Upload Date | September 17 2024 03:11 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 15 Pro Max |
Model ID | iPhone16,2 |
Motherboard | D84AP |
CPU Information | |
---|---|
Name | Apple A17 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1704
316.8 IPS |
|
Image Classification (HP)
|
100% |
10771
2.00 KIPS |
|
Image Classification (Q)
|
97% |
16235
3.03 KIPS |
|
Image Segmentation (SP)
|
100% |
1605
26.0 IPS |
|
Image Segmentation (HP)
|
100% |
12848
208.3 IPS |
|
Image Segmentation (Q)
|
99% |
15958
258.7 IPS |
|
Pose Estimation (SP)
|
100% |
7720
9.01 IPS |
|
Pose Estimation (HP)
|
100% |
104052
121.4 IPS |
|
Pose Estimation (Q)
|
95% |
204609
239.8 IPS |
|
Object Detection (SP)
|
100% |
1763
139.8 IPS |
|
Object Detection (HP)
|
100% |
13887
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19293
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3154
37.5 IPS |
|
Face Detection (HP)
|
100% |
33412
397.0 IPS |
|
Face Detection (Q)
|
100% |
49510
588.3 IPS |
|
Depth Estimation (SP)
|
100% |
6929
53.4 IPS |
|
Depth Estimation (HP)
|
99% |
78506
604.8 IPS |
|
Depth Estimation (Q)
|
85% |
128988
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
20333
26.1 IPS |
|
Style Transfer (HP)
|
100% |
201941
259.6 IPS |
|
Style Transfer (Q)
|
96% |
250204
322.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4726
174.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
34133
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
58238
2.15 KIPS |
|
Text Classification (SP)
|
100% |
3203
4.28 KIPS |
|
Text Classification (HP)
|
100% |
3325
4.44 KIPS |
|
Text Classification (Q)
|
93% |
3383
4.54 KIPS |
|
Machine Translation (SP)
|
100% |
2942
50.7 IPS |
|
Machine Translation (HP)
|
100% |
6008
103.5 IPS |
|
Machine Translation (Q)
|
98% |
7163
123.8 IPS |