User | mchus |
Upload Date | November 15 2024 12:43 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 14.3 (Build 23D56) |
Model | MacBook Pro (16-inch, 2023) |
Model ID | Mac14,10 |
Motherboard | Mac14,10 |
CPU Information | |
---|---|
Name | Apple M2 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Pro |
Base Frequency | 3.48 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1103
205.1 IPS |
|
Image Classification (HP)
|
100% |
8397
1.56 KIPS |
|
Image Classification (Q)
|
94% |
8913
1.67 KIPS |
|
Image Segmentation (SP)
|
100% |
733
11.9 IPS |
|
Image Segmentation (HP)
|
100% |
5146
83.4 IPS |
|
Image Segmentation (Q)
|
99% |
8630
139.9 IPS |
|
Pose Estimation (SP)
|
100% |
11412
13.3 IPS |
|
Pose Estimation (HP)
|
100% |
93079
108.6 IPS |
|
Pose Estimation (Q)
|
95% |
83802
98.2 IPS |
|
Object Detection (SP)
|
100% |
1287
102.1 IPS |
|
Object Detection (HP)
|
99% |
9405
748.1 IPS |
|
Object Detection (Q)
|
93% |
10267
819.2 IPS |
|
Face Detection (SP)
|
100% |
2019
24.0 IPS |
|
Face Detection (HP)
|
100% |
14758
175.4 IPS |
|
Face Detection (Q)
|
100% |
611
7.26 IPS |
|
Depth Estimation (SP)
|
100% |
3977
30.6 IPS |
|
Depth Estimation (HP)
|
99% |
56050
431.8 IPS |
|
Depth Estimation (Q)
|
85% |
64518
504.2 IPS |
|
Style Transfer (SP)
|
100% |
13795
17.7 IPS |
|
Style Transfer (HP)
|
100% |
145152
186.6 IPS |
|
Style Transfer (Q)
|
25% |
5394
150.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
2141
79.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
20932
772.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
22907
845.8 IPS |
|
Text Classification (SP)
|
100% |
899
1.20 KIPS |
|
Text Classification (HP)
|
100% |
4023
5.37 KIPS |
|
Text Classification (Q)
|
93% |
4012
5.38 KIPS |
|
Machine Translation (SP)
|
100% |
1938
33.4 IPS |
|
Machine Translation (HP)
|
100% |
2267
39.1 IPS |
|
Machine Translation (Q)
|
98% |
2260
39.0 IPS |