Hugging Face's logo

qualcomm
/
MobileNet-v2

Image Classification
PyTorch
LiteRT
backbone
real_time
android
Model card Files Community
shreyajn commited on
Commit
4aee4c3
·
verified ·
1 Parent(s): f8a9c45

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +30 -26
README.md CHANGED
@@ -1,11 +1,11 @@
1
  ---
2
  library_name: pytorch
3
  license: apache-2.0
4
- pipeline_tag: image-classification
5
  tags:
6
  - backbone
7
  - real_time
8
  - android
 
9
 
10
  ---
11
 
@@ -36,30 +36,34 @@ 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-v2 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.883 ms | 0 - 39 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
40
- | MobileNet-v2 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.093 ms | 1 - 49 MB | FP16 | NPU | [MobileNet-v2.so](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.so) |
41
- | MobileNet-v2 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.897 ms | 0 - 35 MB | FP16 | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
42
- | MobileNet-v2 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.586 ms | 0 - 26 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
43
- | MobileNet-v2 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.723 ms | 1 - 23 MB | FP16 | NPU | [MobileNet-v2.so](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.so) |
44
- | MobileNet-v2 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.617 ms | 0 - 27 MB | FP16 | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
45
- | MobileNet-v2 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.636 ms | 0 - 23 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
46
- | MobileNet-v2 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.733 ms | 1 - 22 MB | FP16 | NPU | Use Export Script |
47
- | MobileNet-v2 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.641 ms | 0 - 21 MB | FP16 | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
48
- | MobileNet-v2 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.884 ms | 0 - 40 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
49
- | MobileNet-v2 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 1.042 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
50
- | MobileNet-v2 | SA7255P ADP | SA7255P | TFLITE | 12.777 ms | 0 - 13 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
51
- | MobileNet-v2 | SA7255P ADP | SA7255P | QNN | 13.166 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
52
- | MobileNet-v2 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.887 ms | 0 - 5 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
53
- | MobileNet-v2 | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.041 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
54
- | MobileNet-v2 | SA8295P ADP | SA8295P | TFLITE | 1.472 ms | 0 - 19 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
55
- | MobileNet-v2 | SA8295P ADP | SA8295P | QNN | 1.905 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
56
- | MobileNet-v2 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.881 ms | 0 - 50 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
57
- | MobileNet-v2 | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.035 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
58
- | MobileNet-v2 | SA8775P ADP | SA8775P | TFLITE | 1.478 ms | 0 - 14 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
59
- | MobileNet-v2 | SA8775P ADP | SA8775P | QNN | 1.872 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
60
- | MobileNet-v2 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.045 ms | 0 - 17 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
61
- | MobileNet-v2 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.268 ms | 1 - 25 MB | FP16 | NPU | Use Export Script |
62
- | MobileNet-v2 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.225 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
 
 
 
 
63
  | MobileNet-v2 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.963 ms | 9 - 9 MB | FP16 | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
64
 
65
 
@@ -125,7 +129,7 @@ MobileNet-v2
125
  Device : Samsung Galaxy S23 (13)
126
  Runtime : TFLITE
127
  Estimated inference time (ms) : 0.9
128
- Estimated peak memory usage (MB): [0, 39]
129
  Total # Ops : 71
130
  Compute Unit(s) : NPU (71 ops)
131
  ```
 
1
  ---
2
  library_name: pytorch
3
  license: apache-2.0
 
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-v2 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.88 ms | 0 - 49 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
40
+ | MobileNet-v2 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.036 ms | 1 - 3 MB | FP16 | NPU | [MobileNet-v2.so](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.so) |
41
+ | MobileNet-v2 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.908 ms | 0 - 33 MB | FP16 | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
42
+ | MobileNet-v2 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.591 ms | 0 - 21 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
43
+ | MobileNet-v2 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.694 ms | 0 - 15 MB | FP16 | NPU | [MobileNet-v2.so](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.so) |
44
+ | MobileNet-v2 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.612 ms | 0 - 26 MB | FP16 | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
45
+ | MobileNet-v2 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.537 ms | 0 - 18 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
46
+ | MobileNet-v2 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.735 ms | 1 - 21 MB | FP16 | NPU | Use Export Script |
47
+ | MobileNet-v2 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.639 ms | 0 - 22 MB | FP16 | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
48
+ | MobileNet-v2 | SA7255P ADP | SA7255P | TFLITE | 12.8 ms | 0 - 12 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
49
+ | MobileNet-v2 | SA7255P ADP | SA7255P | QNN | 13.155 ms | 1 - 7 MB | FP16 | NPU | Use Export Script |
50
+ | MobileNet-v2 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.876 ms | 0 - 50 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
51
+ | MobileNet-v2 | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.039 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
52
+ | MobileNet-v2 | SA8295P ADP | SA8295P | TFLITE | 1.473 ms | 0 - 13 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
53
+ | MobileNet-v2 | SA8295P ADP | SA8295P | QNN | 1.938 ms | 0 - 11 MB | FP16 | NPU | Use Export Script |
54
+ | MobileNet-v2 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.882 ms | 0 - 39 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
55
+ | MobileNet-v2 | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.045 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
56
+ | MobileNet-v2 | SA8775P ADP | SA8775P | TFLITE | 1.487 ms | 0 - 12 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
57
+ | MobileNet-v2 | SA8775P ADP | SA8775P | QNN | 1.879 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
58
+ | MobileNet-v2 | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 12.8 ms | 0 - 12 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
59
+ | MobileNet-v2 | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 13.155 ms | 1 - 7 MB | FP16 | NPU | Use Export Script |
60
+ | MobileNet-v2 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.878 ms | 0 - 39 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
61
+ | MobileNet-v2 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 1.036 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
62
+ | MobileNet-v2 | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 1.487 ms | 0 - 12 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
63
+ | MobileNet-v2 | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 1.879 ms | 1 - 8 MB | FP16 | NPU | Use Export Script |
64
+ | MobileNet-v2 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.051 ms | 0 - 20 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
65
+ | MobileNet-v2 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.299 ms | 1 - 18 MB | FP16 | NPU | Use Export Script |
66
+ | MobileNet-v2 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.22 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
67
  | MobileNet-v2 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.963 ms | 9 - 9 MB | FP16 | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
68
 
69
 
 
129
  Device : Samsung Galaxy S23 (13)
130
  Runtime : TFLITE
131
  Estimated inference time (ms) : 0.9
132
+ Estimated peak memory usage (MB): [0, 49]
133
  Total # Ops : 71
134
  Compute Unit(s) : NPU (71 ops)
135
  ```