User | JoshuaChung |
Upload Date | September 20 2024 04:42 PM |
Views | 11 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | ARM |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone17,2 |
Model ID | iPhone17,2 |
Motherboard | D94AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.00 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1772
329.6 IPS |
|
Image Classification (HP)
|
100% |
16040
2.98 KIPS |
|
Image Classification (Q)
|
97% |
22694
4.24 KIPS |
|
Image Segmentation (SP)
|
100% |
1540
25.0 IPS |
|
Image Segmentation (HP)
|
100% |
14378
233.1 IPS |
|
Image Segmentation (Q)
|
99% |
17927
290.6 IPS |
|
Pose Estimation (SP)
|
100% |
6573
7.67 IPS |
|
Pose Estimation (HP)
|
100% |
133804
156.1 IPS |
|
Pose Estimation (Q)
|
95% |
259862
304.6 IPS |
|
Object Detection (SP)
|
100% |
1622
128.6 IPS |
|
Object Detection (HP)
|
100% |
15981
1.27 KIPS |
|
Object Detection (Q)
|
91% |
22497
1.80 KIPS |
|
Face Detection (SP)
|
100% |
2831
33.6 IPS |
|
Face Detection (HP)
|
100% |
38446
456.8 IPS |
|
Face Detection (Q)
|
100% |
54748
650.5 IPS |
|
Depth Estimation (SP)
|
100% |
5339
41.1 IPS |
|
Depth Estimation (HP)
|
99% |
92336
711.4 IPS |
|
Depth Estimation (Q)
|
85% |
150815
1.18 KIPS |
|
Style Transfer (SP)
|
100% |
16450
21.1 IPS |
|
Style Transfer (HP)
|
100% |
218417
280.8 IPS |
|
Style Transfer (Q)
|
96% |
302796
390.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
3433
126.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
44765
1.65 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85878
3.17 KIPS |
|
Text Classification (SP)
|
100% |
3004
4.01 KIPS |
|
Text Classification (HP)
|
100% |
4893
6.53 KIPS |
|
Text Classification (Q)
|
93% |
4569
6.13 KIPS |
|
Machine Translation (SP)
|
100% |
3337
57.5 IPS |
|
Machine Translation (HP)
|
100% |
8809
151.7 IPS |
|
Machine Translation (Q)
|
98% |
10470
180.9 IPS |