v0.44.0
Browse filesSee https://github.com/quic/ai-hub-models/releases/v0.44.0 for changelog.
- DEPLOYMENT_MODEL_LICENSE.pdf +0 -3
- LICENSE +0 -1
- README.md +64 -62
- Segformer-Base_float.dlc +1 -1
- Segformer-Base_float.onnx.zip +2 -2
- Segformer-Base_float.tflite +2 -2
- Segformer-Base_w8a16.onnx.zip +2 -2
- Segformer-Base_w8a8.onnx.zip +2 -2
- Segformer-Base_w8a8.tflite +2 -2
DEPLOYMENT_MODEL_LICENSE.pdf
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
|
| 3 |
-
size 109629
|
|
|
|
|
|
|
|
|
|
|
|
LICENSE
CHANGED
|
@@ -1,2 +1 @@
|
|
| 1 |
The license of the original trained model can be found at https://github.com/huggingface/transformers/blob/main/LICENSE.
|
| 2 |
-
The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.
|
|
|
|
| 1 |
The license of the original trained model can be found at https://github.com/huggingface/transformers/blob/main/LICENSE.
|
|
|
README.md
CHANGED
|
@@ -39,67 +39,70 @@ More details on model performance across various devices, can be found
|
|
| 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 |
|
| 43 |
-
| Segformer-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC |
|
| 44 |
-
| Segformer-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE |
|
| 45 |
-
| Segformer-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC |
|
| 46 |
-
| Segformer-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE |
|
| 47 |
-
| Segformer-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 109.
|
| 48 |
-
| Segformer-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 108.
|
| 49 |
-
| Segformer-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE |
|
| 50 |
-
| Segformer-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC |
|
| 51 |
-
| Segformer-Base | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE |
|
| 52 |
-
| Segformer-Base | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC |
|
| 53 |
-
| Segformer-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE |
|
| 54 |
-
| Segformer-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 109.
|
| 55 |
-
| Segformer-Base | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE |
|
| 56 |
-
| Segformer-Base | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC |
|
| 57 |
-
| Segformer-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE |
|
| 58 |
-
| Segformer-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 109.
|
| 59 |
-
| Segformer-Base | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE |
|
| 60 |
-
| Segformer-Base | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC |
|
| 61 |
-
| Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 83.
|
| 62 |
-
| Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 83.
|
| 63 |
-
| Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 83.
|
| 64 |
-
| Segformer-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 74.
|
| 65 |
-
| Segformer-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 74.
|
| 66 |
-
| Segformer-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 74.
|
| 67 |
-
| Segformer-Base | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 73.
|
| 68 |
-
| Segformer-Base | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC |
|
| 69 |
-
| Segformer-Base | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX |
|
| 70 |
-
| Segformer-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 113.
|
| 71 |
-
| Segformer-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 112.
|
| 72 |
-
| Segformer-Base | w8a16 | Dragonwing
|
| 73 |
-
| Segformer-Base | w8a16 |
|
| 74 |
-
| Segformer-Base | w8a16 |
|
| 75 |
-
| Segformer-Base | w8a16 |
|
| 76 |
-
| Segformer-Base | w8a16 | Samsung Galaxy
|
| 77 |
-
| Segformer-Base | w8a16 |
|
| 78 |
-
| Segformer-Base | w8a16 | Snapdragon
|
| 79 |
-
| Segformer-Base | w8a16 | Snapdragon
|
| 80 |
-
| Segformer-Base |
|
| 81 |
-
| Segformer-Base | w8a8 | Dragonwing
|
| 82 |
-
| Segformer-Base | w8a8 |
|
| 83 |
-
| Segformer-Base | w8a8 |
|
| 84 |
-
| Segformer-Base | w8a8 |
|
| 85 |
-
| Segformer-Base | w8a8 |
|
| 86 |
-
| Segformer-Base | w8a8 |
|
| 87 |
-
| Segformer-Base | w8a8 |
|
| 88 |
-
| Segformer-Base | w8a8 |
|
| 89 |
-
| Segformer-Base | w8a8 |
|
| 90 |
-
| Segformer-Base | w8a8 |
|
| 91 |
-
| Segformer-Base | w8a8 |
|
| 92 |
-
| Segformer-Base | w8a8 |
|
| 93 |
-
| Segformer-Base | w8a8 |
|
| 94 |
-
| Segformer-Base | w8a8 |
|
| 95 |
-
| Segformer-Base | w8a8 |
|
| 96 |
-
| Segformer-Base | w8a8 |
|
| 97 |
-
| Segformer-Base | w8a8 | Samsung Galaxy
|
| 98 |
-
| Segformer-Base | w8a8 |
|
| 99 |
-
| Segformer-Base | w8a8 |
|
| 100 |
-
| Segformer-Base | w8a8 |
|
| 101 |
-
| Segformer-Base | w8a8 | Snapdragon
|
| 102 |
-
| Segformer-Base | w8a8 | Snapdragon
|
|
|
|
|
|
|
|
|
|
| 103 |
|
| 104 |
|
| 105 |
|
|
@@ -275,7 +278,6 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
|
|
| 275 |
## License
|
| 276 |
* The license for the original implementation of Segformer-Base can be found
|
| 277 |
[here](https://github.com/huggingface/transformers/blob/main/LICENSE).
