User | Qiguanjiachen |
Upload Date | August 17 2024 05:01 AM |
Views | 12 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,5 |
Motherboard | Mac14,5 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.48 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1080
200.8 IPS |
|
Image Classification (HP)
|
100% |
8152
1.52 KIPS |
|
Image Classification (Q)
|
99% |
8933
1.67 KIPS |
|
Image Segmentation (SP)
|
100% |
748
12.1 IPS |
|
Image Segmentation (HP)
|
100% |
5111
82.9 IPS |
|
Image Segmentation (Q)
|
100% |
5132
83.2 IPS |
|
Pose Estimation (SP)
|
100% |
11310
13.2 IPS |
|
Pose Estimation (HP)
|
100% |
92897
108.4 IPS |
|
Pose Estimation (Q)
|
94% |
89219
104.6 IPS |
|
Object Detection (SP)
|
100% |
1277
101.3 IPS |
|
Object Detection (HP)
|
99% |
9684
770.3 IPS |
|
Object Detection (Q)
|
93% |
10382
828.4 IPS |
|
Face Detection (SP)
|
100% |
2047
24.3 IPS |
|
Face Detection (HP)
|
100% |
11429
135.8 IPS |
|
Face Detection (Q)
|
100% |
13275
157.7 IPS |
|
Depth Estimation (SP)
|
100% |
3808
29.3 IPS |
|
Depth Estimation (HP)
|
99% |
57330
441.7 IPS |
|
Depth Estimation (Q)
|
97% |
60891
470.8 IPS |
|
Style Transfer (SP)
|
100% |
13027
16.7 IPS |
|
Style Transfer (HP)
|
100% |
147221
189.3 IPS |
|
Style Transfer (Q)
|
100% |
147531
189.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
2378
87.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
20729
765.4 IPS |
|
Image Super-Resolution (Q)
|
98% |
28003
1.04 KIPS |
|
Text Classification (SP)
|
100% |
387
516.5 IPS |
|
Text Classification (HP)
|
100% |
4161
5.55 KIPS |
|
Text Classification (Q)
|
93% |
3998
5.37 KIPS |
|
Machine Translation (SP)
|
100% |
1854
31.9 IPS |
|
Machine Translation (HP)
|
100% |
1991
34.3 IPS |
|
Machine Translation (Q)
|
98% |
2004
34.6 IPS |