| User | Beamish |
| Upload Date | November 21 2025 08:57 AM |
| Views | 5 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | Qualcomm Snapdragon 8+ Gen 1 |
| System Information | |
|---|---|
| Operating System | Android 16 |
| Model | Samsung Galaxy Z Flip4 |
| Model ID | samsung SM-F721B |
| Motherboard | taro |
| Governor | walt |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
| Base Frequency | 2.02 GHz |
| Cluster 1 | 4 Cores @ 2.02 GHz |
| Cluster 2 | 3 Cores @ 2.75 GHz |
| Cluster 3 | 1 Core @ 3.19 GHz |
| Memory Information | |
|---|---|
| Size | 7.10 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1023
190.3 IPS |
|
|
Image Classification (HP)
|
100% |
1477
274.6 IPS |
|
|
Image Classification (Q)
|
99% |
1392
259.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
1821
29.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
3007
48.8 IPS |
|
|
Image Segmentation (Q)
|
98% |
2378
38.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
6670
7.78 IPS |
|
|
Pose Estimation (HP)
|
99% |
12444
14.5 IPS |
|
|
Pose Estimation (Q)
|
97% |
12292
14.4 IPS |
|
|
Object Detection (SP)
|
100% |
767
60.8 IPS |
|
|
Object Detection (HP)
|
99% |
1268
100.6 IPS |
|
|
Object Detection (Q)
|
85% |
1065
85.7 IPS |
|
|
Face Detection (SP)
|
100% |
2511
29.8 IPS |
|
|
Face Detection (HP)
|
100% |
5626
66.8 IPS |
|
|
Face Detection (Q)
|
97% |
3930
46.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
3084
23.8 IPS |
|
|
Depth Estimation (HP)
|
98% |
5239
40.5 IPS |
|
|
Depth Estimation (Q)
|
65% |
4955
44.5 IPS |
|
|
Style Transfer (SP)
|
100% |
7490
9.63 IPS |
|
|
Style Transfer (HP)
|
100% |
15044
19.3 IPS |
|
|
Style Transfer (Q)
|
98% |
14568
18.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1531
56.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3201
118.2 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
3004
111.3 IPS |
|
|
Text Classification (SP)
|
35% |
48
464.2 IPS |
|
|
Text Classification (HP)
|
35% |
67
612.9 IPS |
|
|
Text Classification (Q)
|
35% |
64
581.5 IPS |
|
|
Machine Translation (SP)
|
100% |
545
9.39 IPS |
|
|
Machine Translation (HP)
|
97% |
608
10.5 IPS |
|
|
Machine Translation (Q)
|
64% |
482
9.91 IPS |