User | korbs |
Upload Date | July 25 2024 09:22 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Samsung Galaxy Tab S6 |
Model ID | samsung SM-T860 |
Motherboard | msmnile |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 13 part 2052 revision 14 |
Base Frequency | 1.78 GHz |
Cluster 1 | 4 Cores @ 1.79 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 5.32 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
203
37.9 IPS |
|
Image Classification (F16)
|
100% |
342
64.0 IPS |
|
Image Classification (I8)
|
97% |
354
66.2 IPS |
|
Image Segmentation (F32)
|
100% |
270
4.52 IPS |
|
Image Segmentation (F16)
|
100% |
509
8.49 IPS |
|
Image Segmentation (I8)
|
98% |
480
8.02 IPS |
|
Pose Estimation (F32)
|
100% |
418
0.51 IPS |
|
Pose Estimation (F16)
|
100% |
311
0.38 IPS |
|
Pose Estimation (I8)
|
100% |
313
0.38 IPS |
|
Object Detection (F32)
|
100% |
182
13.6 IPS |
|
Object Detection (F16)
|
100% |
236
17.6 IPS |
|
Object Detection (I8)
|
62% |
224
16.7 IPS |
|
Face Detection (F32)
|
100% |
510
6.06 IPS |
|
Face Detection (F16)
|
97% |
1064
12.6 IPS |
|
Face Detection (I8)
|
87% |
1149
13.7 IPS |
|
Depth Estimation (F32)
|
100% |
465
3.60 IPS |
|
Depth Estimation (F16)
|
100% |
904
7.01 IPS |
|
Depth Estimation (I8)
|
95% |
910
7.06 IPS |
|
Style Transfer (F32)
|
100% |
930
1.22 IPS |
|
Style Transfer (F16)
|
100% |
2312
3.04 IPS |
|
Style Transfer (I8)
|
98% |
2315
3.05 IPS |
|
Image Super-Resolution (F32)
|
100% |
239
8.52 IPS |
|
Image Super-Resolution (F16)
|
100% |
453
16.2 IPS |
|
Image Super-Resolution (I8)
|
98% |
448
16.0 IPS |
|
Text Classification (F32)
|
100% |
187
268.5 IPS |
|
Text Classification (F16)
|
100% |
186
267.2 IPS |
|
Text Classification (I8)
|
92% |
319
458.3 IPS |
|
Machine Translation (F32)
|
100% |
345
6.35 IPS |
|
Machine Translation (F16)
|
100% |
350
6.44 IPS |
|
Machine Translation (I8)
|
64% |
376
6.92 IPS |