User | bthomas |
Upload Date | July 05 2024 08:16 PM |
Views | 2 |
System Information | |
---|---|
Operating System | iOS 17.4.1 |
Model | iPhone 15 Pro |
Model ID | iPhone16,1 |
Motherboard | D83AP |
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 |
L1 Instruction Cache | 128 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 4.00 MB x 1 |
Memory Information | |
---|---|
Size | 7.47 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1537
287.6 IPS |
|
Image Classification (F16)
|
100% |
1430
267.5 IPS |
|
Image Classification (I8)
|
99% |
2047
383.1 IPS |
|
Image Segmentation (F32)
|
100% |
1422
23.7 IPS |
|
Image Segmentation (F16)
|
100% |
1586
26.5 IPS |
|
Image Segmentation (I8)
|
100% |
1604
26.8 IPS |
|
Pose Estimation (F32)
|
100% |
14941
18.1 IPS |
|
Pose Estimation (F16)
|
100% |
15920
19.3 IPS |
|
Pose Estimation (I8)
|
100% |
15687
19.0 IPS |
|
Object Detection (F32)
|
100% |
1521
113.6 IPS |
|
Object Detection (F16)
|
100% |
1573
117.4 IPS |
|
Object Detection (I8)
|
97% |
1599
119.4 IPS |
|
Face Detection (F32)
|
100% |
6401
76.1 IPS |
|
Face Detection (F16)
|
98% |
8162
97.0 IPS |
|
Face Detection (I8)
|
97% |
8689
103.3 IPS |
|
Depth Estimation (F32)
|
100% |
12569
97.5 IPS |
|
Depth Estimation (F16)
|
100% |
14049
109.0 IPS |
|
Depth Estimation (I8)
|
37% |
12879
99.9 IPS |
|
Style Transfer (F32)
|
100% |
29867
39.3 IPS |
|
Style Transfer (F16)
|
100% |
36864
48.5 IPS |
|
Style Transfer (I8)
|
100% |
31444
41.4 IPS |
|
Image Super-Resolution (F32)
|
100% |
7306
260.9 IPS |
|
Image Super-Resolution (F16)
|
100% |
4597
164.2 IPS |
|
Image Super-Resolution (I8)
|
100% |
7723
275.8 IPS |
|
Text Classification (F32)
|
100% |
477
685.6 IPS |
|
Text Classification (F16)
|
100% |
510
733.4 IPS |
|
Text Classification (I8)
|
96% |
319
458.3 IPS |
|
Machine Translation (F32)
|
100% |
758
13.9 IPS |
|
Machine Translation (F16)
|
100% |
811
14.9 IPS |
|
Machine Translation (I8)
|
99% |
703
12.9 IPS |