Upload Date | May 29 2024 07:55 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Galaxy S20 FE 5G |
Model ID | samsung SM-G780G |
Motherboard | kona |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 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 | 5.50 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
285
53.3 IPS |
|
Image Classification (F16)
|
100% |
274
51.3 IPS |
|
Image Classification (I8)
|
97% |
635
118.8 IPS |
|
Image Segmentation (F32)
|
100% |
383
6.39 IPS |
|
Image Segmentation (F16)
|
100% |
379
6.34 IPS |
|
Image Segmentation (I8)
|
98% |
507
8.47 IPS |
|
Pose Estimation (F32)
|
100% |
585
0.71 IPS |
|
Pose Estimation (F16)
|
100% |
597
0.72 IPS |
|
Pose Estimation (I8)
|
100% |
2706
3.28 IPS |
|
Object Detection (F32)
|
100% |
316
23.6 IPS |
|
Object Detection (F16)
|
100% |
365
27.2 IPS |
|
Object Detection (I8)
|
61% |
832
62.1 IPS |
|
Face Detection (F32)
|
100% |
633
7.53 IPS |
|
Face Detection (F16)
|
100% |
645
7.67 IPS |
|
Face Detection (I8)
|
86% |
1565
18.6 IPS |
|
Depth Estimation (F32)
|
100% |
582
4.51 IPS |
|
Depth Estimation (F16)
|
100% |
596
4.62 IPS |
|
Depth Estimation (I8)
|
95% |
1377
10.7 IPS |
|
Style Transfer (F32)
|
100% |
955
1.26 IPS |
|
Style Transfer (F16)
|
100% |
959
1.26 IPS |
|
Style Transfer (I8)
|
98% |
2892
3.80 IPS |
|
Image Super-Resolution (F32)
|
100% |
344
12.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
347
12.4 IPS |
|
Image Super-Resolution (I8)
|
98% |
1363
48.7 IPS |
|
Text Classification (F32)
|
100% |
281
404.4 IPS |
|
Text Classification (F16)
|
100% |
313
450.0 IPS |
|
Text Classification (I8)
|
92% |
263
377.9 IPS |
|
Machine Translation (F32)
|
100% |
641
11.8 IPS |
|
Machine Translation (F16)
|
100% |
664
12.2 IPS |
|
Machine Translation (I8)
|
64% |
348
6.40 IPS |