Hugging Face's logo

qualcomm
/
ResNet-Mixed-Convolution

Video Classification
PyTorch
LiteRT
backbone
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
53f2fbc
·
verified ·
1 Parent(s): 6f1b990

v0.32.0

Browse files

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

Files changed (7) hide show
  1. .gitattributes +1 -0
  2. DEPLOYMENT_MODEL_LICENSE.pdf +3 -0
  3. LICENSE +2 -0
  4. README.md +24 -24
  5. ResNet-Mixed-Convolution.onnx +2 -2
  6. ResNet-Mixed-Convolution_w8a16.dlc +2 -2
  7. ResNet-Mixed-Convolution_w8a16.onnx +2 -2
.gitattributes CHANGED
@@ -37,3 +37,4 @@ ResNet-Mixed-Convolution.so filter=lfs diff=lfs merge=lfs -text
37
  ResNet-Mixed-Convolution_w8a8.so filter=lfs diff=lfs merge=lfs -text
38
  ResNet-Mixed-Convolution.dlc filter=lfs diff=lfs merge=lfs -text
39
  ResNet-Mixed-Convolution_w8a16.dlc filter=lfs diff=lfs merge=lfs -text
 
 
37
  ResNet-Mixed-Convolution_w8a8.so filter=lfs diff=lfs merge=lfs -text
38
  ResNet-Mixed-Convolution.dlc filter=lfs diff=lfs merge=lfs -text
39
  ResNet-Mixed-Convolution_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/pytorch/vision/blob/main/LICENSE.
2
+ The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.
README.md CHANGED
@@ -31,8 +31,8 @@ More details on model performance across various devices, can be found
31
  - Model checkpoint: Kinectics-400
32
  - Input resolution: 112x112
33
  - Number of parameters: 11.7M
34
- - Model size (float): 44.7 MB
35
- - Model size (w8a8): 11.7 MB
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
@@ -56,33 +56,33 @@ More details on model performance across various devices, can be found
56
  | ResNet-Mixed-Convolution | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 25.775 ms | 0 - 75 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.dlc) |
57
  | ResNet-Mixed-Convolution | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 139.769 ms | 31 - 92 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
58
  | ResNet-Mixed-Convolution | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 14.085 ms | 2 - 28 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.dlc) |
59
- | ResNet-Mixed-Convolution | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 13.648 ms | 0 - 71 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
60
  | ResNet-Mixed-Convolution | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 103.846 ms | 31 - 89 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
61
  | ResNet-Mixed-Convolution | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 10.025 ms | 0 - 85 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.dlc) |
62
- | ResNet-Mixed-Convolution | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 10.412 ms | 2 - 90 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
63
  | ResNet-Mixed-Convolution | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 126.007 ms | 30 - 79 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
64
  | ResNet-Mixed-Convolution | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 10.72 ms | 2 - 79 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.dlc) |
65
- | ResNet-Mixed-Convolution | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 10.023 ms | 2 - 83 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
66
  | ResNet-Mixed-Convolution | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 16.103 ms | 291 - 291 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.dlc) |
67
- | ResNet-Mixed-Convolution | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 15.045 ms | 22 - 22 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
68
- | ResNet-Mixed-Convolution | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 28.01 ms | 1 - 48 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
69
- | ResNet-Mixed-Convolution | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 12.751 ms | 1 - 67 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
70
- | ResNet-Mixed-Convolution | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 8.355 ms | 1 - 19 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
71
- | ResNet-Mixed-Convolution | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 8.892 ms | 1 - 52 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
72
- | ResNet-Mixed-Convolution | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 54.711 ms | 0 - 53 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
73
- | ResNet-Mixed-Convolution | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 28.01 ms | 1 - 48 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
74
- | ResNet-Mixed-Convolution | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 8.383 ms | 1 - 18 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
75
- | ResNet-Mixed-Convolution | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 14.741 ms | 1 - 50 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
76
- | ResNet-Mixed-Convolution | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 8.341 ms | 1 - 18 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
77
- | ResNet-Mixed-Convolution | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 8.892 ms | 1 - 52 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
78
- | ResNet-Mixed-Convolution | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 8.37 ms | 1 - 17 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
79
- | ResNet-Mixed-Convolution | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 7.78 ms | 0 - 31 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.onnx) |
80
- | ResNet-Mixed-Convolution | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 6.263 ms | 1 - 63 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
81
- | ResNet-Mixed-Convolution | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.904 ms | 0 - 62 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.onnx) |
82
- | ResNet-Mixed-Convolution | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 5.839 ms | 1 - 48 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
83
- | ResNet-Mixed-Convolution | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 5.708 ms | 1 - 48 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.onnx) |
84
- | ResNet-Mixed-Convolution | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 9.986 ms | 29 - 29 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
85
- | ResNet-Mixed-Convolution | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.298 ms | 11 - 11 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.onnx) |
86
 
