User | zedkiel |
Upload Date | October 21 2024 06:30 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B82) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,9 |
Motherboard | Mac14,9 |
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% |
1400
260.4 IPS |
|
Image Classification (HP)
|
100% |
14652
2.72 KIPS |
|
Image Classification (Q)
|
96% |
17481
3.26 KIPS |
|
Image Segmentation (SP)
|
100% |
1685
27.3 IPS |
|
Image Segmentation (HP)
|
100% |
19441
315.2 IPS |
|
Image Segmentation (Q)
|
99% |
24012
389.3 IPS |
|
Pose Estimation (SP)
|
100% |
12718
14.8 IPS |
|
Pose Estimation (HP)
|
100% |
105828
123.5 IPS |
|
Pose Estimation (Q)
|
95% |
104102
122.0 IPS |
|
Object Detection (SP)
|
100% |
1697
134.6 IPS |
|
Object Detection (HP)
|
99% |
15128
1.20 KIPS |
|
Object Detection (Q)
|
91% |
16634
1.33 KIPS |
|
Face Detection (SP)
|
100% |
3671
43.6 IPS |
|
Face Detection (HP)
|
100% |
35446
421.2 IPS |
|
Face Detection (Q)
|
100% |
45089
535.8 IPS |
|
Depth Estimation (SP)
|
100% |
6386
49.2 IPS |
|
Depth Estimation (HP)
|
99% |
88187
679.4 IPS |
|
Depth Estimation (Q)
|
85% |
108648
849.0 IPS |
|
Style Transfer (SP)
|
100% |
24909
32.0 IPS |
|
Style Transfer (HP)
|
100% |
203437
261.5 IPS |
|
Style Transfer (Q)
|
96% |
189505
244.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5110
188.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
40930
1.51 KIPS |
|
Image Super-Resolution (Q)
|
99% |
49007
1.81 KIPS |
|
Text Classification (SP)
|
100% |
2270
3.03 KIPS |
|
Text Classification (HP)
|
100% |
4016
5.36 KIPS |
|
Text Classification (Q)
|
93% |
3948
5.30 KIPS |
|
Machine Translation (SP)
|
100% |
4421
76.2 IPS |
|
Machine Translation (HP)
|
100% |
4460
76.8 IPS |
|
Machine Translation (Q)
|
98% |
4949
85.5 IPS |