User | grinceur |
Upload Date | October 11 2024 12:31 PM |
Views | 11 |
AI Information | |
---|---|
Framework | ONNX |
Backend | CPU |
Device | Snapdragon(TM) 835 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Famille (64-bit) |
Model | THOMSON Z3-13Q835-4T64 |
Motherboard | Qualcomm Technologies, Inc. LNVNB161216 |
Power Plan | Utilisation normale |
CPU Information | |
---|---|
Name | Snapdragon(TM) 835 |
Topology | 8 Processors, 8 Cores |
Identifier | ARMv8 (64-bit) Family 8 Model 801 Revision A04 |
Base Frequency | 1.90 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 4.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
75
13.9 IPS |
|
Image Classification (HP)
|
100% |
58
10.8 IPS |
|
Image Classification (Q)
|
99% |
273
50.9 IPS |
|
Image Segmentation (SP)
|
100% |
72
1.16 IPS |
|
Image Segmentation (HP)
|
100% |
102
1.65 IPS |
|
Image Segmentation (Q)
|
98% |
266
4.32 IPS |
|
Pose Estimation (SP)
|
100% |
312
0.36 IPS |
|
Pose Estimation (HP)
|
100% |
299
0.35 IPS |
|
Pose Estimation (Q)
|
95% |
757
0.89 IPS |
|
Object Detection (SP)
|
100% |
87
6.93 IPS |
|
Object Detection (HP)
|
100% |
64
5.11 IPS |
|
Object Detection (Q)
|
88% |
272
21.8 IPS |
|
Face Detection (SP)
|
100% |
211
2.51 IPS |
|
Face Detection (HP)
|
100% |
172
2.04 IPS |
|
Face Detection (Q)
|
97% |
570
6.80 IPS |
|
Depth Estimation (SP)
|
100% |
243
1.87 IPS |
|
Depth Estimation (HP)
|
99% |
209
1.61 IPS |
|
Depth Estimation (Q)
|
77% |
604
4.83 IPS |
|
Style Transfer (SP)
|
100% |
869
1.12 IPS |
|
Style Transfer (HP)
|
100% |
856
1.10 IPS |
|
Style Transfer (Q)
|
98% |
1825
2.35 IPS |
|
Image Super-Resolution (SP)
|
100% |
158
5.82 IPS |
|
Image Super-Resolution (HP)
|
100% |
152
5.63 IPS |
|
Image Super-Resolution (Q)
|
99% |
284
10.5 IPS |
|
Text Classification (SP)
|
100% |
180
240.1 IPS |
|
Text Classification (HP)
|
100% |
73
98.1 IPS |
|
Text Classification (Q)
|
97% |
104
140.0 IPS |
|
Machine Translation (SP)
|
100% |
175
3.02 IPS |
|
Machine Translation (HP)
|
100% |
76
1.31 IPS |
|
Machine Translation (Q)
|
60% |
234
5.21 IPS |