User | ssk_ats |
Upload Date | August 22 2024 03:49 AM |
Views | 4 |
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 (14-inch, 2021) |
Model ID | MacBookPro18,4 |
Motherboard | MacBookPro18,4 |
CPU Information | |
---|---|
Name | Apple M1 Max |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Max |
Base Frequency | 3.22 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
898
167.1 IPS |
|
Image Classification (HP)
|
100% |
7169
1.33 KIPS |
|
Image Classification (Q)
|
99% |
7514
1.40 KIPS |
|
Image Segmentation (SP)
|
100% |
661
10.7 IPS |
|
Image Segmentation (HP)
|
100% |
3873
62.8 IPS |
|
Image Segmentation (Q)
|
100% |
3870
62.7 IPS |
|
Pose Estimation (SP)
|
100% |
10157
11.9 IPS |
|
Pose Estimation (HP)
|
100% |
69481
81.1 IPS |
|
Pose Estimation (Q)
|
94% |
65717
77.1 IPS |
|
Object Detection (SP)
|
100% |
957
75.9 IPS |
|
Object Detection (HP)
|
99% |
7430
591.1 IPS |
|
Object Detection (Q)
|
93% |
7062
563.5 IPS |
|
Face Detection (SP)
|
100% |
1686
20.0 IPS |
|
Face Detection (HP)
|
100% |
11217
133.3 IPS |
|
Face Detection (Q)
|
100% |
11706
139.1 IPS |
|
Depth Estimation (SP)
|
100% |
3134
24.1 IPS |
|
Depth Estimation (HP)
|
99% |
45343
349.3 IPS |
|
Depth Estimation (Q)
|
97% |
49207
380.5 IPS |
|
Style Transfer (SP)
|
100% |
11738
15.1 IPS |
|
Style Transfer (HP)
|
100% |
117874
151.5 IPS |
|
Style Transfer (Q)
|
100% |
122050
156.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
2551
94.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
17971
663.6 IPS |
|
Image Super-Resolution (Q)
|
98% |
22816
845.3 IPS |
|
Text Classification (SP)
|
100% |
470
627.8 IPS |
|
Text Classification (HP)
|
100% |
3097
4.13 KIPS |
|
Text Classification (Q)
|
93% |
3276
4.40 KIPS |
|
Machine Translation (SP)
|
100% |
1144
19.7 IPS |
|
Machine Translation (HP)
|
100% |
1790
30.8 IPS |
|
Machine Translation (Q)
|
98% |
1816
31.4 IPS |