Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
---
|
2 |
library_name: pytorch
|
3 |
license: bsd-3-clause
|
4 |
-
pipeline_tag: video-classification
|
5 |
tags:
|
6 |
- backbone
|
7 |
- android
|
|
|
8 |
|
9 |
---
|
10 |
|
@@ -35,20 +35,22 @@ 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 |
-
| ResNet-Mixed-Convolution | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE |
|
39 |
-
| ResNet-Mixed-Convolution | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 17.
|
40 |
-
| ResNet-Mixed-Convolution | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE |
|
41 |
-
| ResNet-Mixed-Convolution | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX |
|
42 |
-
| ResNet-Mixed-Convolution | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 151.
|
43 |
-
| ResNet-Mixed-Convolution | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX |
|
44 |
-
| ResNet-Mixed-Convolution |
|
45 |
-
| ResNet-Mixed-Convolution |
|
46 |
-
| ResNet-Mixed-Convolution |
|
47 |
-
| ResNet-Mixed-Convolution |
|
48 |
-
| ResNet-Mixed-Convolution |
|
49 |
-
| ResNet-Mixed-Convolution |
|
50 |
-
| ResNet-Mixed-Convolution |
|
51 |
-
| ResNet-Mixed-Convolution |
|
|
|
|
|
52 |
|
53 |
|
54 |
|
@@ -112,8 +114,8 @@ Profiling Results
|
|
112 |
ResNet-Mixed-Convolution
|
113 |
Device : Samsung Galaxy S23 (13)
|
114 |
Runtime : TFLITE
|
115 |
-
Estimated inference time (ms) :
|
116 |
-
Estimated peak memory usage (MB): [
|
117 |
Total # Ops : 55
|
118 |
Compute Unit(s) : NPU (50 ops) CPU (5 ops)
|
119 |
```
|
|
|
1 |
---
|
2 |
library_name: pytorch
|
3 |
license: bsd-3-clause
|
|
|
4 |
tags:
|
5 |
- backbone
|
6 |
- android
|
7 |
+
pipeline_tag: video-classification
|
8 |
|
9 |
---
|
10 |
|
|
|
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 | 170.534 ms | 32 - 57 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 | 17.887 ms | 2 - 90 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 | 128.027 ms | 31 - 60 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 | 12.936 ms | 4 - 76 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 | 151.632 ms | 30 - 60 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 | 10.561 ms | 4 - 67 MB | FP16 | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
|
44 |
+
| ResNet-Mixed-Convolution | SA7255P ADP | SA7255P | TFLITE | 1031.303 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 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 167.15 ms | 31 - 76 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
46 |
+
| ResNet-Mixed-Convolution | SA8295P ADP | SA8295P | TFLITE | 201.316 ms | 31 - 54 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
47 |
+
| ResNet-Mixed-Convolution | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 167.897 ms | 31 - 46 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
48 |
+
| ResNet-Mixed-Convolution | SA8775P ADP | SA8775P | TFLITE | 219.721 ms | 31 - 57 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
49 |
+
| ResNet-Mixed-Convolution | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 1031.303 ms | 31 - 57 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
50 |
+
| ResNet-Mixed-Convolution | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 170.756 ms | 31 - 66 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
51 |
+
| ResNet-Mixed-Convolution | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 219.721 ms | 31 - 57 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
52 |
+
| ResNet-Mixed-Convolution | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 184.857 ms | 31 - 63 MB | FP16 | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
|
53 |
+
| ResNet-Mixed-Convolution | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 18.902 ms | 25 - 25 MB | FP16 | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
|
54 |
|
55 |
|
56 |
|
|
|
114 |
ResNet-Mixed-Convolution
|
115 |
Device : Samsung Galaxy S23 (13)
|
116 |
Runtime : TFLITE
|
117 |
+
Estimated inference time (ms) : 170.5
|
118 |
+
Estimated peak memory usage (MB): [32, 57]
|
119 |
Total # Ops : 55
|
120 |
Compute Unit(s) : NPU (50 ops) CPU (5 ops)
|
121 |
```
|