Upload Date | September 18 2024 08:33 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Air (2022) |
Model ID | Mac14,2 |
Motherboard | Mac14,2 |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M2 |
Base Frequency | 3.48 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1129
209.9 IPS |
|
Image Classification (HP)
|
100% |
7486
1.39 KIPS |
|
Image Classification (Q)
|
96% |
7618
1.42 KIPS |
|
Image Segmentation (SP)
|
100% |
722
11.7 IPS |
|
Image Segmentation (HP)
|
100% |
5056
82.0 IPS |
|
Image Segmentation (Q)
|
99% |
8083
131.0 IPS |
|
Pose Estimation (SP)
|
100% |
5964
6.96 IPS |
|
Pose Estimation (HP)
|
100% |
88537
103.3 IPS |
|
Pose Estimation (Q)
|
95% |
87258
102.3 IPS |
|
Object Detection (SP)
|
100% |
1248
99.0 IPS |
|
Object Detection (HP)
|
99% |
8525
678.1 IPS |
|
Object Detection (Q)
|
93% |
8937
713.1 IPS |
|
Face Detection (SP)
|
100% |
2116
25.1 IPS |
|
Face Detection (HP)
|
100% |
11147
132.5 IPS |
|
Face Detection (Q)
|
100% |
12894
153.2 IPS |
|
Depth Estimation (SP)
|
100% |
3694
28.5 IPS |
|
Depth Estimation (HP)
|
99% |
50629
390.1 IPS |
|
Depth Estimation (Q)
|
85% |
60157
470.1 IPS |
|
Style Transfer (SP)
|
100% |
10643
13.7 IPS |
|
Style Transfer (HP)
|
100% |
138091
177.5 IPS |
|
Style Transfer (Q)
|
95% |
125394
161.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
2864
105.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
19752
729.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
25576
944.4 IPS |
|
Text Classification (SP)
|
100% |
896
1.20 KIPS |
|
Text Classification (HP)
|
100% |
685
914.4 IPS |
|
Text Classification (Q)
|
93% |
685
919.5 IPS |
|
Machine Translation (SP)
|
100% |
1619
27.9 IPS |
|
Machine Translation (HP)
|
100% |
2413
41.6 IPS |
|
Machine Translation (Q)
|
98% |
2472
42.7 IPS |