Upload Date | July 25 2024 10:35 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy Z Fold4 |
Model ID | samsung SM-F936B |
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 | 10.99 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
447
83.7 IPS |
|
Image Classification (F16)
|
100% |
722
135.2 IPS |
|
Image Classification (I8)
|
97% |
304
56.8 IPS |
|
Image Segmentation (F32)
|
100% |
744
12.4 IPS |
|
Image Segmentation (F16)
|
100% |
960
16.0 IPS |
|
Image Segmentation (I8)
|
98% |
890
14.9 IPS |
|
Pose Estimation (F32)
|
100% |
726
0.88 IPS |
|
Pose Estimation (F16)
|
100% |
1247
1.51 IPS |
|
Pose Estimation (I8)
|
100% |
1321
1.60 IPS |
|
Object Detection (F32)
|
100% |
337
25.2 IPS |
|
Object Detection (F16)
|
100% |
418
31.2 IPS |
|
Object Detection (I8)
|
62% |
367
27.4 IPS |
|
Face Detection (F32)
|
100% |
1611
19.2 IPS |
|
Face Detection (F16)
|
97% |
2095
24.9 IPS |
|
Face Detection (I8)
|
87% |
2129
25.3 IPS |
|
Depth Estimation (F32)
|
100% |
1174
9.10 IPS |
|
Depth Estimation (F16)
|
100% |
2677
20.8 IPS |
|
Depth Estimation (I8)
|
95% |
2586
20.1 IPS |
|
Style Transfer (F32)
|
100% |
2884
3.79 IPS |
|
Style Transfer (F16)
|
100% |
6502
8.55 IPS |
|
Style Transfer (I8)
|
98% |
5489
7.22 IPS |
|
Image Super-Resolution (F32)
|
100% |
396
14.1 IPS |
|
Image Super-Resolution (F16)
|
100% |
521
18.6 IPS |
|
Image Super-Resolution (I8)
|
98% |
515
18.4 IPS |
|
Text Classification (F32)
|
100% |
285
409.2 IPS |
|
Text Classification (F16)
|
100% |
285
410.0 IPS |
|
Text Classification (I8)
|
92% |
518
744.0 IPS |
|
Machine Translation (F32)
|
100% |
484
8.91 IPS |
|
Machine Translation (F16)
|
100% |
473
8.70 IPS |
|
Machine Translation (I8)
|
64% |
626
11.5 IPS |