87
 
88
 
 
31
  - Model checkpoint: Kinectics-400
32
  - Input resolution: 112x112
33
  - Number of parameters: 11.7M
34
+ - Model size (float): 44.6 MB
35
+ - Model size (w8a16): 11.5 MB
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
 
56
  | ResNet-Mixed-Convolution | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 25.775 ms | 0 - 75 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.dlc) |
57
  | ResNet-Mixed-Convolution | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 139.769 ms | 31 - 92 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
58
  | ResNet-Mixed-Convolution | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 14.085 ms | 2 - 28 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.dlc) |
59
+ | ResNet-Mixed-Convolution | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 13.604 ms | 0 - 84 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
60
  | ResNet-Mixed-Convolution | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 103.846 ms | 31 - 89 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
61
  | ResNet-Mixed-Convolution | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 10.025 ms | 0 - 85 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.dlc) |
62
+ | ResNet-Mixed-Convolution | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 10.091 ms | 2 - 87 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
63
  | ResNet-Mixed-Convolution | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 126.007 ms | 30 - 79 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
64
  | ResNet-Mixed-Convolution | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 10.72 ms | 2 - 79 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.dlc) |
65
+ | ResNet-Mixed-Convolution | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 8.382 ms | 2 - 82 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
66
  | ResNet-Mixed-Convolution | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 16.103 ms | 291 - 291 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.dlc) |
67
+ | ResNet-Mixed-Convolution | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 15.03 ms | 22 - 22 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
68
+ | ResNet-Mixed-Convolution | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 28.022 ms | 1 - 51 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
69
+ | ResNet-Mixed-Convolution | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 12.871 ms | 1 - 68 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
70
+ | ResNet-Mixed-Convolution | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 8.346 ms | 1 - 16 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
71
+ | ResNet-Mixed-Convolution | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 8.905 ms | 1 - 51 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
72
+ | ResNet-Mixed-Convolution | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 54.772 ms | 1 - 53 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
73
+ | ResNet-Mixed-Convolution | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 28.022 ms | 1 - 51 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
74
+ | ResNet-Mixed-Convolution | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 8.349 ms | 1 - 16 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
75
+ | ResNet-Mixed-Convolution | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 14.759 ms | 1 - 51 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
76
+ | ResNet-Mixed-Convolution | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 8.363 ms | 1 - 15 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
77
+ | ResNet-Mixed-Convolution | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 8.905 ms | 1 - 51 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
78
+ | ResNet-Mixed-Convolution | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 8.349 ms | 1 - 16 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
79
+ | ResNet-Mixed-Convolution | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 7.696 ms | 0 - 32 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.onnx) |
80
+ | ResNet-Mixed-Convolution | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 6.206 ms | 1 - 64 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
81
+ | ResNet-Mixed-Convolution | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.87 ms | 1 - 65 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.onnx) |
82
+ | ResNet-Mixed-Convolution | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 5.816 ms | 1 - 48 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
83
+ | ResNet-Mixed-Convolution | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 4.831 ms | 1 - 48 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.onnx) |
84
+ | ResNet-Mixed-Convolution | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 9.99 ms | 29 - 29 MB | NPU | [ResNet-Mixed-Convolution.dlc](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.dlc) |
85
+ | ResNet-Mixed-Convolution | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.337 ms | 12 - 12 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a16.onnx) |
86
 
87
 
88
 
ResNet-Mixed-Convolution.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e9dd1ad2cc3ab870338a6879e0c8185f913bd1473a9cd6e8a0bf18d4b7ce051
3
- size 46775992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c397163583fbe3a4dfa9688e259095db7a5e23bd006034032cb0901ae3776ce3
3
+ size 46777822
ResNet-Mixed-Convolution_w8a16.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc7f8511067ef14950ffa4a5b52e55d195ed0250f45d93f1b3c0c706255cd3a0
3
- size 12028455
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c482694ad8c7a1e8f6d88cdce83161a64b70599f58e202b021e62474b5c1d4f
3
+ size 12028398
ResNet-Mixed-Convolution_w8a16.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c11967483315f74250eda40565be1b291d641c0b3fbc7ed331d74b67fe1391cf
3
- size 46826645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:138ac8203b518b76a24064ceb293f72293ea96ca033b25f8e8de0e3a91693f8d
3
+ size 46826669