User | edwardhchan |
Upload Date | October 31 2024 04:50 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
Model | Mac mini (2023) |
Model ID | Mac14,12 |
Motherboard | Mac14,12 |
CPU Information | |
---|---|
Name | Apple M2 Pro |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M2 Pro |
Base Frequency | 3.48 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1384
257.3 IPS |
|
Image Classification (HP)
|
100% |
13538
2.52 KIPS |
|
Image Classification (Q)
|
99% |
16024
2.99 KIPS |
|
Image Segmentation (SP)
|
100% |
1672
27.1 IPS |
|
Image Segmentation (HP)
|
100% |
15785
255.9 IPS |
|
Image Segmentation (Q)
|
100% |
15382
249.4 IPS |
|
Pose Estimation (SP)
|
100% |
12644
14.8 IPS |
|
Pose Estimation (HP)
|
100% |
103254
120.5 IPS |
|
Pose Estimation (Q)
|
94% |
97522
114.4 IPS |
|
Object Detection (SP)
|
100% |
1682
133.4 IPS |
|
Object Detection (HP)
|
99% |
14700
1.17 KIPS |
|
Object Detection (Q)
|
91% |
17996
1.44 KIPS |
|
Face Detection (SP)
|
100% |
3631
43.1 IPS |
|
Face Detection (HP)
|
100% |
23544
279.8 IPS |
|
Face Detection (Q)
|
100% |
36951
439.1 IPS |
|
Depth Estimation (SP)
|
100% |
6332
48.8 IPS |
|
Depth Estimation (HP)
|
99% |
74291
572.4 IPS |
|
Depth Estimation (Q)
|
97% |
82746
639.8 IPS |
|
Style Transfer (SP)
|
100% |
25362
32.6 IPS |
|
Style Transfer (HP)
|
100% |
156388
201.0 IPS |
|
Style Transfer (Q)
|
100% |
157620
202.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
5196
191.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
43138
1.59 KIPS |
|
Image Super-Resolution (Q)
|
98% |
51429
1.91 KIPS |
|
Text Classification (SP)
|
100% |
2323
3.10 KIPS |
|
Text Classification (HP)
|
100% |
3872
5.17 KIPS |
|
Text Classification (Q)
|
93% |
3975
5.33 KIPS |
|
Machine Translation (SP)
|
100% |
4237
73.0 IPS |
|
Machine Translation (HP)
|
100% |
5773
99.4 IPS |
|
Machine Translation (Q)
|
98% |
6337
109.5 IPS |