User | AlexSwitch |
Upload Date | November 23 2024 08:34 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B91) |
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% |
1383
257.2 IPS |
|
Image Classification (HP)
|
100% |
14045
2.61 KIPS |
|
Image Classification (Q)
|
96% |
17556
3.28 KIPS |
|
Image Segmentation (SP)
|
100% |
1661
26.9 IPS |
|
Image Segmentation (HP)
|
100% |
19510
316.3 IPS |
|
Image Segmentation (Q)
|
99% |
24743
401.1 IPS |
|
Pose Estimation (SP)
|
100% |
12659
14.8 IPS |
|
Pose Estimation (HP)
|
100% |
106201
123.9 IPS |
|
Pose Estimation (Q)
|
95% |
104192
122.1 IPS |
|
Object Detection (SP)
|
100% |
1694
134.4 IPS |
|
Object Detection (HP)
|
99% |
15157
1.21 KIPS |
|
Object Detection (Q)
|
91% |
16703
1.33 KIPS |
|
Face Detection (SP)
|
100% |
3644
43.3 IPS |
|
Face Detection (HP)
|
100% |
35427
421.0 IPS |
|
Face Detection (Q)
|
100% |
45297
538.2 IPS |
|
Depth Estimation (SP)
|
100% |
6274
48.3 IPS |
|
Depth Estimation (HP)
|
99% |
87719
675.8 IPS |
|
Depth Estimation (Q)
|
85% |
108541
848.2 IPS |
|
Style Transfer (SP)
|
100% |
25090
32.3 IPS |
|
Style Transfer (HP)
|
100% |
204677
263.1 IPS |
|
Style Transfer (Q)
|
96% |
190635
246.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5072
187.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
41070
1.52 KIPS |
|
Image Super-Resolution (Q)
|
99% |
48748
1.80 KIPS |
|
Text Classification (SP)
|
100% |
2275
3.04 KIPS |
|
Text Classification (HP)
|
100% |
3962
5.29 KIPS |
|
Text Classification (Q)
|
93% |
3947
5.30 KIPS |
|
Machine Translation (SP)
|
100% |
4361
75.1 IPS |
|
Machine Translation (HP)
|
100% |
3758
64.7 IPS |
|
Machine Translation (Q)
|
98% |
4353
75.2 IPS |