Upload Date | June 17 2025 09:30 AM |
Views | 5 |
System Information | |
---|---|
Operating System | Android 12 |
Model | DTEN Bar_DCR200 |
Model ID | DTEN Bar_DCR200 |
Motherboard | R1-003 |
Governor | performance |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.35 GHz |
Memory Information | |
---|---|
Size | 15.33 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
42
7.89 IPS |
|
Image Classification (F16)
|
100% |
42
7.88 IPS |
|
Image Classification (I8)
|
97% |
46
8.67 IPS |
|
Image Segmentation (F32)
|
100% |
172
2.87 IPS |
|
Image Segmentation (F16)
|
100% |
170
2.85 IPS |
|
Image Segmentation (I8)
|
98% |
190
3.18 IPS |
|
Pose Estimation (F32)
|
100% |
475
0.58 IPS |
|
Pose Estimation (F16)
|
100% |
487
0.59 IPS |
|
Pose Estimation (I8)
|
100% |
1431
1.73 IPS |
|
Object Detection (F32)
|
100% |
65
4.84 IPS |
|
Object Detection (F16)
|
100% |
64
4.77 IPS |
|
Object Detection (I8)
|
61% |
76
5.71 IPS |
|
Face Detection (F32)
|
100% |
214
2.55 IPS |
|
Face Detection (F16)
|
100% |
216
2.57 IPS |
|
Face Detection (I8)
|
86% |
260
3.09 IPS |
|
Depth Estimation (F32)
|
100% |
207
1.61 IPS |
|
Depth Estimation (F16)
|
100% |
211
1.64 IPS |
|
Depth Estimation (I8)
|
95% |
268
2.08 IPS |
|
Style Transfer (F32)
|
100% |
784
1.03 IPS |
|
Style Transfer (F16)
|
100% |
791
1.04 IPS |
|
Style Transfer (I8)
|
98% |
2110
2.78 IPS |
|
Image Super-Resolution (F32)
|
100% |
119
4.25 IPS |
|
Image Super-Resolution (F16)
|
100% |
121
4.33 IPS |
|
Image Super-Resolution (I8)
|
98% |
172
6.14 IPS |
|
Text Classification (F32)
|
100% |
8
11.2 IPS |
|
Text Classification (F16)
|
100% |
8
11.2 IPS |
|
Text Classification (I8)
|
92% |
9
12.6 IPS |
|
Machine Translation (F32)
|
100% |
21
0.39 IPS |
|
Machine Translation (F16)
|
100% |
21
0.39 IPS |
|
Machine Translation (I8)
|
64% |
22
0.40 IPS |