Upload Date | September 14 2024 04:35 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Qualcomm |
System Information | |
---|---|
Operating System | Android 14 |
Model | Motorola Moto X4 |
Model ID | Motorola Moto X4 |
Motherboard | SDM660 |
Governor | performance |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 10 part 2049 revision 4 |
Base Frequency | 2.21 GHz |
Cluster 1 | 4 Cores @ 1.84 GHz |
Cluster 2 | 4 Cores @ 2.21 GHz |
Memory Information | |
---|---|
Size | 2.67 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
0% |
0
787.1 IPS |
|
Image Classification (HP)
|
0% |
0
790.9 IPS |
|
Image Classification (Q)
|
0% |
0
1.28 KIPS |
|
Image Segmentation (SP)
|
73% |
3156
54.5 IPS |
|
Image Segmentation (HP)
|
73% |
3139
54.2 IPS |
|
Image Segmentation (Q)
|
73% |
8619
148.9 IPS |
|
Pose Estimation (SP)
|
0% |
0
202.1 IPS |
|
Pose Estimation (HP)
|
0% |
0
196.0 IPS |
|
Pose Estimation (Q)
|
0% |
0
552.8 IPS |
|
Object Detection (SP)
|
0% |
0
270.5 IPS |
|
Object Detection (HP)
|
0% |
0
271.0 IPS |
|
Object Detection (Q)
|
0% |
0
225.3 IPS |
|
Face Detection (SP)
|
0% |
0
87.3 IPS |
|
Face Detection (HP)
|
0% |
0
88.4 IPS |
|
Face Detection (Q)
|
0% |
0
158.0 IPS |
|
Depth Estimation (SP)
|
0% |
0
222.4 IPS |
|
Depth Estimation (HP)
|
0% |
0
225.1 IPS |
|
Depth Estimation (Q)
|
0% |
0
205.4 IPS |
|
Style Transfer (SP)
|
32% |
29264
367.1 IPS |
|
Style Transfer (HP)
|
32% |
29832
374.2 IPS |
|
Style Transfer (Q)
|
0% |
0
1.49 KIPS |
|
Image Super-Resolution (SP)
|
1% |
0
535.1 IPS |
|
Image Super-Resolution (HP)
|
1% |
0
532.8 IPS |
|
Image Super-Resolution (Q)
|
2% |
91
1.07 KIPS |
|
Text Classification (SP)
|
29% |
184
3.17 KIPS |
|
Text Classification (HP)
|
29% |
187
3.22 KIPS |
|
Text Classification (Q)
|
29% |
138
2.38 KIPS |
|
Machine Translation (SP)
|
0% |
0
1.82 IPS |
|
Machine Translation (HP)
|
0% |
0
1.84 IPS |
|
Machine Translation (Q)
|
0% |
0
1.57 IPS |