Upload Date | November 19 2024 07:48 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Intel Core i5-7200U |
System Information | |
---|---|
Operating System | Ubuntu 24.04.1 LTS |
Model | SAMSUNG ELECTRONICS CO., LTD. 900X3J |
Motherboard | SAMSUNG ELECTRONICS CO., LTD. NP900X3J-KV1BR |
CPU Information | |
---|---|
Name | Intel Core i5-7200U |
Topology | 1 Processor, 2 Cores, 4 Threads |
Identifier | GenuineIntel Family 6 Model 142 Stepping 9 |
Base Frequency | 3.10 GHz |
Cluster 1 | 0 Cores |
Memory Information | |
---|---|
Size | 7.67 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
230
42.8 IPS |
|
Image Classification (HP)
|
100% |
248
46.0 IPS |
|
Image Classification (Q)
|
99% |
74
13.7 IPS |
|
Image Segmentation (SP)
|
100% |
118
1.91 IPS |
|
Image Segmentation (HP)
|
100% |
143
2.32 IPS |
|
Image Segmentation (Q)
|
98% |
80
1.30 IPS |
|
Pose Estimation (SP)
|
100% |
154
0.18 IPS |
|
Pose Estimation (HP)
|
100% |
263
0.31 IPS |
|
Pose Estimation (Q)
|
96% |
262
0.31 IPS |
|
Object Detection (SP)
|
100% |
126
10.0 IPS |
|
Object Detection (HP)
|
100% |
116
9.20 IPS |
|
Object Detection (Q)
|
85% |
72
5.78 IPS |
|
Face Detection (SP)
|
100% |
266
3.16 IPS |
|
Face Detection (HP)
|
100% |
301
3.57 IPS |
|
Face Detection (Q)
|
97% |
268
3.20 IPS |
|
Depth Estimation (SP)
|
100% |
371
2.86 IPS |
|
Depth Estimation (HP)
|
99% |
252
1.94 IPS |
|
Depth Estimation (Q)
|
63% |
266
2.50 IPS |
|
Style Transfer (SP)
|
100% |
566
0.73 IPS |
|
Style Transfer (HP)
|
100% |
435
0.56 IPS |
|
Style Transfer (Q)
|
98% |
616
0.79 IPS |
|
Image Super-Resolution (SP)
|
100% |
139
5.13 IPS |
|
Image Super-Resolution (HP)
|
100% |
135
4.97 IPS |
|
Image Super-Resolution (Q)
|
97% |
222
8.22 IPS |
|
Text Classification (SP)
|
100% |
505
673.6 IPS |
|
Text Classification (HP)
|
100% |
597
796.6 IPS |
|
Text Classification (Q)
|
92% |
136
182.7 IPS |
|
Machine Translation (SP)
|
100% |
503
8.66 IPS |
|
Machine Translation (HP)
|
100% |
369
6.35 IPS |
|
Machine Translation (Q)
|
58% |
113
2.64 IPS |