Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -35,6 +35,20 @@ More details on model performance across various devices, can be found
|
|
35 |
|
36 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
37 |
|---|---|---|---|---|---|---|---|---|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
|
39 |
|
40 |
|
@@ -94,7 +108,16 @@ device. This script does the following:
|
|
94 |
python -m qai_hub_models.models.resnet_mixed.export
|
95 |
```
|
96 |
```
|
97 |
-
Profiling Results
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
98 |
|
99 |
|
100 |
## How does this work?
|
|
|
35 |
|
36 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
37 |
|---|---|---|---|---|---|---|---|---|
|
38 |
+
| ResNet-Mixed-Convolution | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 167.191 ms | 30 - 76 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
39 |
+
| ResNet-Mixed-Convolution | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 17.682 ms | 0 - 91 MB | FP16 | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
|
40 |
+
| ResNet-Mixed-Convolution | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 127.47 ms | 29 - 58 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
41 |
+
| ResNet-Mixed-Convolution | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 13.111 ms | 4 - 70 MB | FP16 | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
|
42 |
+
| ResNet-Mixed-Convolution | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 150.781 ms | 29 - 59 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
43 |
+
| ResNet-Mixed-Convolution | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 12.757 ms | 2 - 64 MB | FP16 | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
|
44 |
+
| ResNet-Mixed-Convolution | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 166.676 ms | 31 - 57 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
45 |
+
| ResNet-Mixed-Convolution | SA7255P ADP | SA7255P | TFLITE | 1030.441 ms | 31 - 57 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
46 |
+
| ResNet-Mixed-Convolution | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 166.883 ms | 31 - 82 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
47 |
+
| ResNet-Mixed-Convolution | SA8295P ADP | SA8295P | TFLITE | 203.1 ms | 31 - 59 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
48 |
+
| ResNet-Mixed-Convolution | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 169.72 ms | 30 - 75 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
49 |
+
| ResNet-Mixed-Convolution | SA8775P ADP | SA8775P | TFLITE | 219.728 ms | 31 - 58 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
50 |
+
| ResNet-Mixed-Convolution | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 184.655 ms | 31 - 60 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
51 |
+
| ResNet-Mixed-Convolution | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 18.869 ms | 25 - 25 MB | FP16 | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
|
52 |
|
53 |
|
54 |
|
|
|
108 |
python -m qai_hub_models.models.resnet_mixed.export
|
109 |
```
|
110 |
```
|
111 |
+
Profiling Results
|
112 |
+
------------------------------------------------------------
|
113 |
+
ResNet-Mixed-Convolution
|
114 |
+
Device : Samsung Galaxy S23 (13)
|
115 |
+
Runtime : TFLITE
|
116 |
+
Estimated inference time (ms) : 167.2
|
117 |
+
Estimated peak memory usage (MB): [30, 76]
|
118 |
+
Total # Ops : 55
|
119 |
+
Compute Unit(s) : NPU (50 ops) CPU (5 ops)
|
120 |
+
```
|
121 |
|
122 |
|
123 |
## How does this work?
|