qaihm-bot commited on
Commit
ed63ef3
·
verified ·
1 Parent(s): 13133c7

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

.gitattributes CHANGED
@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
36
  Segformer-Base.dlc filter=lfs diff=lfs merge=lfs -text
37
  Segformer-Base_w8a16.dlc filter=lfs diff=lfs merge=lfs -text
38
  Segformer-Base_w8a8.dlc filter=lfs diff=lfs merge=lfs -text
 
 
36
  Segformer-Base.dlc filter=lfs diff=lfs merge=lfs -text
37
  Segformer-Base_w8a16.dlc filter=lfs diff=lfs merge=lfs -text
38
  Segformer-Base_w8a8.dlc filter=lfs diff=lfs merge=lfs -text
39
+ 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/huggingface/transformers/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
@@ -30,9 +30,11 @@ More details on model performance across various devices, can be found
30
  - **Model Stats:**
31
  - Model checkpoint: nvidia/segformer-b0-finetuned-ade-512-512
32
  - Input resolution: 512x512
33
- - Number of parameters: 3.7M
34
- - Model size: 14.4 MB
35
  - Number of output classes: 150
 
 
 
 
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
@@ -56,65 +58,65 @@ More details on model performance across various devices, can be found
56
  | Segformer-Base | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 116.315 ms | 2 - 51 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
57
  | Segformer-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 114.914 ms | 0 - 42 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
58
  | Segformer-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 114.277 ms | 3 - 19 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
59
- | Segformer-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 110.869 ms | 20 - 51 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
60
  | Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 86.645 ms | 8 - 72 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
61
  | Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 86.093 ms | 3 - 60 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
62
- | Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 83.425 ms | 21 - 81 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
63
  | Segformer-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 76.112 ms | 9 - 62 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
64
  | Segformer-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 92.911 ms | 3 - 54 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
65
- | Segformer-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 78.241 ms | 21 - 67 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
66
  | Segformer-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 119.744 ms | 31 - 31 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
67
- | Segformer-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 118.375 ms | 35 - 35 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
68
- | Segformer-Base | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 22.589 ms | 0 - 35 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
69
- | Segformer-Base | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 16.08 ms | 2 - 45 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
70
- | Segformer-Base | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 12.294 ms | 2 - 14 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
71
- | Segformer-Base | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 13.298 ms | 2 - 38 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
72
- | Segformer-Base | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 44.511 ms | 2 - 69 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
73
- | Segformer-Base | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 22.589 ms | 0 - 35 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
74
- | Segformer-Base | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 12.252 ms | 2 - 17 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
75
- | Segformer-Base | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 15.09 ms | 2 - 39 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
76
- | Segformer-Base | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 12.437 ms | 2 - 14 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
77
- | Segformer-Base | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 13.298 ms | 2 - 38 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
78
- | Segformer-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 12.31 ms | 2 - 14 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
79
- | Segformer-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 40.224 ms | 31 - 109 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
80
- | Segformer-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 8.172 ms | 2 - 48 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
81
- | Segformer-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 29.02 ms | 29 - 291 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
82
- | Segformer-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 7.292 ms | 1 - 41 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
83
- | Segformer-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 28.532 ms | 26 - 235 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
84
- | Segformer-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 13.693 ms | 0 - 0 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
85
- | Segformer-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 43.855 ms | 55 - 55 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
86
- | Segformer-Base | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 23.648 ms | 2 - 40 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
87
- | Segformer-Base | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 12.996 ms | 1 - 33 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
88
- | Segformer-Base | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 13.514 ms | 2 - 49 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
89
- | Segformer-Base | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 8.385 ms | 1 - 46 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
90
- | Segformer-Base | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 13.184 ms | 2 - 15 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
91
- | Segformer-Base | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 7.165 ms | 1 - 10 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
92
- | Segformer-Base | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 13.734 ms | 2 - 40 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
93
- | Segformer-Base | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 7.795 ms | 1 - 34 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
94
- | Segformer-Base | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 132.091 ms | 15 - 56 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
95
- | Segformer-Base | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 25.935 ms | 1 - 48 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
96
- | Segformer-Base | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 442.717 ms | 41 - 59 MB | GPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
97
- | Segformer-Base | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 23.648 ms | 2 - 40 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
98
- | Segformer-Base | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 12.996 ms | 1 - 33 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
99
- | Segformer-Base | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 13.29 ms | 2 - 15 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
100
- | Segformer-Base | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 7.135 ms | 1 - 12 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
101
- | Segformer-Base | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 15.487 ms | 2 - 43 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
102
- | Segformer-Base | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 8.958 ms | 1 - 35 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
103
- | Segformer-Base | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 13.199 ms | 2 - 15 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
104
- | Segformer-Base | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 7.132 ms | 1 - 11 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
105
- | Segformer-Base | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 13.734 ms | 2 - 40 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
106
- | Segformer-Base | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 7.795 ms | 1 - 34 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
107
- | Segformer-Base | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 13.163 ms | 2 - 14 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
108
- | Segformer-Base | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 7.133 ms | 1 - 12 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
109
- | Segformer-Base | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 17.824 ms | 2 - 25 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
110
- | Segformer-Base | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 9.068 ms | 2 - 51 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
111
- | Segformer-Base | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 4.756 ms | 1 - 46 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
112
- | Segformer-Base | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 12.495 ms | 7 - 66 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
113
- | Segformer-Base | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 9.281 ms | 1 - 40 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
114
- | Segformer-Base | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 4.429 ms | 1 - 39 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
115
- | Segformer-Base | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 11.905 ms | 5 - 56 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
116
- | Segformer-Base | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8.004 ms | 18 - 18 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
117
- | Segformer-Base | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 19.367 ms | 9 - 9 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
118
 