|
| 278 |
-
* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
|
| 279 |
|
| 280 |
|
| 281 |
|
|
|
|
| 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 | 212.895 ms | 9 - 166 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 | 212.792 ms | 1 - 158 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 | 123.547 ms | 10 - 210 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 | 123.575 ms | 3 - 203 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 | 109.256 ms | 10 - 12 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 | 109.663 ms | 3 - 5 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 48 |
+
| Segformer-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 108.66 ms | 19 - 28 MB | NPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx.zip) |
|
| 49 |
+
| Segformer-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 111.372 ms | 9 - 166 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 50 |
+
| Segformer-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 516.664 ms | 1 - 157 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 51 |
+
| Segformer-Base | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 212.895 ms | 9 - 166 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 52 |
+
| Segformer-Base | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 212.792 ms | 1 - 158 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 53 |
+
| Segformer-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 109.47 ms | 9 - 12 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 54 |
+
| Segformer-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 109.38 ms | 3 - 5 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 55 |
+
| Segformer-Base | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 125.11 ms | 9 - 172 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 56 |
+
| Segformer-Base | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 125.031 ms | 0 - 163 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 57 |
+
| Segformer-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 109.279 ms | 10 - 12 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 58 |
+
| Segformer-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 109.299 ms | 3 - 5 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 59 |
+
| Segformer-Base | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 111.372 ms | 9 - 166 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 60 |
+
| Segformer-Base | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 516.664 ms | 1 - 157 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 61 |
+
| Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 83.718 ms | 8 - 208 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 62 |
+
| Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 83.866 ms | 3 - 205 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 63 |
+
| Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 83.68 ms | 27 - 206 MB | NPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx.zip) |
|
| 64 |
+
| Segformer-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 74.648 ms | 9 - 174 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 65 |
+
| Segformer-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 74.878 ms | 3 - 167 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 66 |
+
| Segformer-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 74.659 ms | 20 - 161 MB | NPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx.zip) |
|
| 67 |
+
| Segformer-Base | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 73.639 ms | 8 - 172 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
|
| 68 |
+
| Segformer-Base | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 73.745 ms | 3 - 167 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 69 |
+
| Segformer-Base | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 74.457 ms | 24 - 170 MB | NPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx.zip) |
|
| 70 |
+
| Segformer-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 113.886 ms | 3 - 3 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
|
| 71 |
+
| Segformer-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 112.87 ms | 33 - 33 MB | NPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx.zip) |
|
| 72 |
+
| Segformer-Base | w8a16 | Dragonwing Q-6690 MTP | Qualcomm® Qcm6690 | ONNX | 490.192 ms | 361 - 378 MB | CPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx.zip) |
|
| 73 |
+
| Segformer-Base | w8a16 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | ONNX | 829.11 ms | 379 - 385 MB | CPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx.zip) |
|
| 74 |
+
| Segformer-Base | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 61.739 ms | 88 - 90 MB | NPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx.zip) |
|
| 75 |
+
| Segformer-Base | w8a16 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 365.061 ms | 374 - 379 MB | CPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx.zip) |
|
| 76 |
+
| Segformer-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 49.337 ms | 89 - 274 MB | NPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx.zip) |
|
| 77 |
+
| Segformer-Base | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 45.932 ms | 89 - 226 MB | NPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx.zip) |
|
| 78 |
+
| Segformer-Base | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | ONNX | 412.126 ms | 355 - 374 MB | CPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx.zip) |
|
| 79 |
+
| Segformer-Base | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 39.861 ms | 91 - 226 MB | NPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx.zip) |
