TECNO TECNO KI5k
Geekbench ML Score
239
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | January 12 2024 08:57 AM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | TECNO TECNO KI5k |
| Model ID | TECNO TECNO KI5k |
| Motherboard | TECNO-KI5k |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM Unisoc |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
| Base Frequency | 1.61 GHz |
| Cluster 1 | 8 Cores @ 1.61 GHz |
| Memory Information | |
|---|---|
| Size | 3.68 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
101
18.9 IPS |
|
|
Image Classification (F16)
|
100% |
100
18.8 IPS |
|
|
Image Classification (I8)
|
97% |
186
34.7 IPS |
|
|
Image Segmentation (F32)
|
100% |
172
2.87 IPS |
|
|
Image Segmentation (F16)
|
100% |
175
2.92 IPS |
|
|
Image Segmentation (I8)
|
98% |
232
3.88 IPS |
|
|
Pose Estimation (F32)
|
100% |
236
0.29 IPS |
|
|
Pose Estimation (F16)
|
100% |
243
0.29 IPS |
|
|
Pose Estimation (I8)
|
100% |
1170
1.42 IPS |
|
|
Object Detection (F32)
|
100% |
125
9.36 IPS |
|
|
Object Detection (F16)
|
100% |
119
8.88 IPS |
|
|
Object Detection (I8)
|
61% |
233
17.4 IPS |
|
|
Face Detection (F32)
|
100% |
265
3.15 IPS |
|
|
Face Detection (F16)
|
100% |
263
3.13 IPS |
|
|
Face Detection (I8)
|
86% |
577
6.86 IPS |
|
|
Depth Estimation (F32)
|
100% |
258
2.00 IPS |
|
|
Depth Estimation (F16)
|
100% |
264
2.05 IPS |
|
|
Depth Estimation (I8)
|
95% |
558
4.32 IPS |
|
|
Style Transfer (F32)
|
100% |
422
0.56 IPS |
|
|
Style Transfer (F16)
|
100% |
427
0.56 IPS |
|
|
Style Transfer (I8)
|
98% |
1230
1.62 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
150
5.36 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
160
5.70 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
482
17.2 IPS |
|
|
Text Classification (F32)
|
100% |
137
197.0 IPS |
|
|
Text Classification (F16)
|
100% |
136
195.8 IPS |
|
|
Text Classification (I8)
|
92% |
121
174.1 IPS |
|
|
Machine Translation (F32)
|
100% |
253
4.65 IPS |
|
|
Machine Translation (F16)
|
100% |
247
4.55 IPS |
|
|
Machine Translation (I8)
|
64% |
144
2.64 IPS |
