Upload Date | May 07 2024 01:44 AM |
Views | 7 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Solana Mobile Saga |
Model ID | Solana Mobile Saga |
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 | 10.88 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
350
65.6 IPS |
|
Image Classification (F16)
|
100% |
394
73.7 IPS |
|
Image Classification (I8)
|
97% |
666
124.7 IPS |
|
Image Segmentation (F32)
|
100% |
519
8.67 IPS |
|
Image Segmentation (F16)
|
100% |
513
8.57 IPS |
|
Image Segmentation (I8)
|
98% |
625
10.4 IPS |
|
Pose Estimation (F32)
|
100% |
888
1.07 IPS |
|
Pose Estimation (F16)
|
100% |
857
1.04 IPS |
|
Pose Estimation (I8)
|
100% |
3813
4.62 IPS |
|
Object Detection (F32)
|
100% |
386
28.8 IPS |
|
Object Detection (F16)
|
100% |
374
27.9 IPS |
|
Object Detection (I8)
|
61% |
829
61.9 IPS |
|
Face Detection (F32)
|
100% |
859
10.2 IPS |
|
Face Detection (F16)
|
100% |
860
10.2 IPS |
|
Face Detection (I8)
|
86% |
1624
19.3 IPS |
|
Depth Estimation (F32)
|
100% |
925
7.17 IPS |
|
Depth Estimation (F16)
|
100% |
905
7.02 IPS |
|
Depth Estimation (I8)
|
95% |
1853
14.4 IPS |
|
Style Transfer (F32)
|
100% |
1659
2.18 IPS |
|
Style Transfer (F16)
|
100% |
1627
2.14 IPS |
|
Style Transfer (I8)
|
98% |
3414
4.49 IPS |
|
Image Super-Resolution (F32)
|
100% |
548
19.6 IPS |
|
Image Super-Resolution (F16)
|
100% |
554
19.8 IPS |
|
Image Super-Resolution (I8)
|
98% |
1462
52.2 IPS |
|
Text Classification (F32)
|
100% |
434
623.1 IPS |
|
Text Classification (F16)
|
100% |
435
624.5 IPS |
|
Text Classification (I8)
|
92% |
336
483.4 IPS |
|
Machine Translation (F32)
|
100% |
826
15.2 IPS |
|
Machine Translation (F16)
|
100% |
798
14.7 IPS |
|
Machine Translation (I8)
|
64% |
390
7.18 IPS |