|
| 80 |
+
| Segformer-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 52.548 ms | 131 - 131 MB | NPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx.zip) |
|
| 81 |
+
| Segformer-Base | w8a8 | Dragonwing Q-6690 MTP | Qualcomm® Qcm6690 | TFLITE | 145.585 ms | 15 - 165 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 82 |
+
| Segformer-Base | w8a8 | Dragonwing Q-6690 MTP | Qualcomm® Qcm6690 | ONNX | 207.965 ms | 201 - 217 MB | CPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx.zip) |
|
| 83 |
+
| Segformer-Base | w8a8 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | TFLITE | 146.328 ms | 13 - 48 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 84 |
+
| Segformer-Base | w8a8 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | ONNX | 358.036 ms | 200 - 207 MB | CPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx.zip) |
|
| 85 |
+
| Segformer-Base | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 22.055 ms | 3 - 152 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 86 |
+
| Segformer-Base | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 19.223 ms | 2 - 188 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 87 |
+
| Segformer-Base | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 13.076 ms | 2 - 5 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 88 |
+
| Segformer-Base | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 52.539 ms | 48 - 53 MB | NPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx.zip) |
|
| 89 |
+
| Segformer-Base | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 13.519 ms | 2 - 152 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 90 |
+
| Segformer-Base | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 65.718 ms | 13 - 39 MB | GPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 91 |
+
| Segformer-Base | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 189.527 ms | 190 - 196 MB | CPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx.zip) |
|
| 92 |
+
| Segformer-Base | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 22.055 ms | 3 - 152 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 93 |
+
| Segformer-Base | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 12.986 ms | 2 - 5 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 94 |
+
| Segformer-Base | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 16.019 ms | 2 - 159 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 95 |
+
| Segformer-Base | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 13.069 ms | 2 - 5 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 96 |
+
| Segformer-Base | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 13.519 ms | 2 - 152 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 97 |
+
| Segformer-Base | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 9.05 ms | 2 - 189 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 98 |
+
| Segformer-Base | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 41.879 ms | 58 - 222 MB | NPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx.zip) |
|
| 99 |
+
| Segformer-Base | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 7.706 ms | 2 - 158 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 100 |
+
| Segformer-Base | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 40.541 ms | 58 - 184 MB | NPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx.zip) |
|
| 101 |
+
| Segformer-Base | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | TFLITE | 48.591 ms | 15 - 164 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 102 |
+
| Segformer-Base | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | ONNX | 191.501 ms | 199 - 217 MB | CPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx.zip) |
|
| 103 |
+
| Segformer-Base | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 6.625 ms | 1 - 154 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
|
| 104 |
+
| Segformer-Base | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 37.306 ms | 57 - 185 MB | NPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx.zip) |
|
| 105 |
+
| Segformer-Base | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 44.969 ms | 65 - 65 MB | NPU | [Segformer-Base.onnx.zip](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx.zip) |
|
| 106 |
|
| 107 |
|
| 108 |
|
|
|
|
| 278 |
## License
|
| 279 |
* The license for the original implementation of Segformer-Base can be found
|
| 280 |
[here](https://github.com/huggingface/transformers/blob/main/LICENSE).
|
|
|
|
| 281 |
|
| 282 |
|
| 283 |
|
Segformer-Base_float.dlc
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15339444
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18b6ee099f1ee048e78ddb5bcacff30586911fce5045d3f4e80960dbc55f2bab
|
| 3 |
size 15339444
|
Segformer-Base_float.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 sha256:91f7eeaa7ca19c788d73328b2db09ed47e2ece444898f4f2034ffcf5a89b3281
|
| 3 |
+
size 13994809
|
Segformer-Base_float.tflite
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 sha256:5b8422594eac5dfc10c970d954cf6b98f0f90e35810e720583d4980dd6fc1969
|
| 3 |
+
size 15113552
|
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:a8ca0575cb1312db5cf443d678a4764bfb9be18b121ca8a89d94b74d0a27086d
|
| 3 |
+
size 10824759
|
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 sha256:72ec200260c82878393aa9cdef70b3edf7dd52b39538cdc090b6c91820824e33
|
| 3 |
+
size 10828356
|
Segformer-Base_w8a8.tflite
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:e3416ac8d28906d6024fdcc1d3b9519080d460c55d14c34aef95c9c091dce244
|
| 3 |
+
size 4092896
|