User | MacHammerFan |
Upload Date | December 04 2024 09:06 AM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B91) |
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 | 3.47 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1387
257.9 IPS |
|
Image Classification (HP)
|
100% |
14426
2.68 KIPS |
|
Image Classification (Q)
|
96% |
17396
3.25 KIPS |
|
Image Segmentation (SP)
|
100% |
1699
27.5 IPS |
|
Image Segmentation (HP)
|
100% |
19388
314.3 IPS |
|
Image Segmentation (Q)
|
99% |
24533
397.7 IPS |
|
Pose Estimation (SP)
|
100% |
13028
15.2 IPS |
|
Pose Estimation (HP)
|
100% |
106876
124.7 IPS |
|
Pose Estimation (Q)
|
95% |
104927
123.0 IPS |
|
Object Detection (SP)
|
100% |
1695
134.4 IPS |
|
Object Detection (HP)
|
99% |
15219
1.21 KIPS |
|
Object Detection (Q)
|
91% |
16831
1.34 KIPS |
|
Face Detection (SP)
|
100% |
3559
42.3 IPS |
|
Face Detection (HP)
|
100% |
36110
429.1 IPS |
|
Face Detection (Q)
|
100% |
46289
550.0 IPS |
|
Depth Estimation (SP)
|
100% |
6300
48.5 IPS |
|
Depth Estimation (HP)
|
99% |
88508
681.9 IPS |
|
Depth Estimation (Q)
|
85% |
110422
862.9 IPS |
|
Style Transfer (SP)
|
100% |
24983
32.1 IPS |
|
Style Transfer (HP)
|
100% |
202297
260.1 IPS |
|
Style Transfer (Q)
|
96% |
192141
247.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5097
188.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
41956
1.55 KIPS |
|
Image Super-Resolution (Q)
|
99% |
50624
1.87 KIPS |
|
Text Classification (SP)
|
100% |
2278
3.04 KIPS |
|
Text Classification (HP)
|
100% |
3988
5.32 KIPS |
|
Text Classification (Q)
|
93% |
4004
5.37 KIPS |
|
Machine Translation (SP)
|
100% |
4569
78.7 IPS |
|
Machine Translation (HP)
|
100% |
4784
82.4 IPS |
|
Machine Translation (Q)
|
98% |
4904
84.7 IPS |