User | alpha_p |
Upload Date | August 16 2024 04:21 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 15.0 (Build 24A5320a) |
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 | 3.48 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1383
257.2 IPS |
|
Image Classification (HP)
|
100% |
13989
2.60 KIPS |
|
Image Classification (Q)
|
99% |
15658
2.92 KIPS |
|
Image Segmentation (SP)
|
100% |
1681
27.3 IPS |
|
Image Segmentation (HP)
|
100% |
9276
150.4 IPS |
|
Image Segmentation (Q)
|
100% |
9152
148.4 IPS |
|
Pose Estimation (SP)
|
100% |
12918
15.1 IPS |
|
Pose Estimation (HP)
|
100% |
102863
120.0 IPS |
|
Pose Estimation (Q)
|
94% |
98016
115.0 IPS |
|
Object Detection (SP)
|
100% |
1694
134.4 IPS |
|
Object Detection (HP)
|
99% |
13857
1.10 KIPS |
|
Object Detection (Q)
|
91% |
16775
1.34 KIPS |
|
Face Detection (SP)
|
100% |
3621
43.0 IPS |
|
Face Detection (HP)
|
100% |
23206
275.7 IPS |
|
Face Detection (Q)
|
100% |
35794
425.3 IPS |
|
Depth Estimation (SP)
|
100% |
6396
49.3 IPS |
|
Depth Estimation (HP)
|
99% |
73511
566.4 IPS |
|
Depth Estimation (Q)
|
97% |
81980
633.9 IPS |
|
Style Transfer (SP)
|
100% |
25015
32.2 IPS |
|
Style Transfer (HP)
|
100% |
155949
200.5 IPS |
|
Style Transfer (Q)
|
100% |
157183
202.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4517
166.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
40978
1.51 KIPS |
|
Image Super-Resolution (Q)
|
98% |
49641
1.84 KIPS |
|
Text Classification (SP)
|
100% |
2285
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3817
5.09 KIPS |
|
Text Classification (Q)
|
93% |
3816
5.12 KIPS |
|
Machine Translation (SP)
|
100% |
4599
79.2 IPS |
|
Machine Translation (HP)
|
100% |
2298
39.6 IPS |
|
Machine Translation (Q)
|
98% |
2291
39.6 IPS |