Upload Date | May 22 2024 04:24 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy S21 Ultra 5G |
Model ID | samsung SM-G998U |
Motherboard | lahaina |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM SM8350 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 10.07 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
409
76.6 IPS |
|
Image Classification (F16)
|
100% |
413
77.2 IPS |
|
Image Classification (I8)
|
97% |
377
70.5 IPS |
|
Image Segmentation (F32)
|
100% |
611
10.2 IPS |
|
Image Segmentation (F16)
|
100% |
801
13.4 IPS |
|
Image Segmentation (I8)
|
98% |
708
11.8 IPS |
|
Pose Estimation (F32)
|
100% |
715
0.87 IPS |
|
Pose Estimation (F16)
|
100% |
375
0.45 IPS |
|
Pose Estimation (I8)
|
100% |
396
0.48 IPS |
|
Object Detection (F32)
|
100% |
315
23.5 IPS |
|
Object Detection (F16)
|
100% |
306
22.9 IPS |
|
Object Detection (I8)
|
62% |
233
17.4 IPS |
|
Face Detection (F32)
|
100% |
1464
17.4 IPS |
|
Face Detection (F16)
|
97% |
2004
23.8 IPS |
|
Face Detection (I8)
|
87% |
1529
18.2 IPS |
|
Depth Estimation (F32)
|
100% |
946
7.34 IPS |
|
Depth Estimation (F16)
|
100% |
1312
10.2 IPS |
|
Depth Estimation (I8)
|
95% |
1302
10.1 IPS |
|
Style Transfer (F32)
|
100% |
2083
2.74 IPS |
|
Style Transfer (F16)
|
100% |
3318
4.37 IPS |
|
Style Transfer (I8)
|
98% |
3723
4.90 IPS |
|
Image Super-Resolution (F32)
|
100% |
469
16.7 IPS |
|
Image Super-Resolution (F16)
|
100% |
491
17.5 IPS |
|
Image Super-Resolution (I8)
|
98% |
493
17.6 IPS |
|
Text Classification (F32)
|
100% |
265
380.8 IPS |
|
Text Classification (F16)
|
100% |
266
382.3 IPS |
|
Text Classification (I8)
|
92% |
509
730.9 IPS |
|
Machine Translation (F32)
|
100% |
427
7.86 IPS |
|
Machine Translation (F16)
|
100% |
407
7.50 IPS |
|
Machine Translation (I8)
|
64% |
528
9.71 IPS |