User | Puffin |
Upload Date | January 27 2025 03:14 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Intel Core i7-1185G7 |
System Information | |
---|---|
Operating System | KDE neon 6.2 |
Model | Micro-Star International Co., Ltd. Prestige 15 A11SB |
Motherboard | Micro-Star International Co., Ltd. MS-16S6 |
CPU Information | |
---|---|
Name | Intel Core i7-1185G7 |
Topology | 1 Processor, 4 Cores, 8 Threads |
Identifier | GenuineIntel Family 6 Model 140 Stepping 1 |
Base Frequency | 4.80 GHz |
Cluster 1 | 0 Cores |
Memory Information | |
---|---|
Size | 31.06 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1074
199.8 IPS |
|
Image Classification (HP)
|
100% |
1078
200.5 IPS |
|
Image Classification (Q)
|
99% |
443
82.6 IPS |
|
Image Segmentation (SP)
|
100% |
1403
22.7 IPS |
|
Image Segmentation (HP)
|
100% |
1408
22.8 IPS |
|
Image Segmentation (Q)
|
98% |
612
9.95 IPS |
|
Pose Estimation (SP)
|
100% |
1769
2.06 IPS |
|
Pose Estimation (HP)
|
100% |
1778
2.07 IPS |
|
Pose Estimation (Q)
|
96% |
1383
1.62 IPS |
|
Object Detection (SP)
|
100% |
1129
89.5 IPS |
|
Object Detection (HP)
|
100% |
1142
90.6 IPS |
|
Object Detection (Q)
|
85% |
599
48.2 IPS |
|
Face Detection (SP)
|
100% |
2092
24.9 IPS |
|
Face Detection (HP)
|
100% |
2004
23.8 IPS |
|
Face Detection (Q)
|
97% |
1338
16.0 IPS |
|
Depth Estimation (SP)
|
100% |
1921
14.8 IPS |
|
Depth Estimation (HP)
|
99% |
1928
14.9 IPS |
|
Depth Estimation (Q)
|
63% |
1110
10.4 IPS |
|
Style Transfer (SP)
|
100% |
2537
3.26 IPS |
|
Style Transfer (HP)
|
100% |
2546
3.27 IPS |
|
Style Transfer (Q)
|
98% |
3045
3.93 IPS |
|
Image Super-Resolution (SP)
|
100% |
1237
45.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
1245
46.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
775
28.7 IPS |
|
Text Classification (SP)
|
100% |
1308
1.75 KIPS |
|
Text Classification (HP)
|
100% |
1312
1.75 KIPS |
|
Text Classification (Q)
|
92% |
493
662.2 IPS |
|
Machine Translation (SP)
|
100% |
1753
30.2 IPS |
|
Machine Translation (HP)
|
100% |
1796
30.9 IPS |
|
Machine Translation (Q)
|
58% |
445
10.4 IPS |