User | Katyusha |
Upload Date | January 02 2025 05:28 AM |
Views | 11 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ZHAOXIN KaiXian KX-7000 |
System Information | |
---|---|
Operating System | AOSC OS (12.0.1) |
Model | Shanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB |
Motherboard | Shanghai Zhaoxin Semiconductor Co., Ltd. JZ7KMA01 |
CPU Information | |
---|---|
Name | ZHAOXIN KaiXian KX-7000 |
Topology | 1 Processor, 8 Cores |
Identifier | CentaurHauls Family 7 Model 11 Stepping 1 |
Base Frequency | 3.73 GHz |
Cluster 1 | 0 Cores |
Memory Information | |
---|---|
Size | 31.13 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
612
113.9 IPS |
|
Image Classification (HP)
|
100% |
612
113.8 IPS |
|
Image Classification (Q)
|
99% |
460
85.7 IPS |
|
Image Segmentation (SP)
|
100% |
781
12.7 IPS |
|
Image Segmentation (HP)
|
100% |
783
12.7 IPS |
|
Image Segmentation (Q)
|
98% |
466
7.58 IPS |
|
Pose Estimation (SP)
|
100% |
870
1.01 IPS |
|
Pose Estimation (HP)
|
100% |
868
1.01 IPS |
|
Pose Estimation (Q)
|
96% |
1462
1.71 IPS |
|
Object Detection (SP)
|
100% |
536
42.5 IPS |
|
Object Detection (HP)
|
100% |
538
42.7 IPS |
|
Object Detection (Q)
|
85% |
424
34.1 IPS |
|
Face Detection (SP)
|
100% |
1252
14.9 IPS |
|
Face Detection (HP)
|
100% |
1252
14.9 IPS |
|
Face Detection (Q)
|
97% |
1047
12.5 IPS |
|
Depth Estimation (SP)
|
100% |
989
7.62 IPS |
|
Depth Estimation (HP)
|
99% |
988
7.62 IPS |
|
Depth Estimation (Q)
|
63% |
930
8.72 IPS |
|
Style Transfer (SP)
|
100% |
1335
1.72 IPS |
|
Style Transfer (HP)
|
100% |
1338
1.72 IPS |
|
Style Transfer (Q)
|
98% |
2558
3.30 IPS |
|
Image Super-Resolution (SP)
|
100% |
627
23.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
627
23.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
783
29.0 IPS |
|
Text Classification (SP)
|
100% |
674
899.8 IPS |
|
Text Classification (HP)
|
100% |
675
900.9 IPS |
|
Text Classification (Q)
|
92% |
288
387.4 IPS |
|
Machine Translation (SP)
|
100% |
852
14.7 IPS |
|
Machine Translation (HP)
|
100% |
859
14.8 IPS |
|
Machine Translation (Q)
|
58% |
264
6.19 IPS |