User | vorlons |
Upload Date | August 16 2024 01:20 PM |
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 (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 | 3.22 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
939
174.6 IPS |
|
Image Classification (HP)
|
100% |
7387
1.37 KIPS |
|
Image Classification (Q)
|
99% |
7720
1.44 KIPS |
|
Image Segmentation (SP)
|
100% |
674
10.9 IPS |
|
Image Segmentation (HP)
|
100% |
3884
63.0 IPS |
|
Image Segmentation (Q)
|
100% |
3883
62.9 IPS |
|
Pose Estimation (SP)
|
100% |
10081
11.8 IPS |
|
Pose Estimation (HP)
|
100% |
69261
80.8 IPS |
|
Pose Estimation (Q)
|
94% |
66213
77.7 IPS |
|
Object Detection (SP)
|
100% |
1063
84.3 IPS |
|
Object Detection (HP)
|
99% |
7654
608.9 IPS |
|
Object Detection (Q)
|
93% |
7343
585.9 IPS |
|
Face Detection (SP)
|
100% |
1978
23.5 IPS |
|
Face Detection (HP)
|
100% |
11212
133.2 IPS |
|
Face Detection (Q)
|
100% |
10567
125.6 IPS |
|
Depth Estimation (SP)
|
100% |
3170
24.4 IPS |
|
Depth Estimation (HP)
|
99% |
47082
362.7 IPS |
|
Depth Estimation (Q)
|
97% |
50062
387.1 IPS |
|
Style Transfer (SP)
|
100% |
12127
15.6 IPS |
|
Style Transfer (HP)
|
100% |
118269
152.0 IPS |
|
Style Transfer (Q)
|
100% |
95614
122.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
2081
76.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
19076
704.4 IPS |
|
Image Super-Resolution (Q)
|
98% |
23299
863.2 IPS |
|
Text Classification (SP)
|
100% |
751
1.00 KIPS |
|
Text Classification (HP)
|
100% |
3630
4.84 KIPS |
|
Text Classification (Q)
|
93% |
3597
4.83 KIPS |
|
Machine Translation (SP)
|
100% |
1263
21.8 IPS |
|
Machine Translation (HP)
|
100% |
1913
33.0 IPS |
|
Machine Translation (Q)
|
98% |
1856
32.1 IPS |