Google trogdor
Geekbench ML Score
237
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | December 08 2022 09:47 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | Google trogdor |
| Model ID | Google trogdor |
| Motherboard | lazor-arc-r |
| CPU Information | |
|---|---|
| Name | Qualcomm ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 81 architecture 8 variant 15 part 2052 revision 15 |
| Base Frequency | 0 MHz |
| Cluster 1 | 8 Cores @ 0.00 Hz |
| Memory Information | |
|---|---|
| Size | 2.67 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
114
12.2 IPS |
|
|
Image Classification (F16)
|
100% |
118
12.7 IPS |
|
|
Image Classification (I8)
|
81% |
248
26.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
350
2.16 IPS |
|
|
Image Segmentation (F16)
|
100% |
328
2.02 IPS |
|
|
Image Segmentation (I8)
|
89% |
613
3.79 IPS |
|
|
Pose Estimation (F32)
|
100% |
134
0.54 IPS |
|
|
Pose Estimation (F16)
|
100% |
134
0.54 IPS |
|
|
Pose Estimation (I8)
|
80% |
138
0.56 IPS |
|
|
Object Detection (F32)
|
100% |
162
5.69 IPS |
|
|
Object Detection (F16)
|
100% |
178
6.26 IPS |
|
|
Object Detection (I8)
|
52% |
309
10.8 IPS |
|
|
Face Detection (F32)
|
100% |
349
4.01 IPS |
|
|
Face Detection (F16)
|
100% |
348
4.00 IPS |
|
|
Face Detection (I8)
|
75% |
445
5.11 IPS |
|
|
Text Classification (F32)
|
100% |
367
145.2 IPS |
|
|
Text Classification (F16)
|
100% |
372
147.1 IPS |
|
|
Machine Translation (F32)
|
100% |
191
29.4 IPS |
|
|
Machine Translation (F16)
|
100% |
193
29.7 IPS |
