qaihm-bot commited on
Commit
95c431e
·
verified ·
1 Parent(s): 3e729d7

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +34 -30
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
  library_name: pytorch
3
  license: bsd-3-clause
4
- pipeline_tag: image-classification
5
  tags:
6
  - quantized
7
  - android
 
8
 
9
  ---
10
 
@@ -35,34 +35,38 @@ 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
- | GoogLeNetQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.284 ms | 0 - 14 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
39
- | GoogLeNetQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.343 ms | 0 - 13 MB | INT8 | NPU | [GoogLeNetQuantized.so](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.so) |
40
- | GoogLeNetQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.533 ms | 0 - 29 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
41
- | GoogLeNetQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.197 ms | 0 - 18 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
42
- | GoogLeNetQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.25 ms | 0 - 26 MB | INT8 | NPU | [GoogLeNetQuantized.so](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.so) |
43
- | GoogLeNetQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.371 ms | 0 - 27 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
44
- | GoogLeNetQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.218 ms | 0 - 19 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
45
- | GoogLeNetQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.255 ms | 0 - 18 MB | INT8 | NPU | Use Export Script |
46
- | GoogLeNetQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.403 ms | 0 - 22 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
47
- | GoogLeNetQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 0.902 ms | 0 - 16 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
48
- | GoogLeNetQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 1.172 ms | 0 - 11 MB | INT8 | NPU | Use Export Script |
49
- | GoogLeNetQuantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 6.023 ms | 0 - 3 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
50
- | GoogLeNetQuantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.288 ms | 0 - 14 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
51
- | GoogLeNetQuantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.307 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
52
- | GoogLeNetQuantized | SA7255P ADP | SA7255P | TFLITE | 3.613 ms | 0 - 12 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
53
- | GoogLeNetQuantized | SA7255P ADP | SA7255P | QNN | 3.901 ms | 0 - 9 MB | INT8 | NPU | Use Export Script |
54
- | GoogLeNetQuantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.282 ms | 0 - 13 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
55
- | GoogLeNetQuantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.302 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
56
- | GoogLeNetQuantized | SA8295P ADP | SA8295P | TFLITE | 0.648 ms | 0 - 18 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
57
- | GoogLeNetQuantized | SA8295P ADP | SA8295P | QNN | 1.027 ms | 0 - 14 MB | INT8 | NPU | Use Export Script |
58
- | GoogLeNetQuantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.283 ms | 0 - 14 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
59
- | GoogLeNetQuantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.304 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
60
- | GoogLeNetQuantized | SA8775P ADP | SA8775P | TFLITE | 0.578 ms | 0 - 12 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
61
- | GoogLeNetQuantized | SA8775P ADP | SA8775P | QNN | 0.771 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
62
- | GoogLeNetQuantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.343 ms | 0 - 15 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
63
- | GoogLeNetQuantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.417 ms | 0 - 24 MB | INT8 | NPU | Use Export Script |
64
- | GoogLeNetQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.406 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
65
- | GoogLeNetQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.578 ms | 9 - 9 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
 
 
 
 
66
 
67
 
68
 
@@ -127,7 +131,7 @@ GoogLeNetQuantized
127
  Device : Samsung Galaxy S23 (13)
128
  Runtime : TFLITE
129
  Estimated inference time (ms) : 0.3
130
- Estimated peak memory usage (MB): [0, 14]
131
  Total # Ops : 86
132
  Compute Unit(s) : NPU (86 ops)
133
  ```
 
1
  ---
2
  library_name: pytorch
3
  license: bsd-3-clause
 
4
  tags:
5
  - quantized
6
  - android
7
+ pipeline_tag: image-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
+ | GoogLeNetQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.279 ms | 0 - 5 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
39
+ | GoogLeNetQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.31 ms | 0 - 3 MB | INT8 | NPU | [GoogLeNetQuantized.so](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.so) |
40
+ | GoogLeNetQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.514 ms | 0 - 29 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
41
+ | GoogLeNetQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.209 ms | 0 - 24 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
42
+ | GoogLeNetQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.231 ms | 0 - 17 MB | INT8 | NPU | [GoogLeNetQuantized.so](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.so) |
43
+ | GoogLeNetQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.372 ms | 0 - 27 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
44
+ | GoogLeNetQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.177 ms | 0 - 19 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
45
+ | GoogLeNetQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.26 ms | 0 - 19 MB | INT8 | NPU | Use Export Script |
46
+ | GoogLeNetQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.342 ms | 0 - 19 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
47
+ | GoogLeNetQuantized | SA7255P ADP | SA7255P | TFLITE | 3.615 ms | 0 - 11 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
48
+ | GoogLeNetQuantized | SA7255P ADP | SA7255P | QNN | 3.924 ms | 0 - 6 MB | INT8 | NPU | Use Export Script |
49
+ | GoogLeNetQuantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.283 ms | 0 - 14 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
50
+ | GoogLeNetQuantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.304 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
51
+ | GoogLeNetQuantized | SA8295P ADP | SA8295P | TFLITE | 0.638 ms | 0 - 13 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
52
+ | GoogLeNetQuantized | SA8295P ADP | SA8295P | QNN | 0.884 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
53
+ | GoogLeNetQuantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.285 ms | 0 - 14 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
54
+ | GoogLeNetQuantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.303 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
55
+ | GoogLeNetQuantized | SA8775P ADP | SA8775P | TFLITE | 0.575 ms | 0 - 10 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
56
+ | GoogLeNetQuantized | SA8775P ADP | SA8775P | QNN | 0.755 ms | 0 - 8 MB | INT8 | NPU | Use Export Script |
57
+ | GoogLeNetQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 0.899 ms | 0 - 16 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
58
+ | GoogLeNetQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 1.212 ms | 0 - 11 MB | INT8 | NPU | Use Export Script |
59
+ | GoogLeNetQuantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 6.072 ms | 0 - 2 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
60
+ | GoogLeNetQuantized | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 3.615 ms | 0 - 11 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
61
+ | GoogLeNetQuantized | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 3.924 ms | 0 - 6 MB | INT8 | NPU | Use Export Script |
62
+ | GoogLeNetQuantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.284 ms | 0 - 13 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
63
+ | GoogLeNetQuantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.308 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
64
+ | GoogLeNetQuantized | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 0.575 ms | 0 - 10 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
65
+ | GoogLeNetQuantized | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 0.755 ms | 0 - 8 MB | INT8 | NPU | Use Export Script |
66
+ | GoogLeNetQuantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.353 ms | 0 - 19 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
67
+ | GoogLeNetQuantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.412 ms | 0 - 18 MB | INT8 | NPU | Use Export Script |
68
+ | GoogLeNetQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.427 ms | 1 - 1 MB | INT8 | NPU | Use Export Script |
69
+ | GoogLeNetQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.574 ms | 9 - 9 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
70
 
71
 
72
 
 
131
  Device : Samsung Galaxy S23 (13)
132
  Runtime : TFLITE
133
  Estimated inference time (ms) : 0.3
134
+ Estimated peak memory usage (MB): [0, 5]
135
  Total # Ops : 86
136
  Compute Unit(s) : NPU (86 ops)
137
  ```