Upload Date | October 20 2024 05:23 PM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | ARM SM7325 |
System Information | |
---|---|
Operating System | Android 12 |
Model | HUAWEI BAL-AL60 |
Model ID | HUAWEI BAL-AL60 |
Motherboard | BAL |
CPU Information | |
---|---|
Name | ARM SM7325 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 7.18 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
126
23.4 IPS |
|
Image Classification (HP)
|
100% |
127
23.6 IPS |
|
Image Classification (Q)
|
99% |
7310
1.36 KIPS |
|
Image Segmentation (SP)
|
100% |
168
2.73 IPS |
|
Image Segmentation (HP)
|
100% |
170
2.75 IPS |
|
Image Segmentation (Q)
|
98% |
6763
110.0 IPS |
|
Pose Estimation (SP)
|
100% |
228
0.27 IPS |
|
Pose Estimation (HP)
|
100% |
226
0.26 IPS |
|
Pose Estimation (Q)
|
94% |
44784
52.5 IPS |
|
Object Detection (SP)
|
100% |
125
9.92 IPS |
|
Object Detection (HP)
|
100% |
126
9.96 IPS |
|
Object Detection (Q)
|
88% |
3439
275.5 IPS |
|
Face Detection (SP)
|
100% |
318
3.77 IPS |
|
Face Detection (HP)
|
100% |
320
3.80 IPS |
|
Face Detection (Q)
|
97% |
20466
244.0 IPS |
|
Depth Estimation (SP)
|
100% |
278
2.14 IPS |
|
Depth Estimation (HP)
|
99% |
280
2.16 IPS |
|
Depth Estimation (Q)
|
64% |
20416
188.0 IPS |
|
Style Transfer (SP)
|
100% |
480
0.62 IPS |
|
Style Transfer (HP)
|
100% |
469
0.60 IPS |
|
Style Transfer (Q)
|
98% |
80276
103.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
133
4.93 IPS |
|
Image Super-Resolution (HP)
|
100% |
134
4.95 IPS |
|
Image Super-Resolution (Q)
|
97% |
20264
750.9 IPS |
|
Text Classification (SP)
|
100% |
189
251.7 IPS |
|
Text Classification (HP)
|
100% |
189
252.3 IPS |
|
Text Classification (Q)
|
94% |
2654
3.56 KIPS |
|
Machine Translation (SP)
|
100% |
307
5.29 IPS |
|
Machine Translation (HP)
|
100% |
307
5.29 IPS |
|
Machine Translation (Q)
|
37% |
101
10.2 IPS |