User | evodomgeek |
Upload Date | February 23 2025 02:38 PM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A14 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2.1 |
Model | iPhone 12 Pro |
Model ID | iPhone13,3 |
Motherboard | D53pAP |
CPU Information | |
---|---|
Name | Apple A14 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 2.99 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.58 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1102
204.9 IPS |
|
Image Classification (HP)
|
100% |
4681
870.5 IPS |
|
Image Classification (Q)
|
96% |
5178
966.9 IPS |
|
Image Segmentation (SP)
|
100% |
1069
17.3 IPS |
|
Image Segmentation (HP)
|
100% |
8677
140.7 IPS |
|
Image Segmentation (Q)
|
99% |
8946
145.0 IPS |
|
Pose Estimation (SP)
|
100% |
4332
5.06 IPS |
|
Pose Estimation (HP)
|
100% |
60788
70.9 IPS |
|
Pose Estimation (Q)
|
95% |
60866
71.3 IPS |
|
Object Detection (SP)
|
100% |
1212
96.1 IPS |
|
Object Detection (HP)
|
99% |
5978
475.6 IPS |
|
Object Detection (Q)
|
91% |
5351
427.6 IPS |
|
Face Detection (SP)
|
100% |
2418
28.7 IPS |
|
Face Detection (HP)
|
100% |
15317
182.0 IPS |
|
Face Detection (Q)
|
100% |
12663
150.5 IPS |
|
Depth Estimation (SP)
|
100% |
4068
31.3 IPS |
|
Depth Estimation (HP)
|
99% |
38722
298.3 IPS |
|
Depth Estimation (Q)
|
85% |
39362
307.6 IPS |
|
Style Transfer (SP)
|
100% |
10942
14.1 IPS |
|
Style Transfer (HP)
|
100% |
106474
136.9 IPS |
|
Style Transfer (Q)
|
96% |
99398
128.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
2255
83.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
21147
780.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
19887
734.3 IPS |
|
Text Classification (SP)
|
100% |
2095
2.80 KIPS |
|
Text Classification (HP)
|
100% |
2233
2.98 KIPS |
|
Text Classification (Q)
|
93% |
2254
3.02 KIPS |
|
Machine Translation (SP)
|
100% |
2207
38.0 IPS |
|
Machine Translation (HP)
|
100% |
3493
60.2 IPS |
|
Machine Translation (Q)
|
98% |
4477
77.4 IPS |