Upload Date | April 27 2024 04:52 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy S21 FE |
Model ID | samsung SM-G990U |
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 | 5.24 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
422
79.0 IPS |
|
Image Classification (F16)
|
100% |
409
76.4 IPS |
|
Image Classification (I8)
|
97% |
393
73.5 IPS |
|
Image Segmentation (F32)
|
100% |
614
10.2 IPS |
|
Image Segmentation (F16)
|
100% |
683
11.4 IPS |
|
Image Segmentation (I8)
|
98% |
661
11.0 IPS |
|
Pose Estimation (F32)
|
100% |
715
0.87 IPS |
|
Pose Estimation (F16)
|
100% |
393
0.48 IPS |
|
Pose Estimation (I8)
|
100% |
390
0.47 IPS |
|
Object Detection (F32)
|
100% |
342
25.5 IPS |
|
Object Detection (F16)
|
100% |
374
27.9 IPS |
|
Object Detection (I8)
|
62% |
239
17.9 IPS |
|
Face Detection (F32)
|
100% |
1428
17.0 IPS |
|
Face Detection (F16)
|
97% |
1936
23.0 IPS |
|
Face Detection (I8)
|
87% |
1859
22.1 IPS |
|
Depth Estimation (F32)
|
100% |
1015
7.87 IPS |
|
Depth Estimation (F16)
|
100% |
1277
9.90 IPS |
|
Depth Estimation (I8)
|
95% |
1248
9.68 IPS |
|
Style Transfer (F32)
|
100% |
2163
2.85 IPS |
|
Style Transfer (F16)
|
100% |
3728
4.90 IPS |
|
Style Transfer (I8)
|
98% |
3726
4.90 IPS |
|
Image Super-Resolution (F32)
|
100% |
504
18.0 IPS |
|
Image Super-Resolution (F16)
|
100% |
524
18.7 IPS |
|
Image Super-Resolution (I8)
|
98% |
527
18.8 IPS |
|
Text Classification (F32)
|
100% |
264
378.8 IPS |
|
Text Classification (F16)
|
100% |
278
399.0 IPS |
|
Text Classification (I8)
|
92% |
509
730.9 IPS |
|
Machine Translation (F32)
|
100% |
455
8.37 IPS |
|
Machine Translation (F16)
|
100% |
446
8.21 IPS |
|
Machine Translation (I8)
|
64% |
573
10.5 IPS |