Upload Date | September 12 2025 09:03 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Intel Core i9-13900HX |
System Information | |
---|---|
Operating System | Pop!_OS 22.04 LTS |
Model | System76 Serval WS |
Motherboard | System76 Serval WS |
CPU Information | |
---|---|
Name | Intel Core i9-13900HX |
Topology | 1 Processor, 24 Cores, 32 Threads |
Identifier | GenuineIntel Family 6 Model 183 Stepping 1 |
Base Frequency | 5.20 GHz |
Cluster 1 | 0 Cores |
Memory Information | |
---|---|
Size | 31.18 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2001
372.1 IPS |
|
Image Classification (HP)
|
100% |
2311
429.8 IPS |
|
Image Classification (Q)
|
99% |
1403
261.8 IPS |
|
Image Segmentation (SP)
|
100% |
3302
53.5 IPS |
|
Image Segmentation (HP)
|
100% |
3254
52.8 IPS |
|
Image Segmentation (Q)
|
98% |
1345
21.9 IPS |
|
Pose Estimation (SP)
|
100% |
3106
3.62 IPS |
|
Pose Estimation (HP)
|
100% |
2763
3.22 IPS |
|
Pose Estimation (Q)
|
96% |
3693
4.33 IPS |
|
Object Detection (SP)
|
100% |
2313
183.4 IPS |
|
Object Detection (HP)
|
100% |
2329
184.8 IPS |
|
Object Detection (Q)
|
85% |
1509
121.5 IPS |
|
Face Detection (SP)
|
100% |
3438
40.8 IPS |
|
Face Detection (HP)
|
100% |
3428
40.7 IPS |
|
Face Detection (Q)
|
97% |
2936
35.0 IPS |
|
Depth Estimation (SP)
|
100% |
2792
21.5 IPS |
|
Depth Estimation (HP)
|
99% |
2765
21.3 IPS |
|
Depth Estimation (Q)
|
63% |
2284
21.4 IPS |
|
Style Transfer (SP)
|
100% |
2924
3.76 IPS |
|
Style Transfer (HP)
|
100% |
2925
3.76 IPS |
|
Style Transfer (Q)
|
98% |
6621
8.54 IPS |
|
Image Super-Resolution (SP)
|
100% |
2222
82.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
1832
67.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
1583
58.7 IPS |
|
Text Classification (SP)
|
100% |
1471
1.96 KIPS |
|
Text Classification (HP)
|
100% |
1456
1.94 KIPS |
|
Text Classification (Q)
|
92% |
662
889.0 IPS |
|
Machine Translation (SP)
|
100% |
3109
53.5 IPS |
|
Machine Translation (HP)
|
100% |
3040
52.4 IPS |
|
Machine Translation (Q)
|
58% |
614
14.4 IPS |