Upload Date | August 16 2024 09:47 PM |
Views | 2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy A73 |
Model ID | samsung SM-A736B |
Motherboard | lahaina |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 7.16 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
198
37.1 IPS |
|
Image Classification (F16)
|
100% |
274
51.2 IPS |
|
Image Classification (I8)
|
97% |
257
48.1 IPS |
|
Image Segmentation (F32)
|
100% |
326
5.45 IPS |
|
Image Segmentation (F16)
|
100% |
415
6.94 IPS |
|
Image Segmentation (I8)
|
98% |
408
6.82 IPS |
|
Pose Estimation (F32)
|
100% |
312
0.38 IPS |
|
Pose Estimation (F16)
|
100% |
224
0.27 IPS |
|
Pose Estimation (I8)
|
100% |
220
0.27 IPS |
|
Object Detection (F32)
|
100% |
160
12.0 IPS |
|
Object Detection (F16)
|
100% |
193
14.4 IPS |
|
Object Detection (I8)
|
62% |
187
14.0 IPS |
|
Face Detection (F32)
|
100% |
676
8.04 IPS |
|
Face Detection (F16)
|
97% |
1001
11.9 IPS |
|
Face Detection (I8)
|
87% |
936
11.1 IPS |
|
Depth Estimation (F32)
|
100% |
494
3.83 IPS |
|
Depth Estimation (F16)
|
100% |
763
5.92 IPS |
|
Depth Estimation (I8)
|
95% |
747
5.80 IPS |
|
Style Transfer (F32)
|
100% |
959
1.26 IPS |
|
Style Transfer (F16)
|
100% |
1603
2.11 IPS |
|
Style Transfer (I8)
|
98% |
1595
2.10 IPS |
|
Image Super-Resolution (F32)
|
100% |
219
7.84 IPS |
|
Image Super-Resolution (F16)
|
100% |
401
14.3 IPS |
|
Image Super-Resolution (I8)
|
98% |
366
13.1 IPS |
|
Text Classification (F32)
|
100% |
167
240.6 IPS |
|
Text Classification (F16)
|
100% |
168
241.2 IPS |
|
Text Classification (I8)
|
92% |
324
465.1 IPS |
|
Machine Translation (F32)
|
100% |
301
5.53 IPS |
|
Machine Translation (F16)
|
100% |
300
5.52 IPS |
|
Machine Translation (I8)
|
64% |
391
7.20 IPS |