qaihm-bot commited on
Commit
41dcae8
·
verified ·
1 Parent(s): d5e6f88

See https://github.com/quic/ai-hub-models/releases/v0.32.0 for changelog.

.gitattributes CHANGED
@@ -37,3 +37,4 @@ MobileNet-v2.so filter=lfs diff=lfs merge=lfs -text
37
  MobileNet-v2_w8a16.so filter=lfs diff=lfs merge=lfs -text
38
  MobileNet-v2.dlc filter=lfs diff=lfs merge=lfs -text
39
  MobileNet-v2_w8a16.dlc filter=lfs diff=lfs merge=lfs -text
 
 
37
  MobileNet-v2_w8a16.so filter=lfs diff=lfs merge=lfs -text
38
  MobileNet-v2.dlc filter=lfs diff=lfs merge=lfs -text
39
  MobileNet-v2_w8a16.dlc filter=lfs diff=lfs merge=lfs -text
40
+ DEPLOYMENT_MODEL_LICENSE.pdf filter=lfs diff=lfs merge=lfs -text
DEPLOYMENT_MODEL_LICENSE.pdf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
3
+ size 109629
LICENSE ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ The license of the original trained model can be found at https://github.com/tonylins/pytorch-mobilenet-v2/blob/master/LICENSE.
2
+ The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.
MobileNet-v2.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:149f786462f2bb8f6959a3371c50a36a472d51a536fd1fe80c6fcd4f2326c1d0
3
- size 13982002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af9d31dec52ad990d9b7fc7c0bec3113ff18678a07204a0b14bc065716533f6e
3
+ size 13986126
MobileNet-v2_w8a16.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99793ea929edb9a90cf3441dc7c2d143bf244f3a51016743b35cf1e471f6db39
3
- size 4604256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74029ab272daceb19c322919603600b9ca23a15d49e6115af31887f0b52bd411
3
+ size 4604199
MobileNet-v2_w8a16.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c09f81512a4614074cc5d7235d822c1609ab23032845e623767d3d2178977d31
3
- size 14121177
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b9200eff0c1a211c9ee5bb7d96afc6bb7661eb4f9d1eac7f717c927d31bc468
3
+ size 14121209
README.md CHANGED
@@ -33,7 +33,7 @@ More details on model performance across various devices, can be found
33
  - Input resolution: 224x224
34
  - Number of parameters: 3.49M
35
  - Model size (float): 13.3 MB
36
- - Model size (w8a8): 3.42 MB
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
@@ -57,33 +57,33 @@ More details on model performance across various devices, can be found
57
  | MobileNet-v2 | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 1.158 ms | 1 - 19 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.dlc) |
58
  | MobileNet-v2 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 0.86 ms | 0 - 68 MB | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
59
  | MobileNet-v2 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 0.838 ms | 0 - 46 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.dlc) |
60
- | MobileNet-v2 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 0.718 ms | 0 - 23 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
61
  | MobileNet-v2 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.579 ms | 0 - 36 MB | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
62
  | MobileNet-v2 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.553 ms | 0 - 31 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.dlc) |
63
- | MobileNet-v2 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.48 ms | 0 - 33 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
64
  | MobileNet-v2 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.608 ms | 0 - 27 MB | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
65
  | MobileNet-v2 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 0.53 ms | 0 - 20 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.dlc) |
66
- | MobileNet-v2 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 0.493 ms | 0 - 20 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
67
  | MobileNet-v2 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1.327 ms | 37 - 37 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.dlc) |
68
- | MobileNet-v2 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.805 ms | 7 - 7 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
69
- | MobileNet-v2 | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 1.734 ms | 0 - 17 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
70
- | MobileNet-v2 | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 0.981 ms | 0 - 35 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
71
- | MobileNet-v2 | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 0.826 ms | 0 - 28 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
72
- | MobileNet-v2 | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 1.033 ms | 0 - 19 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
73
- | MobileNet-v2 | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 2.684 ms | 0 - 19 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
74
- | MobileNet-v2 | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 1.734 ms | 0 - 17 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
75
- | MobileNet-v2 | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 0.823 ms | 0 - 28 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
76
- | MobileNet-v2 | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 1.234 ms | 0 - 22 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
77
- | MobileNet-v2 | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 0.821 ms | 0 - 28 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
78
- | MobileNet-v2 | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 1.033 ms | 0 - 19 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
79
- | MobileNet-v2 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 0.816 ms | 0 - 28 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
80
- | MobileNet-v2 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 56.532 ms | 0 - 110 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.onnx) |
81
- | MobileNet-v2 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.564 ms | 0 - 33 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
82
- | MobileNet-v2 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 43.03 ms | 3 - 394 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.onnx) |
83
- | MobileNet-v2 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 0.445 ms | 0 - 24 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
84
- | MobileNet-v2 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 39.223 ms | 3 - 478 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.onnx) |
85
- | MobileNet-v2 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1.024 ms | 24 - 24 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
86
- | MobileNet-v2 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 54.625 ms | 29 - 29 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.onnx) |
87
 
