Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
---
|
2 |
library_name: pytorch
|
3 |
license: bsd-3-clause
|
4 |
-
pipeline_tag: image-classification
|
5 |
tags:
|
6 |
- backbone
|
7 |
- real_time
|
8 |
- android
|
|
|
9 |
|
10 |
---
|
11 |
|
@@ -36,31 +36,35 @@ More details on model performance across various devices, can be found
|
|
36 |
|
37 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
38 |
|---|---|---|---|---|---|---|---|---|
|
39 |
-
| MobileNet-v3-Large | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.
|
40 |
-
| MobileNet-v3-Large | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN |
|
41 |
-
| MobileNet-v3-Large | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.
|
42 |
-
| MobileNet-v3-Large | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.
|
43 |
-
| MobileNet-v3-Large | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.
|
44 |
-
| MobileNet-v3-Large | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.
|
45 |
-
| MobileNet-v3-Large | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.
|
46 |
-
| MobileNet-v3-Large | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.725 ms |
|
47 |
-
| MobileNet-v3-Large | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.
|
48 |
-
| MobileNet-v3-Large |
|
49 |
-
| MobileNet-v3-Large |
|
50 |
-
| MobileNet-v3-Large |
|
51 |
-
| MobileNet-v3-Large |
|
52 |
-
| MobileNet-v3-Large |
|
53 |
-
| MobileNet-v3-Large |
|
54 |
-
| MobileNet-v3-Large |
|
55 |
-
| MobileNet-v3-Large |
|
56 |
-
| MobileNet-v3-Large |
|
57 |
-
| MobileNet-v3-Large |
|
58 |
-
| MobileNet-v3-Large |
|
59 |
-
| MobileNet-v3-Large |
|
60 |
-
| MobileNet-v3-Large |
|
61 |
-
| MobileNet-v3-Large |
|
62 |
-
| MobileNet-v3-Large |
|
63 |
-
| MobileNet-v3-Large |
|
|
|
|
|
|
|
|
|
64 |
|
65 |
|
66 |
|
@@ -125,7 +129,7 @@ MobileNet-v3-Large
|
|
125 |
Device : Samsung Galaxy S23 (13)
|
126 |
Runtime : TFLITE
|
127 |
Estimated inference time (ms) : 1.0
|
128 |
-
Estimated peak memory usage (MB): [0,
|
129 |
Total # Ops : 128
|
130 |
Compute Unit(s) : NPU (128 ops)
|
131 |
```
|
|
|
1 |
---
|
2 |
library_name: pytorch
|
3 |
license: bsd-3-clause
|
|
|
4 |
tags:
|
5 |
- backbone
|
6 |
- real_time
|
7 |
- android
|
8 |
+
pipeline_tag: image-classification
|
9 |
|
10 |
---
|
11 |
|
|
|
36 |
|
37 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
38 |
|---|---|---|---|---|---|---|---|---|
|
39 |
+
| MobileNet-v3-Large | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.992 ms | 0 - 74 MB | FP16 | NPU | [MobileNet-v3-Large.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.tflite) |
|
40 |
+
| MobileNet-v3-Large | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.999 ms | 1 - 3 MB | FP16 | NPU | [MobileNet-v3-Large.so](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.so) |
|
41 |
+
| MobileNet-v3-Large | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.02 ms | 0 - 57 MB | FP16 | NPU | [MobileNet-v3-Large.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.onnx) |
|
42 |
+
| MobileNet-v3-Large | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.678 ms | 0 - 25 MB | FP16 | NPU | [MobileNet-v3-Large.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.tflite) |
|
43 |
+
| MobileNet-v3-Large | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.685 ms | 0 - 19 MB | FP16 | NPU | [MobileNet-v3-Large.so](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.so) |
|
44 |
+
| MobileNet-v3-Large | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.728 ms | 0 - 29 MB | FP16 | NPU | [MobileNet-v3-Large.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.onnx) |
|
45 |
+
| MobileNet-v3-Large | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.677 ms | 0 - 22 MB | FP16 | NPU | [MobileNet-v3-Large.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.tflite) |
|
46 |
+
| MobileNet-v3-Large | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.725 ms | 0 - 23 MB | FP16 | NPU | Use Export Script |
|
47 |
+
| MobileNet-v3-Large | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.608 ms | 0 - 18 MB | FP16 | NPU | [MobileNet-v3-Large.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.onnx) |
|
48 |
+
| MobileNet-v3-Large | SA7255P ADP | SA7255P | TFLITE | 15.033 ms | 0 - 13 MB | FP16 | NPU | [MobileNet-v3-Large.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.tflite) |
|
49 |
+
| MobileNet-v3-Large | SA7255P ADP | SA7255P | QNN | 14.692 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
|
50 |
+
| MobileNet-v3-Large | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.991 ms | 0 - 74 MB | FP16 | NPU | [MobileNet-v3-Large.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.tflite) |
|
51 |
+
| MobileNet-v3-Large | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.001 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
|
52 |
+
| MobileNet-v3-Large | SA8295P ADP | SA8295P | TFLITE | 1.86 ms | 0 - 15 MB | FP16 | NPU | [MobileNet-v3-Large.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.tflite) |
|
53 |
+
| MobileNet-v3-Large | SA8295P ADP | SA8295P | QNN | 2.503 ms | 0 - 11 MB | FP16 | NPU | Use Export Script |
|
54 |
+
| MobileNet-v3-Large | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.995 ms | 0 - 64 MB | FP16 | NPU | [MobileNet-v3-Large.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.tflite) |
|
55 |
+
| MobileNet-v3-Large | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.005 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
|
56 |
+
| MobileNet-v3-Large | SA8775P ADP | SA8775P | TFLITE | 1.693 ms | 0 - 13 MB | FP16 | NPU | [MobileNet-v3-Large.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.tflite) |
|
57 |
+
| MobileNet-v3-Large | SA8775P ADP | SA8775P | QNN | 1.817 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
|
58 |
+
| MobileNet-v3-Large | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 15.033 ms | 0 - 13 MB | FP16 | NPU | [MobileNet-v3-Large.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.tflite) |
|
59 |
+
| MobileNet-v3-Large | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 14.692 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
|
60 |
+
| MobileNet-v3-Large | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.992 ms | 0 - 74 MB | FP16 | NPU | [MobileNet-v3-Large.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.tflite) |
|
61 |
+
| MobileNet-v3-Large | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.997 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
|
62 |
+
| MobileNet-v3-Large | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 1.693 ms | 0 - 13 MB | FP16 | NPU | [MobileNet-v3-Large.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.tflite) |
|
63 |
+
| MobileNet-v3-Large | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 1.817 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
|
64 |
+
| MobileNet-v3-Large | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.372 ms | 0 - 20 MB | FP16 | NPU | [MobileNet-v3-Large.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.tflite) |
|
65 |
+
| MobileNet-v3-Large | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.452 ms | 1 - 21 MB | FP16 | NPU | Use Export Script |
|
66 |
+
| MobileNet-v3-Large | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.141 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
|
67 |
+
| MobileNet-v3-Large | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.04 ms | 14 - 14 MB | FP16 | NPU | [MobileNet-v3-Large.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Large/blob/main/MobileNet-v3-Large.onnx) |
|
68 |
|
69 |
|
70 |
|
|
|
129 |
Device : Samsung Galaxy S23 (13)
|
130 |
Runtime : TFLITE
|
131 |
Estimated inference time (ms) : 1.0
|
132 |
+
Estimated peak memory usage (MB): [0, 74]
|
133 |
Total # Ops : 128
|
134 |
Compute Unit(s) : NPU (128 ops)
|
135 |
```
|