Hugging Face's logo

qualcomm
/
MobileNet-v3-Large-Quantized

Image Classification
PyTorch
LiteRT
ONNX
quantized
backbone
real_time
android
Model card Files Community
qaihm-bot commited on
Commit
af237f7
·
verified ·
1 Parent(s): 97b3208

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +23 -25
README.md CHANGED
@@ -1,7 +1,4 @@
1
  ---
2
- datasets:
3
- - imagenet-1k
4
- - imagenet-22k
5
  library_name: pytorch
6
  license: bsd-3-clause
7
  pipeline_tag: image-classification
@@ -40,28 +37,29 @@ More details on model performance across various devices, can be found
40
 
41
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
42
  |---|---|---|---|---|---|---|---|---|
43
- | MobileNet-v3-Large-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.346 ms | 0 - 10 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
44
  | MobileNet-v3-Large-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.63 ms | 0 - 14 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.so](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.so) |
45
- | MobileNet-v3-Large-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.656 ms | 0 - 11 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.onnx) |
46
- | MobileNet-v3-Large-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.239 ms | 0 - 52 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
47
- | MobileNet-v3-Large-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.602 ms | 0 - 18 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.so](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.so) |
48
- | MobileNet-v3-Large-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.495 ms | 0 - 82 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.onnx) |
49
- | MobileNet-v3-Large-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 1.133 ms | 0 - 32 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
50
- | MobileNet-v3-Large-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 1.699 ms | 0 - 8 MB | INT8 | NPU | Use Export Script |
51
- | MobileNet-v3-Large-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 6.815 ms | 0 - 2 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
52
- | MobileNet-v3-Large-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.349 ms | 0 - 1 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
53
- | MobileNet-v3-Large-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.574 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
54
- | MobileNet-v3-Large-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.336 ms | 0 - 1 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
55
- | MobileNet-v3-Large-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.574 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
56
- | MobileNet-v3-Large-Quantized | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 0.348 ms | 0 - 1 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
57
- | MobileNet-v3-Large-Quantized | SA8775 (Proxy) | SA8775P Proxy | QNN | 0.577 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
58
- | MobileNet-v3-Large-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.439 ms | 0 - 53 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
59
- | MobileNet-v3-Large-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.767 ms | 0 - 20 MB | INT8 | NPU | Use Export Script |
60
- | MobileNet-v3-Large-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.249 ms | 0 - 30 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
61
- | MobileNet-v3-Large-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.473 ms | 0 - 14 MB | INT8 | NPU | Use Export Script |
62
- | MobileNet-v3-Large-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.528 ms | 0 - 37 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.onnx) |
63
- | MobileNet-v3-Large-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.716 ms | 1 - 1 MB | INT8 | NPU | Use Export Script |
64
- | MobileNet-v3-Large-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.72 ms | 10 - 10 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.onnx) |
 
65
 
66
 
67
 
@@ -126,7 +124,7 @@ MobileNet-v3-Large-Quantized
126
  Device : Samsung Galaxy S23 (13)
127
  Runtime : TFLITE
128
  Estimated inference time (ms) : 0.3
129
- Estimated peak memory usage (MB): [0, 10]
130
  Total # Ops : 137
131
  Compute Unit(s) : NPU (137 ops)
132
  ```
 
1
  ---
 
 
 
2
  library_name: pytorch
3
  license: bsd-3-clause
4
  pipeline_tag: image-classification
 
37
 
38
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
+ | MobileNet-v3-Large-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.343 ms | 0 - 127 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
41
  | MobileNet-v3-Large-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.63 ms | 0 - 14 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.so](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.so) |
42
+ | MobileNet-v3-Large-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.245 ms | 0 - 52 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
43
+ | MobileNet-v3-Large-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.452 ms | 0 - 17 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.so](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.so) |
44
+ | MobileNet-v3-Large-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.25 ms | 0 - 30 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
45
+ | MobileNet-v3-Large-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.374 ms | 0 - 13 MB | INT8 | NPU | Use Export Script |
46
+ | MobileNet-v3-Large-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 1.157 ms | 0 - 32 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
47
+ | MobileNet-v3-Large-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 1.711 ms | 0 - 8 MB | INT8 | NPU | Use Export Script |
48
+ | MobileNet-v3-Large-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 6.807 ms | 0 - 7 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
49
+ | MobileNet-v3-Large-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.347 ms | 0 - 70 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
50
+ | MobileNet-v3-Large-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.574 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
51
+ | MobileNet-v3-Large-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.341 ms | 0 - 13 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
52
+ | MobileNet-v3-Large-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.58 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
53
+ | MobileNet-v3-Large-Quantized | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 0.351 ms | 0 - 2 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
54
+ | MobileNet-v3-Large-Quantized | SA8775 (Proxy) | SA8775P Proxy | QNN | 0.573 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
55
+ | MobileNet-v3-Large-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.338 ms | 0 - 2 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
56
+ | MobileNet-v3-Large-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.575 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
57
+ | MobileNet-v3-Large-Quantized | SA8295P ADP | SA8295P | TFLITE | 0.797 ms | 0 - 29 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
58
+ | MobileNet-v3-Large-Quantized | SA8295P ADP | SA8295P | QNN | 1.137 ms | 0 - 6 MB | INT8 | NPU | Use Export Script |
59
+ | MobileNet-v3-Large-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.437 ms | 0 - 52 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.tflite) |
60
+ | MobileNet-v3-Large-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.759 ms | 0 - 18 MB | INT8 | NPU | Use Export Script |
61
+ | MobileNet-v3-Large-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.708 ms | 1 - 1 MB | INT8 | NPU | Use Export Script |
62
+ | MobileNet-v3-Large-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 187.074 ms | 58 - 58 MB | INT8 | NPU | [MobileNet-v3-Large-Quantized.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Large-Quantized/blob/main/MobileNet-v3-Large-Quantized.onnx) |
63
 
64
 
65
 
 
124
  Device : Samsung Galaxy S23 (13)
125
  Runtime : TFLITE
126
  Estimated inference time (ms) : 0.3
127
+ Estimated peak memory usage (MB): [0, 127]
128
  Total # Ops : 137
129
  Compute Unit(s) : NPU (137 ops)
130
  ```