User | aeonsim |
Upload Date | August 16 2024 03:13 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 14.5 (Build 23F79) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,9 |
Motherboard | Mac14,9 |
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 | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1090
202.7 IPS |
|
Image Classification (HP)
|
100% |
8328
1.55 KIPS |
|
Image Classification (Q)
|
99% |
8924
1.66 KIPS |
|
Image Segmentation (SP)
|
100% |
748
12.1 IPS |
|
Image Segmentation (HP)
|
100% |
5137
83.3 IPS |
|
Image Segmentation (Q)
|
100% |
5140
83.3 IPS |
|
Pose Estimation (SP)
|
100% |
11174
13.0 IPS |
|
Pose Estimation (HP)
|
100% |
92512
107.9 IPS |
|
Pose Estimation (Q)
|
94% |
87474
102.6 IPS |
|
Object Detection (SP)
|
100% |
1242
98.5 IPS |
|
Object Detection (HP)
|
99% |
9159
728.6 IPS |
|
Object Detection (Q)
|
93% |
10011
798.8 IPS |
|
Face Detection (SP)
|
100% |
2057
24.4 IPS |
|
Face Detection (HP)
|
100% |
11776
139.9 IPS |
|
Face Detection (Q)
|
100% |
13543
160.9 IPS |
|
Depth Estimation (SP)
|
100% |
4091
31.5 IPS |
|
Depth Estimation (HP)
|
99% |
57578
443.6 IPS |
|
Depth Estimation (Q)
|
97% |
60679
469.2 IPS |
|
Style Transfer (SP)
|
100% |
13159
16.9 IPS |
|
Style Transfer (HP)
|
100% |
145581
187.1 IPS |
|
Style Transfer (Q)
|
100% |
146434
188.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
2703
99.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
20891
771.4 IPS |
|
Image Super-Resolution (Q)
|
98% |
28257
1.05 KIPS |
|
Text Classification (SP)
|
100% |
942
1.26 KIPS |
|
Text Classification (HP)
|
100% |
4239
5.66 KIPS |
|
Text Classification (Q)
|
93% |
4027
5.41 KIPS |
|
Machine Translation (SP)
|
100% |
1961
33.8 IPS |
|
Machine Translation (HP)
|
100% |
2283
39.3 IPS |
|
Machine Translation (Q)
|
98% |
2278
39.4 IPS |