Upload Date | August 17 2024 06:07 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | LENOVO TB350FU |
Model ID | LENOVO TB350FU |
Motherboard | tulip_row_wifi |
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 | 3.73 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
199
37.2 IPS |
|
Image Classification (F16)
|
100% |
202
37.7 IPS |
|
Image Classification (I8)
|
97% |
347
65.0 IPS |
|
Image Segmentation (F32)
|
100% |
301
5.03 IPS |
|
Image Segmentation (F16)
|
100% |
308
5.14 IPS |
|
Image Segmentation (I8)
|
98% |
420
7.02 IPS |
|
Pose Estimation (F32)
|
100% |
417
0.50 IPS |
|
Pose Estimation (F16)
|
100% |
404
0.49 IPS |
|
Pose Estimation (I8)
|
100% |
1918
2.32 IPS |
|
Object Detection (F32)
|
100% |
235
17.5 IPS |
|
Object Detection (F16)
|
100% |
234
17.4 IPS |
|
Object Detection (I8)
|
61% |
422
31.5 IPS |
|
Face Detection (F32)
|
100% |
461
5.48 IPS |
|
Face Detection (F16)
|
100% |
457
5.43 IPS |
|
Face Detection (I8)
|
86% |
907
10.8 IPS |
|
Depth Estimation (F32)
|
100% |
440
3.41 IPS |
|
Depth Estimation (F16)
|
100% |
442
3.43 IPS |
|
Depth Estimation (I8)
|
95% |
945
7.33 IPS |
|
Style Transfer (F32)
|
100% |
672
0.88 IPS |
|
Style Transfer (F16)
|
100% |
675
0.89 IPS |
|
Style Transfer (I8)
|
98% |
2053
2.70 IPS |
|
Image Super-Resolution (F32)
|
100% |
261
9.34 IPS |
|
Image Super-Resolution (F16)
|
100% |
257
9.18 IPS |
|
Image Super-Resolution (I8)
|
98% |
751
26.8 IPS |
|
Text Classification (F32)
|
100% |
250
359.5 IPS |
|
Text Classification (F16)
|
100% |
248
357.0 IPS |
|
Text Classification (I8)
|
92% |
196
281.5 IPS |
|
Machine Translation (F32)
|
100% |
493
9.07 IPS |
|
Machine Translation (F16)
|
100% |
493
9.06 IPS |
|
Machine Translation (I8)
|
64% |
264
4.86 IPS |