User | krish1108 |
Upload Date | February 26 2025 03:51 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 15.3.1 (Build 24D70) |
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 | 3.48 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1406
261.4 IPS |
|
Image Classification (HP)
|
100% |
14097
2.62 KIPS |
|
Image Classification (Q)
|
96% |
16146
3.02 KIPS |
|
Image Segmentation (SP)
|
100% |
1712
27.8 IPS |
|
Image Segmentation (HP)
|
100% |
19160
310.6 IPS |
|
Image Segmentation (Q)
|
99% |
24258
393.2 IPS |
|
Pose Estimation (SP)
|
100% |
12920
15.1 IPS |
|
Pose Estimation (HP)
|
100% |
105722
123.4 IPS |
|
Pose Estimation (Q)
|
95% |
103817
121.7 IPS |
|
Object Detection (SP)
|
100% |
1702
135.0 IPS |
|
Object Detection (HP)
|
99% |
14854
1.18 KIPS |
|
Object Detection (Q)
|
91% |
16431
1.31 KIPS |
|
Face Detection (SP)
|
100% |
3686
43.8 IPS |
|
Face Detection (HP)
|
100% |
34680
412.1 IPS |
|
Face Detection (Q)
|
100% |
43101
512.1 IPS |
|
Depth Estimation (SP)
|
100% |
6384
49.2 IPS |
|
Depth Estimation (HP)
|
99% |
87485
674.0 IPS |
|
Depth Estimation (Q)
|
85% |
108375
846.9 IPS |
|
Style Transfer (SP)
|
100% |
24765
31.8 IPS |
|
Style Transfer (HP)
|
100% |
205793
264.5 IPS |
|
Style Transfer (Q)
|
96% |
190674
246.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
5104
188.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
41018
1.51 KIPS |
|
Image Super-Resolution (Q)
|
99% |
47945
1.77 KIPS |
|
Text Classification (SP)
|
100% |
2270
3.03 KIPS |
|
Text Classification (HP)
|
100% |
3926
5.24 KIPS |
|
Text Classification (Q)
|
93% |
3903
5.24 KIPS |
|
Machine Translation (SP)
|
100% |
4083
70.3 IPS |
|
Machine Translation (HP)
|
100% |
3902
67.2 IPS |
|
Machine Translation (Q)
|
98% |
3961
68.4 IPS |