| Upload Date | December 09 2022 05:50 AM |
| Views | 5 |
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | samsung SM-T875N |
| Model ID | samsung SM-T875N |
| 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 @ 3.09 GHz |
| Memory Information | |
|---|---|
| Size | 5.45 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
446
47.8 IPS |
|
|
Image Classification (F16)
|
100% |
262
28.0 IPS |
|
|
Image Classification (I8)
|
81% |
188
20.1 IPS |
|
|
Image Segmentation (F32)
|
100% |
612
3.78 IPS |
|
|
Image Segmentation (F16)
|
100% |
575
3.55 IPS |
|
|
Image Segmentation (I8)
|
89% |
870
5.38 IPS |
|
|
Pose Estimation (F32)
|
100% |
264
1.07 IPS |
|
|
Pose Estimation (F16)
|
100% |
255
1.03 IPS |
|
|
Pose Estimation (I8)
|
80% |
233
0.94 IPS |
|
|
Object Detection (F32)
|
100% |
336
11.8 IPS |
|
|
Object Detection (F16)
|
100% |
352
12.3 IPS |
|
|
Object Detection (I8)
|
52% |
315
11.1 IPS |
|
|
Face Detection (F32)
|
100% |
633
7.27 IPS |
|
|
Face Detection (F16)
|
100% |
551
6.33 IPS |
|
|
Face Detection (I8)
|
75% |
544
6.25 IPS |
|
|
Text Classification (F32)
|
100% |
345
136.4 IPS |
|
|
Text Classification (F16)
|
100% |
344
136.2 IPS |
|
|
Machine Translation (F32)
|
100% |
587
90.5 IPS |
|
|
Machine Translation (F16)
|
100% |
571
88.0 IPS |
Compare
Set Baseline