User | morglor |
Upload Date | April 03 2024 02:42 AM |
Views | 3 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Google Pixel 6a |
Model ID | Google Pixel 6a |
Motherboard | bluejay |
Governor | sched_pixel |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.25 GHz |
Cluster 3 | 2 Cores @ 2.80 GHz |
Memory Information | |
---|---|
Size | 5.47 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
360
67.3 IPS |
|
Image Classification (F16)
|
100% |
350
65.5 IPS |
|
Image Classification (I8)
|
97% |
734
137.3 IPS |
|
Image Segmentation (F32)
|
100% |
431
7.19 IPS |
|
Image Segmentation (F16)
|
100% |
410
6.84 IPS |
|
Image Segmentation (I8)
|
98% |
662
11.1 IPS |
|
Pose Estimation (F32)
|
100% |
590
0.71 IPS |
|
Pose Estimation (F16)
|
100% |
623
0.75 IPS |
|
Pose Estimation (I8)
|
100% |
2451
2.97 IPS |
|
Object Detection (F32)
|
100% |
286
21.3 IPS |
|
Object Detection (F16)
|
100% |
279
20.8 IPS |
|
Object Detection (I8)
|
61% |
743
55.5 IPS |
|
Face Detection (F32)
|
100% |
619
7.36 IPS |
|
Face Detection (F16)
|
100% |
588
7.00 IPS |
|
Face Detection (I8)
|
86% |
1115
13.3 IPS |
|
Depth Estimation (F32)
|
100% |
427
3.31 IPS |
|
Depth Estimation (F16)
|
100% |
421
3.27 IPS |
|
Depth Estimation (I8)
|
95% |
940
7.29 IPS |
|
Style Transfer (F32)
|
100% |
813
1.07 IPS |
|
Style Transfer (F16)
|
100% |
742
0.98 IPS |
|
Style Transfer (I8)
|
98% |
1898
2.50 IPS |
|
Image Super-Resolution (F32)
|
100% |
338
12.1 IPS |
|
Image Super-Resolution (F16)
|
100% |
387
13.8 IPS |
|
Image Super-Resolution (I8)
|
98% |
1178
42.1 IPS |
|
Text Classification (F32)
|
100% |
281
403.5 IPS |
|
Text Classification (F16)
|
100% |
298
428.9 IPS |
|
Text Classification (I8)
|
92% |
275
395.9 IPS |
|
Machine Translation (F32)
|
100% |
618
11.4 IPS |
|
Machine Translation (F16)
|
100% |
516
9.49 IPS |
|
Machine Translation (I8)
|
64% |
274
5.04 IPS |