Upload Date | July 06 2024 10:37 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy S21 5G |
Model ID | samsung SM-G991B |
Motherboard | exynos2100 |
Governor | energy_step |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
Base Frequency | 2.21 GHz |
Cluster 1 | 4 Cores @ 2.21 GHz |
Cluster 2 | 3 Cores @ 2.81 GHz |
Cluster 3 | 1 Core @ 2.91 GHz |
Memory Information | |
---|---|
Size | 7.03 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
305
57.1 IPS |
|
Image Classification (F16)
|
100% |
302
56.5 IPS |
|
Image Classification (I8)
|
97% |
640
119.7 IPS |
|
Image Segmentation (F32)
|
100% |
360
6.02 IPS |
|
Image Segmentation (F16)
|
100% |
315
5.25 IPS |
|
Image Segmentation (I8)
|
98% |
318
5.31 IPS |
|
Pose Estimation (F32)
|
100% |
591
0.72 IPS |
|
Pose Estimation (F16)
|
100% |
579
0.70 IPS |
|
Pose Estimation (I8)
|
100% |
2635
3.19 IPS |
|
Object Detection (F32)
|
100% |
238
17.7 IPS |
|
Object Detection (F16)
|
100% |
268
20.0 IPS |
|
Object Detection (I8)
|
61% |
253
18.9 IPS |
|
Face Detection (F32)
|
100% |
350
4.17 IPS |
|
Face Detection (F16)
|
100% |
336
3.99 IPS |
|
Face Detection (I8)
|
86% |
1411
16.8 IPS |
|
Depth Estimation (F32)
|
100% |
573
4.44 IPS |
|
Depth Estimation (F16)
|
100% |
410
3.18 IPS |
|
Depth Estimation (I8)
|
95% |
882
6.84 IPS |
|
Style Transfer (F32)
|
100% |
1117
1.47 IPS |
|
Style Transfer (F16)
|
100% |
1071
1.41 IPS |
|
Style Transfer (I8)
|
98% |
2240
2.95 IPS |
|
Image Super-Resolution (F32)
|
100% |
365
13.0 IPS |
|
Image Super-Resolution (F16)
|
100% |
350
12.5 IPS |
|
Image Super-Resolution (I8)
|
98% |
847
30.3 IPS |
|
Text Classification (F32)
|
100% |
362
521.0 IPS |
|
Text Classification (F16)
|
100% |
383
549.8 IPS |
|
Text Classification (I8)
|
92% |
308
442.6 IPS |
|
Machine Translation (F32)
|
100% |
493
9.07 IPS |
|
Machine Translation (F16)
|
100% |
445
8.18 IPS |
|
Machine Translation (I8)
|
64% |
63
1.16 IPS |