User | f180n4cc1 |
Upload Date | August 16 2024 07:58 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5024e) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,7 |
Motherboard | Mac15,7 |
CPU Information | |
---|---|
Name | Apple M3 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M3 Pro |
Base Frequency | 3.78 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1588
295.3 IPS |
|
Image Classification (HP)
|
100% |
15640
2.91 KIPS |
|
Image Classification (Q)
|
99% |
17125
3.19 KIPS |
|
Image Segmentation (SP)
|
100% |
1991
32.3 IPS |
|
Image Segmentation (HP)
|
100% |
14085
228.3 IPS |
|
Image Segmentation (Q)
|
100% |
14092
228.4 IPS |
|
Pose Estimation (SP)
|
100% |
8974
10.5 IPS |
|
Pose Estimation (HP)
|
100% |
118097
137.8 IPS |
|
Pose Estimation (Q)
|
94% |
118169
138.6 IPS |
|
Object Detection (SP)
|
100% |
1828
145.0 IPS |
|
Object Detection (HP)
|
100% |
16112
1.28 KIPS |
|
Object Detection (Q)
|
91% |
19897
1.59 KIPS |
|
Face Detection (SP)
|
100% |
3707
44.0 IPS |
|
Face Detection (HP)
|
100% |
25951
308.4 IPS |
|
Face Detection (Q)
|
100% |
39395
468.1 IPS |
|
Depth Estimation (SP)
|
100% |
7201
55.5 IPS |
|
Depth Estimation (HP)
|
99% |
81051
624.4 IPS |
|
Depth Estimation (Q)
|
97% |
90587
700.4 IPS |
|
Style Transfer (SP)
|
100% |
22450
28.9 IPS |
|
Style Transfer (HP)
|
100% |
168580
216.7 IPS |
|
Style Transfer (Q)
|
100% |
168525
216.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
5240
193.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
43826
1.62 KIPS |
|
Image Super-Resolution (Q)
|
98% |
54714
2.03 KIPS |
|
Text Classification (SP)
|
100% |
2734
3.65 KIPS |
|
Text Classification (HP)
|
100% |
4705
6.28 KIPS |
|
Text Classification (Q)
|
93% |
4737
6.36 KIPS |
|
Machine Translation (SP)
|
100% |
3517
60.6 IPS |
|
Machine Translation (HP)
|
100% |
2632
45.3 IPS |
|
Machine Translation (Q)
|
98% |
2619
45.3 IPS |