User | Technologov |
Upload Date | January 28 2025 08:27 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Intel Core i5-8350U |
System Information | |
---|---|
Operating System | Debian GNU/Linux 12 (bookworm) |
Model | HP HP EliteBook 840 G5 |
Motherboard | HP 83B2 |
CPU Information | |
---|---|
Name | Intel Core i5-8350U |
Topology | 1 Processor, 4 Cores, 8 Threads |
Identifier | GenuineIntel Family 6 Model 142 Stepping 10 |
Base Frequency | 3.60 GHz |
Cluster 1 | 0 Cores |
Memory Information | |
---|---|
Size | 15.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
763
141.9 IPS |
|
Image Classification (HP)
|
100% |
743
138.2 IPS |
|
Image Classification (Q)
|
99% |
377
70.2 IPS |
|
Image Segmentation (SP)
|
100% |
826
13.4 IPS |
|
Image Segmentation (HP)
|
100% |
840
13.6 IPS |
|
Image Segmentation (Q)
|
98% |
459
7.47 IPS |
|
Pose Estimation (SP)
|
100% |
936
1.09 IPS |
|
Pose Estimation (HP)
|
100% |
933
1.09 IPS |
|
Pose Estimation (Q)
|
96% |
836
0.98 IPS |
|
Object Detection (SP)
|
100% |
747
59.3 IPS |
|
Object Detection (HP)
|
100% |
737
58.5 IPS |
|
Object Detection (Q)
|
85% |
399
32.1 IPS |
|
Face Detection (SP)
|
100% |
1207
14.3 IPS |
|
Face Detection (HP)
|
100% |
1203
14.3 IPS |
|
Face Detection (Q)
|
97% |
871
10.4 IPS |
|
Depth Estimation (SP)
|
100% |
1120
8.63 IPS |
|
Depth Estimation (HP)
|
99% |
1111
8.56 IPS |
|
Depth Estimation (Q)
|
63% |
738
6.92 IPS |
|
Style Transfer (SP)
|
100% |
1520
1.95 IPS |
|
Style Transfer (HP)
|
100% |
1519
1.95 IPS |
|
Style Transfer (Q)
|
98% |
1870
2.41 IPS |
|
Image Super-Resolution (SP)
|
100% |
672
24.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
708
26.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
566
21.0 IPS |
|
Text Classification (SP)
|
100% |
1113
1.49 KIPS |
|
Text Classification (HP)
|
100% |
1115
1.49 KIPS |
|
Text Classification (Q)
|
92% |
341
457.8 IPS |
|
Machine Translation (SP)
|
100% |
1270
21.9 IPS |
|
Machine Translation (HP)
|
100% |
1323
22.8 IPS |
|
Machine Translation (Q)
|
58% |
262
6.15 IPS |