Upload Date | June 29 2024 04:36 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | HEADWOLF F5 |
Model ID | HEADWOLF F5 |
Motherboard | HEADWOLF |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.20 GHz |
Memory Information | |
---|---|
Size | 7.54 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
192
35.9 IPS |
|
Image Classification (F16)
|
100% |
187
35.0 IPS |
|
Image Classification (I8)
|
97% |
329
61.5 IPS |
|
Image Segmentation (F32)
|
100% |
294
4.91 IPS |
|
Image Segmentation (F16)
|
100% |
294
4.91 IPS |
|
Image Segmentation (I8)
|
98% |
415
6.93 IPS |
|
Pose Estimation (F32)
|
100% |
395
0.48 IPS |
|
Pose Estimation (F16)
|
100% |
405
0.49 IPS |
|
Pose Estimation (I8)
|
100% |
1789
2.17 IPS |
|
Object Detection (F32)
|
100% |
226
16.9 IPS |
|
Object Detection (F16)
|
100% |
222
16.6 IPS |
|
Object Detection (I8)
|
61% |
394
29.4 IPS |
|
Face Detection (F32)
|
100% |
438
5.21 IPS |
|
Face Detection (F16)
|
100% |
436
5.18 IPS |
|
Face Detection (I8)
|
86% |
893
10.6 IPS |
|
Depth Estimation (F32)
|
100% |
429
3.32 IPS |
|
Depth Estimation (F16)
|
100% |
418
3.24 IPS |
|
Depth Estimation (I8)
|
95% |
920
7.13 IPS |
|
Style Transfer (F32)
|
100% |
661
0.87 IPS |
|
Style Transfer (F16)
|
100% |
661
0.87 IPS |
|
Style Transfer (I8)
|
98% |
2039
2.68 IPS |
|
Image Super-Resolution (F32)
|
100% |
244
8.70 IPS |
|
Image Super-Resolution (F16)
|
100% |
244
8.72 IPS |
|
Image Super-Resolution (I8)
|
98% |
675
24.1 IPS |
|
Text Classification (F32)
|
100% |
226
324.8 IPS |
|
Text Classification (F16)
|
100% |
236
338.8 IPS |
|
Text Classification (I8)
|
92% |
183
263.7 IPS |
|
Machine Translation (F32)
|
100% |
457
8.41 IPS |
|
Machine Translation (F16)
|
100% |
456
8.38 IPS |
|
Machine Translation (I8)
|
64% |
258
4.74 IPS |