Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,6 +1,4 @@
|
|
| 1 |
---
|
| 2 |
-
datasets:
|
| 3 |
-
- VOC2012
|
| 4 |
library_name: pytorch
|
| 5 |
license: mit
|
| 6 |
pipeline_tag: image-segmentation
|
|
@@ -37,27 +35,29 @@ More details on model performance across various devices, can be found
|
|
| 37 |
|
| 38 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 39 |
|---|---|---|---|---|---|---|---|---|
|
| 40 |
-
| DeepLabV3-Plus-MobileNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 13.
|
| 41 |
-
| DeepLabV3-Plus-MobileNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 13.
|
| 42 |
-
| DeepLabV3-Plus-MobileNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 16.
|
| 43 |
-
| DeepLabV3-Plus-MobileNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE |
|
| 44 |
-
| DeepLabV3-Plus-MobileNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN |
|
| 45 |
-
| DeepLabV3-Plus-MobileNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX |
|
| 46 |
-
| DeepLabV3-Plus-MobileNet |
|
| 47 |
-
| DeepLabV3-Plus-MobileNet |
|
| 48 |
-
| DeepLabV3-Plus-MobileNet |
|
| 49 |
-
| DeepLabV3-Plus-MobileNet |
|
| 50 |
-
| DeepLabV3-Plus-MobileNet |
|
| 51 |
-
| DeepLabV3-Plus-MobileNet |
|
| 52 |
-
| DeepLabV3-Plus-MobileNet |
|
| 53 |
-
| DeepLabV3-Plus-MobileNet |
|
| 54 |
-
| DeepLabV3-Plus-MobileNet |
|
| 55 |
-
| DeepLabV3-Plus-MobileNet |
|
| 56 |
-
| DeepLabV3-Plus-MobileNet |
|
| 57 |
-
| DeepLabV3-Plus-MobileNet |
|
| 58 |
-
| DeepLabV3-Plus-MobileNet |
|
| 59 |
-
| DeepLabV3-Plus-MobileNet |
|
| 60 |
-
| DeepLabV3-Plus-MobileNet |
|
|
|
|
|
|
|
| 61 |
|
| 62 |
|
| 63 |
|
|
@@ -121,8 +121,8 @@ Profiling Results
|
|
| 121 |
DeepLabV3-Plus-MobileNet
|
| 122 |
Device : Samsung Galaxy S23 (13)
|
| 123 |
Runtime : TFLITE
|
| 124 |
-
Estimated inference time (ms) : 13.
|
| 125 |
-
Estimated peak memory usage (MB): [21,
|
| 126 |
Total # Ops : 98
|
| 127 |
Compute Unit(s) : NPU (98 ops)
|
| 128 |
```
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
library_name: pytorch
|
| 3 |
license: mit
|
| 4 |
pipeline_tag: image-segmentation
|
|
|
|
| 35 |
|
| 36 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 37 |
|---|---|---|---|---|---|---|---|---|
|
| 38 |
+
| DeepLabV3-Plus-MobileNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 13.28 ms | 21 - 23 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
|
| 39 |
+
| DeepLabV3-Plus-MobileNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 13.067 ms | 3 - 23 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.so](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.so) |
|
| 40 |
+
| DeepLabV3-Plus-MobileNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 16.956 ms | 42 - 55 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.onnx](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx) |
|
| 41 |
+
| DeepLabV3-Plus-MobileNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 9.517 ms | 21 - 99 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
|
| 42 |
+
| DeepLabV3-Plus-MobileNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 9.428 ms | 3 - 28 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.so](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.so) |
|
| 43 |
+
| DeepLabV3-Plus-MobileNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 13.939 ms | 45 - 128 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.onnx](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx) |
|
| 44 |
+
| DeepLabV3-Plus-MobileNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 9.295 ms | 21 - 58 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
|
| 45 |
+
| DeepLabV3-Plus-MobileNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 9.218 ms | 3 - 27 MB | FP16 | NPU | Use Export Script |
|
| 46 |
+
| DeepLabV3-Plus-MobileNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 12.333 ms | 20 - 59 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.onnx](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx) |
|
| 47 |
+
| DeepLabV3-Plus-MobileNet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 13.012 ms | 21 - 37 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
|
| 48 |
+
| DeepLabV3-Plus-MobileNet | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 12.013 ms | 2 - 4 MB | FP16 | NPU | Use Export Script |
|
| 49 |
+
| DeepLabV3-Plus-MobileNet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 13.249 ms | 18 - 21 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
|
| 50 |
+
| DeepLabV3-Plus-MobileNet | SA8255 (Proxy) | SA8255P Proxy | QNN | 12.192 ms | 3 - 4 MB | FP16 | NPU | Use Export Script |
|
| 51 |
+
| DeepLabV3-Plus-MobileNet | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 13.239 ms | 7 - 22 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
|
| 52 |
+
| DeepLabV3-Plus-MobileNet | SA8775 (Proxy) | SA8775P Proxy | QNN | 12.115 ms | 3 - 4 MB | FP16 | NPU | Use Export Script |
|
| 53 |
+
| DeepLabV3-Plus-MobileNet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 13.287 ms | 19 - 21 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
|
| 54 |
+
| DeepLabV3-Plus-MobileNet | SA8650 (Proxy) | SA8650P Proxy | QNN | 12.181 ms | 3 - 5 MB | FP16 | NPU | Use Export Script |
|
| 55 |
+
| DeepLabV3-Plus-MobileNet | SA8295P ADP | SA8295P | TFLITE | 20.643 ms | 21 - 58 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
|
| 56 |
+
| DeepLabV3-Plus-MobileNet | SA8295P ADP | SA8295P | QNN | 20.846 ms | 0 - 6 MB | FP16 | NPU | Use Export Script |
|
| 57 |
+
| DeepLabV3-Plus-MobileNet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 18.33 ms | 21 - 97 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) |
|
| 58 |
+
| DeepLabV3-Plus-MobileNet | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 18.505 ms | 3 - 32 MB | FP16 | NPU | Use Export Script |
|
| 59 |
+
| DeepLabV3-Plus-MobileNet | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 12.424 ms | 3 - 3 MB | FP16 | NPU | Use Export Script |
|
| 60 |
+
| DeepLabV3-Plus-MobileNet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 16.7 ms | 66 - 66 MB | FP16 | NPU | [DeepLabV3-Plus-MobileNet.onnx](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.onnx) |
|
| 61 |
|
| 62 |
|
| 63 |
|
|
|
|
| 121 |
DeepLabV3-Plus-MobileNet
|
| 122 |
Device : Samsung Galaxy S23 (13)
|
| 123 |
Runtime : TFLITE
|
| 124 |
+
Estimated inference time (ms) : 13.3
|
| 125 |
+
Estimated peak memory usage (MB): [21, 23]
|
| 126 |
Total # Ops : 98
|
| 127 |
Compute Unit(s) : NPU (98 ops)
|
| 128 |
```
|