User | matwyn |
Upload Date | August 16 2024 10:26 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Pro |
System Information | |
---|---|
Operating System | macOS 14.5 (Build 23F79) |
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 | 4.05 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 18.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1281
238.2 IPS |
|
Image Classification (HP)
|
100% |
7979
1.48 KIPS |
|
Image Classification (Q)
|
99% |
8582
1.60 KIPS |
|
Image Segmentation (SP)
|
100% |
838
13.6 IPS |
|
Image Segmentation (HP)
|
100% |
6725
109.0 IPS |
|
Image Segmentation (Q)
|
100% |
6724
109.0 IPS |
|
Pose Estimation (SP)
|
100% |
8509
9.93 IPS |
|
Pose Estimation (HP)
|
100% |
106020
123.7 IPS |
|
Pose Estimation (Q)
|
94% |
102903
120.7 IPS |
|
Object Detection (SP)
|
100% |
1492
118.4 IPS |
|
Object Detection (HP)
|
100% |
10151
805.2 IPS |
|
Object Detection (Q)
|
93% |
11080
884.1 IPS |
|
Face Detection (SP)
|
100% |
2421
28.8 IPS |
|
Face Detection (HP)
|
100% |
13764
163.6 IPS |
|
Face Detection (Q)
|
100% |
16101
191.3 IPS |
|
Depth Estimation (SP)
|
100% |
4308
33.2 IPS |
|
Depth Estimation (HP)
|
99% |
60335
464.8 IPS |
|
Depth Estimation (Q)
|
97% |
65464
506.2 IPS |
|
Style Transfer (SP)
|
100% |
12425
16.0 IPS |
|
Style Transfer (HP)
|
100% |
155944
200.5 IPS |
|
Style Transfer (Q)
|
100% |
156055
200.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4024
148.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
21362
788.8 IPS |
|
Image Super-Resolution (Q)
|
98% |
27481
1.02 KIPS |
|
Text Classification (SP)
|
100% |
586
781.8 IPS |
|
Text Classification (HP)
|
100% |
4735
6.32 KIPS |
|
Text Classification (Q)
|
93% |
4777
6.41 KIPS |
|
Machine Translation (SP)
|
100% |
2205
38.0 IPS |
|
Machine Translation (HP)
|
100% |
2872
49.5 IPS |
|
Machine Translation (Q)
|
98% |
2850
49.2 IPS |