User | M91 |
Upload Date | July 27 2024 12:24 AM |
Views | 2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Google Pixel 8a |
Model ID | Google Pixel 8a |
Motherboard | akita |
Governor | sched_pixel |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 9 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
Base Frequency | 1.70 GHz |
Cluster 1 | 4 Cores @ 1.70 GHz |
Cluster 2 | 4 Cores @ 2.37 GHz |
Cluster 3 | 1 Core @ 2.91 GHz |
Memory Information | |
---|---|
Size | 7.42 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
358
67.0 IPS |
|
Image Classification (F16)
|
100% |
399
74.6 IPS |
|
Image Classification (I8)
|
97% |
326
61.0 IPS |
|
Image Segmentation (F32)
|
100% |
785
13.1 IPS |
|
Image Segmentation (F16)
|
100% |
877
14.6 IPS |
|
Image Segmentation (I8)
|
98% |
896
15.0 IPS |
|
Pose Estimation (F32)
|
100% |
466
0.56 IPS |
|
Pose Estimation (F16)
|
100% |
652
0.79 IPS |
|
Pose Estimation (I8)
|
100% |
647
0.78 IPS |
|
Object Detection (F32)
|
100% |
287
21.4 IPS |
|
Object Detection (F16)
|
100% |
335
25.0 IPS |
|
Object Detection (I8)
|
62% |
360
26.9 IPS |
|
Face Detection (F32)
|
100% |
1174
14.0 IPS |
|
Face Detection (F16)
|
98% |
1375
16.3 IPS |
|
Face Detection (I8)
|
86% |
1255
14.9 IPS |
|
Depth Estimation (F32)
|
100% |
938
7.27 IPS |
|
Depth Estimation (F16)
|
100% |
1133
8.79 IPS |
|
Depth Estimation (I8)
|
95% |
1131
8.77 IPS |
|
Style Transfer (F32)
|
100% |
2451
3.22 IPS |
|
Style Transfer (F16)
|
100% |
3227
4.25 IPS |
|
Style Transfer (I8)
|
98% |
3237
4.26 IPS |
|
Image Super-Resolution (F32)
|
100% |
539
19.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
646
23.1 IPS |
|
Image Super-Resolution (I8)
|
98% |
637
22.8 IPS |
|
Text Classification (F32)
|
100% |
359
515.7 IPS |
|
Text Classification (F16)
|
100% |
368
528.4 IPS |
|
Text Classification (I8)
|
92% |
556
798.4 IPS |
|
Machine Translation (F32)
|
100% |
542
9.98 IPS |
|
Machine Translation (F16)
|
100% |
523
9.62 IPS |
|
Machine Translation (I8)
|
64% |
505
9.29 IPS |