Upload Date | November 18 2024 08:45 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
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 | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
5196
966.4 IPS |
|
Image Classification (HP)
|
100% |
5274
980.8 IPS |
|
Image Classification (Q)
|
97% |
4490
837.8 IPS |
|
Image Segmentation (SP)
|
100% |
7196
116.7 IPS |
|
Image Segmentation (HP)
|
100% |
7378
119.6 IPS |
|
Image Segmentation (Q)
|
99% |
7126
115.5 IPS |
|
Pose Estimation (SP)
|
100% |
37080
43.3 IPS |
|
Pose Estimation (HP)
|
100% |
39378
45.9 IPS |
|
Pose Estimation (Q)
|
95% |
36652
43.0 IPS |
|
Object Detection (SP)
|
100% |
4734
375.5 IPS |
|
Object Detection (HP)
|
100% |
4933
391.3 IPS |
|
Object Detection (Q)
|
91% |
4139
330.7 IPS |
|
Face Detection (SP)
|
100% |
16609
197.3 IPS |
|
Face Detection (HP)
|
100% |
17509
208.0 IPS |
|
Face Detection (Q)
|
100% |
12521
148.8 IPS |
|
Depth Estimation (SP)
|
100% |
23893
184.1 IPS |
|
Depth Estimation (HP)
|
99% |
25259
194.6 IPS |
|
Depth Estimation (Q)
|
85% |
20456
159.9 IPS |
|
Style Transfer (SP)
|
100% |
68489
88.0 IPS |
|
Style Transfer (HP)
|
100% |
74779
96.1 IPS |
|
Style Transfer (Q)
|
96% |
69799
90.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
13313
491.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
14178
523.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
11285
416.7 IPS |
|
Text Classification (SP)
|
100% |
2330
3.11 KIPS |
|
Text Classification (HP)
|
100% |
3977
5.31 KIPS |
|
Text Classification (Q)
|
93% |
3969
5.33 KIPS |
|
Machine Translation (SP)
|
100% |
708
12.2 IPS |
|
Machine Translation (HP)
|
100% |
683
11.8 IPS |
|
Machine Translation (Q)
|
98% |
694
12.0 IPS |