88
 
89
 
 
33
  - Input resolution: 224x224
34
  - Number of parameters: 3.49M
35
  - Model size (float): 13.3 MB
36
+ - Model size (w8a16): 4.39 MB
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
 
57
  | MobileNet-v2 | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 1.158 ms | 1 - 19 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.dlc) |
58
  | MobileNet-v2 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 0.86 ms | 0 - 68 MB | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
59
  | MobileNet-v2 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 0.838 ms | 0 - 46 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.dlc) |
60
+ | MobileNet-v2 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 0.716 ms | 0 - 24 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
61
  | MobileNet-v2 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.579 ms | 0 - 36 MB | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
62
  | MobileNet-v2 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.553 ms | 0 - 31 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.dlc) |
63
+ | MobileNet-v2 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.485 ms | 0 - 34 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
64
  | MobileNet-v2 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.608 ms | 0 - 27 MB | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
65
  | MobileNet-v2 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 0.53 ms | 0 - 20 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.dlc) |
66
+ | MobileNet-v2 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 0.51 ms | 1 - 24 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
67
  | MobileNet-v2 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1.327 ms | 37 - 37 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.dlc) |
68
+ | MobileNet-v2 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.79 ms | 7 - 7 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
69
+ | MobileNet-v2 | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 1.739 ms | 0 - 17 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
70
+ | MobileNet-v2 | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 0.984 ms | 0 - 31 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
71
+ | MobileNet-v2 | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 0.816 ms | 0 - 27 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
72
+ | MobileNet-v2 | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 1.028 ms | 0 - 18 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
73
+ | MobileNet-v2 | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 2.698 ms | 0 - 21 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
74
+ | MobileNet-v2 | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 1.739 ms | 0 - 17 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
75
+ | MobileNet-v2 | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 0.82 ms | 0 - 28 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
76
+ | MobileNet-v2 | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 1.226 ms | 0 - 23 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
77
+ | MobileNet-v2 | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 0.822 ms | 0 - 29 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
78
+ | MobileNet-v2 | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 1.028 ms | 0 - 18 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
79
+ | MobileNet-v2 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 0.82 ms | 0 - 29 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
80
+ | MobileNet-v2 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 57.233 ms | 10 - 71 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.onnx) |
81
+ | MobileNet-v2 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.567 ms | 0 - 31 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
82
+ | MobileNet-v2 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 44.723 ms | 1 - 396 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.onnx) |
83
+ | MobileNet-v2 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 0.471 ms | 0 - 22 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
84
+ | MobileNet-v2 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 38.445 ms | 3 - 479 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.onnx) |
85
+ | MobileNet-v2 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1.024 ms | 18 - 18 MB | NPU | [MobileNet-v2.dlc](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.dlc) |
86
+ | MobileNet-v2 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 104.184 ms | 26 - 26 MB | NPU | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2_w8a16.onnx) |
87
 
88
 
89