Upload Date | May 17 2022 12:22 PM |
Views | 4 |
System Information | |
---|---|
Operating System | Android 12 |
Model | samsung SM-A528B |
Model ID | samsung SM-A528B |
Motherboard | lahaina |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 7.16 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
432
46.3 IPS |
|
Image Classification (F16)
|
100% |
299
32.1 IPS |
|
Image Classification (I8)
|
81% |
202
21.6 IPS |
|
Image Segmentation (F32)
|
100% |
602
3.72 IPS |
|
Image Segmentation (F16)
|
100% |
609
3.76 IPS |
|
Image Segmentation (I8)
|
89% |
877
5.42 IPS |
|
Pose Estimation (F32)
|
100% |
265
1.07 IPS |
|
Pose Estimation (F16)
|
100% |
264
1.07 IPS |
|
Pose Estimation (I8)
|
80% |
240
0.97 IPS |
|
Object Detection (F32)
|
100% |
382
13.4 IPS |
|
Object Detection (F16)
|
100% |
384
13.5 IPS |
|
Object Detection (I8)
|
52% |
301
10.6 IPS |
|
Face Detection (F32)
|
100% |
528
6.07 IPS |
|
Face Detection (F16)
|
100% |
542
6.22 IPS |
|
Face Detection (I8)
|
75% |
516
5.93 IPS |
|
Text Classification (F32)
|
100% |
342
135.3 IPS |
|
Text Classification (F16)
|
100% |
344
136.2 IPS |
|
Machine Translation (F32)
|
100% |
478
73.7 IPS |
|
Machine Translation (F16)
|
100% |
479
73.8 IPS |