User | souko |
Upload Date | August 17 2024 06:18 PM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Pro (16-inch, 2021) |
Model ID | MacBookPro18,2 |
Motherboard | MacBookPro18,2 |
CPU Information | |
---|---|
Name | Apple M1 Max |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Max |
Base Frequency | 3.18 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
901
167.5 IPS |
|
Image Classification (HP)
|
100% |
7388
1.37 KIPS |
|
Image Classification (Q)
|
99% |
7783
1.45 KIPS |
|
Image Segmentation (SP)
|
100% |
654
10.6 IPS |
|
Image Segmentation (HP)
|
100% |
3714
60.2 IPS |
|
Image Segmentation (Q)
|
100% |
3717
60.3 IPS |
|
Pose Estimation (SP)
|
100% |
9907
11.6 IPS |
|
Pose Estimation (HP)
|
100% |
69762
81.4 IPS |
|
Pose Estimation (Q)
|
94% |
65691
77.1 IPS |
|
Object Detection (SP)
|
100% |
1024
81.2 IPS |
|
Object Detection (HP)
|
99% |
7460
593.4 IPS |
|
Object Detection (Q)
|
93% |
7158
571.2 IPS |
|
Face Detection (SP)
|
100% |
1712
20.3 IPS |
|
Face Detection (HP)
|
100% |
11173
132.8 IPS |
|
Face Detection (Q)
|
100% |
11326
134.6 IPS |
|
Depth Estimation (SP)
|
100% |
3125
24.1 IPS |
|
Depth Estimation (HP)
|
99% |
46898
361.3 IPS |
|
Depth Estimation (Q)
|
97% |
49373
381.8 IPS |
|
Style Transfer (SP)
|
100% |
11841
15.2 IPS |
|
Style Transfer (HP)
|
100% |
117365
150.9 IPS |
|
Style Transfer (Q)
|
100% |
123395
158.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
2171
80.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
18915
698.4 IPS |
|
Image Super-Resolution (Q)
|
98% |
23101
855.8 IPS |
|
Text Classification (SP)
|
100% |
671
895.4 IPS |
|
Text Classification (HP)
|
100% |
3260
4.35 KIPS |
|
Text Classification (Q)
|
93% |
3080
4.13 KIPS |
|
Machine Translation (SP)
|
100% |
1317
22.7 IPS |
|
Machine Translation (HP)
|
100% |
1845
31.8 IPS |
|
Machine Translation (Q)
|
98% |
1846
31.9 IPS |