119
 
120
 
 
30
  - **Model Stats:**
31
  - Model checkpoint: nvidia/segformer-b0-finetuned-ade-512-512
32
  - Input resolution: 512x512
 
 
33
  - Number of output classes: 150
34
+ - Number of parameters: 3.75M
35
+ - Model size (float): 14.4 MB
36
+ - Model size (w8a16): 4.57 MB
37
+ - Model size (w8a8): 3.90 MB
38
 
39
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
40
  |---|---|---|---|---|---|---|---|---|
 
58
  | Segformer-Base | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 116.315 ms | 2 - 51 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
59
  | Segformer-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 114.914 ms | 0 - 42 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
60
  | Segformer-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 114.277 ms | 3 - 19 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
61
+ | Segformer-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 110.684 ms | 22 - 53 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
62
  | Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 86.645 ms | 8 - 72 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
63
  | Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 86.093 ms | 3 - 60 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
64
+ | Segformer-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 84.246 ms | 26 - 84 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
65
  | Segformer-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 76.112 ms | 9 - 62 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.tflite) |
66
  | Segformer-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 92.911 ms | 3 - 54 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
67
+ | Segformer-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 94.634 ms | 26 - 73 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
68
  | Segformer-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 119.744 ms | 31 - 31 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.dlc) |
69
+ | Segformer-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 118.293 ms | 35 - 35 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base.onnx) |
70
+ | Segformer-Base | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 22.12 ms | 2 - 37 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
71
+ | Segformer-Base | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 14.453 ms | 2 - 46 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
72
+ | Segformer-Base | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 12.227 ms | 2 - 14 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
73
+ | Segformer-Base | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 12.605 ms | 2 - 38 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
74
+ | Segformer-Base | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 44.72 ms | 2 - 69 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
75
+ | Segformer-Base | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 22.12 ms | 2 - 37 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
76
+ | Segformer-Base | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 12.347 ms | 2 - 14 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
77
+ | Segformer-Base | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 14.846 ms | 2 - 38 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
78
+ | Segformer-Base | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 12.255 ms | 2 - 13 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
79
+ | Segformer-Base | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 12.605 ms | 2 - 38 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
80
+ | Segformer-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 12.298 ms | 2 - 14 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
81
+ | Segformer-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 39.84 ms | 31 - 105 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
82
+ | Segformer-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 8.226 ms | 2 - 51 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
83
+ | Segformer-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 27.765 ms | 24 - 282 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
84
+ | Segformer-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 7.417 ms | 2 - 43 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
85
+ | Segformer-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 29.544 ms | 29 - 241 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
86
+ | Segformer-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 13.624 ms | 1 - 1 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
87
+ | Segformer-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 45.624 ms | 58 - 58 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
88
+ | Segformer-Base | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 23.299 ms | 2 - 40 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
89
+ | Segformer-Base | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 12.961 ms | 1 - 33 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
90
+ | Segformer-Base | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 13.628 ms | 2 - 47 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
91
+ | Segformer-Base | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 8.276 ms | 1 - 43 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
92
+ | Segformer-Base | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 12.945 ms | 2 - 12 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
93
+ | Segformer-Base | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 7.134 ms | 0 - 10 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
