User | JoshuaChung |
Upload Date | September 23 2024 05:57 AM |
Views | 8 |
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 | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1932
359.3 IPS |
|
Image Classification (HP)
|
100% |
15432
2.87 KIPS |
|
Image Classification (Q)
|
97% |
20903
3.90 KIPS |
|
Image Segmentation (SP)
|
100% |
1843
29.9 IPS |
|
Image Segmentation (HP)
|
100% |
14642
237.4 IPS |
|
Image Segmentation (Q)
|
99% |
18255
295.9 IPS |
|
Pose Estimation (SP)
|
100% |
7531
8.79 IPS |
|
Pose Estimation (HP)
|
100% |
138676
161.8 IPS |
|
Pose Estimation (Q)
|
95% |
288611
338.3 IPS |
|
Object Detection (SP)
|
100% |
1944
154.2 IPS |
|
Object Detection (HP)
|
100% |
16169
1.28 KIPS |
|
Object Detection (Q)
|
91% |
22922
1.83 KIPS |
|
Face Detection (SP)
|
100% |
3207
38.1 IPS |
|
Face Detection (HP)
|
100% |
40919
486.2 IPS |
|
Face Detection (Q)
|
100% |
54792
651.0 IPS |
|
Depth Estimation (SP)
|
100% |
6938
53.5 IPS |
|
Depth Estimation (HP)
|
99% |
94535
728.3 IPS |
|
Depth Estimation (Q)
|
85% |
160107
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
20756
26.7 IPS |
|
Style Transfer (HP)
|
100% |
245062
315.0 IPS |
|
Style Transfer (Q)
|
96% |
301896
389.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
5062
186.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
50822
1.88 KIPS |
|
Image Super-Resolution (Q)
|
99% |
86665
3.20 KIPS |
|
Text Classification (SP)
|
100% |
3421
4.57 KIPS |
|
Text Classification (HP)
|
100% |
4712
6.29 KIPS |
|
Text Classification (Q)
|
93% |
4864
6.53 KIPS |
|
Machine Translation (SP)
|
100% |
3697
63.7 IPS |
|
Machine Translation (HP)
|
100% |
9615
165.6 IPS |
|
Machine Translation (Q)
|
98% |
11356
196.2 IPS |