|
| 2 |
+
qnn_context_binary:
|
| 3 |
+
qairt: 2.34.2.250528164111_119506
|
| 4 |
+
precompiled_qnn_onnx:
|
| 5 |
+
qairt: 2.33.2.250410134701_117956
|