94
+ | Segformer-Base | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 13.523 ms | 2 - 41 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
95
+ | Segformer-Base | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 7.764 ms | 1 - 34 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
96
+ | Segformer-Base | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 126.846 ms | 15 - 55 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
97
+ | Segformer-Base | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 26.472 ms | 1 - 49 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
98
+ | Segformer-Base | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 425.541 ms | 45 - 61 MB | GPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
99
+ | Segformer-Base | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 23.299 ms | 2 - 40 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
100
+ | Segformer-Base | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 12.961 ms | 1 - 33 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
101
+ | Segformer-Base | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 13.006 ms | 2 - 17 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
102
+ | Segformer-Base | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 7.105 ms | 0 - 10 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
103
+ | Segformer-Base | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 15.496 ms | 2 - 42 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
104
+ | Segformer-Base | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 8.945 ms | 1 - 35 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
105
+ | Segformer-Base | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 12.996 ms | 2 - 17 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
106
+ | Segformer-Base | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 7.109 ms | 1 - 8 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
107
+ | Segformer-Base | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 13.523 ms | 2 - 41 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
108
+ | Segformer-Base | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 7.764 ms | 1 - 34 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
109
+ | Segformer-Base | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 12.983 ms | 2 - 13 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
110
+ | Segformer-Base | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 7.108 ms | 1 - 11 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
111
+ | Segformer-Base | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 17.99 ms | 3 - 25 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
112
+ | Segformer-Base | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 8.881 ms | 2 - 49 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
113
+ | Segformer-Base | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 4.766 ms | 1 - 45 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
114
+ | Segformer-Base | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 12.54 ms | 7 - 71 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
115
+ | Segformer-Base | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 9.246 ms | 2 - 44 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
116
+ | Segformer-Base | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 4.355 ms | 1 - 40 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
117
+ | Segformer-Base | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 11.89 ms | 7 - 59 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
118
+ | Segformer-Base | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 7.993 ms | 0 - 0 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
119
+ | Segformer-Base | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 19.401 ms | 9 - 9 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.onnx) |
120
 
121
 
122
 
Segformer-Base.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7a91ccebd74cb978a659e02b127bb5ae4d1bf9970be76f9688f974721337336
3
- size 15145277
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f204084f2fa8a11c746e041193971312d9c0d0460c29148515a1ea3d42e872c6
3
+ size 15160235
Segformer-Base_w8a16.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fade3511d45d6f444f8f630e48455ab0005c93233818f5bdc66f57ec14274eac
3
- size 4754166
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce732c1ab966b9b8fda73748377d8c9040f7769d6328e42d956f838c1f91a2c0
3
+ size 4754109
Segformer-Base_w8a16.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:825a6b5fc08372f08925e151ec7dc9a87df66ab42277ec0e7b51056f026b87c7
3
- size 15454331
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:029a2b14dac3c912dccc1051d1e632642920c968831cf49b3f6c53cdba57438e
3
+ size 15453043
Segformer-Base_w8a8.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b25891d76bf9a81637b81dba4dd8152cc2a30923b3a855b82c91b666c483a96
3
- size 4741903
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b89b70faf73786d24d6ee2b643659bf71f69d2a9a9b6734c7f493372191a74b1
3
+ size 4741846
Segformer-Base_w8a8.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d98860398daeea7f59e1b0b518a17bbbdefb1cf227c989ac9871e0178f75bcf
3
- size 15445355
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b168f1d7d50a0d88f9c22aded99b137e45e5e5e4f29fe194389ee8e6483b80
3
+ size 15445345
Segformer-Base_w8a8.tflite CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef433cde49eb9aeb6007d0826a4330b74109ea1acb0566e41480a9dc668c510c
3
  size 4087088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c123c05a54c81290e6a608cd9be1322d9713e9f10001230130fd8213ea098a2
3
  size 4087088