User | astrokari |
Upload Date | August 31 2024 06:34 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5035e) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,5 |
Motherboard | Mac14,5 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.48 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1394
259.3 IPS |
|
Image Classification (HP)
|
100% |
14669
2.73 KIPS |
|
Image Classification (Q)
|
99% |
16013
2.99 KIPS |
|
Image Segmentation (SP)
|
100% |
1739
28.2 IPS |
|
Image Segmentation (HP)
|
100% |
9337
151.4 IPS |
|
Image Segmentation (Q)
|
100% |
9352
151.6 IPS |
|
Pose Estimation (SP)
|
100% |
13016
15.2 IPS |
|
Pose Estimation (HP)
|
100% |
102897
120.1 IPS |
|
Pose Estimation (Q)
|
94% |
97784
114.7 IPS |
|
Object Detection (SP)
|
100% |
1701
134.9 IPS |
|
Object Detection (HP)
|
99% |
14092
1.12 KIPS |
|
Object Detection (Q)
|
91% |
16785
1.34 KIPS |
|
Face Detection (SP)
|
100% |
3631
43.1 IPS |
|
Face Detection (HP)
|
100% |
23897
284.0 IPS |
|
Face Detection (Q)
|
100% |
36978
439.4 IPS |
|
Depth Estimation (SP)
|
100% |
6346
48.9 IPS |
|
Depth Estimation (HP)
|
99% |
73724
568.0 IPS |
|
Depth Estimation (Q)
|
97% |
82129
635.0 IPS |
|
Style Transfer (SP)
|
100% |
25104
32.3 IPS |
|
Style Transfer (HP)
|
100% |
156058
200.6 IPS |
|
Style Transfer (Q)
|
100% |
156931
201.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5153
190.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
41329
1.53 KIPS |
|
Image Super-Resolution (Q)
|
98% |
48008
1.78 KIPS |
|
Text Classification (SP)
|
100% |
2259
3.01 KIPS |
|
Text Classification (HP)
|
100% |
3917
5.23 KIPS |
|
Text Classification (Q)
|
93% |
3894
5.23 KIPS |
|
Machine Translation (SP)
|
100% |
4723
81.3 IPS |
|
Machine Translation (HP)
|
100% |
2085
35.9 IPS |
|
Machine Translation (Q)
|
98% |
2081
36.0 IPS |