User | zedkiel |
Upload Date | October 21 2024 08:09 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B82) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,9 |
Motherboard | Mac14,9 |
CPU Information | |
---|---|
Name | Apple M2 Pro |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M2 Pro |
Base Frequency | 3.48 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1390
258.5 IPS |
|
Image Classification (HP)
|
100% |
14013
2.61 KIPS |
|
Image Classification (Q)
|
96% |
16493
3.08 KIPS |
|
Image Segmentation (SP)
|
100% |
1682
27.3 IPS |
|
Image Segmentation (HP)
|
100% |
19637
318.3 IPS |
|
Image Segmentation (Q)
|
99% |
24676
400.0 IPS |
|
Pose Estimation (SP)
|
100% |
12723
14.8 IPS |
|
Pose Estimation (HP)
|
100% |
106155
123.9 IPS |
|
Pose Estimation (Q)
|
95% |
103998
121.9 IPS |
|
Object Detection (SP)
|
100% |
1695
134.5 IPS |
|
Object Detection (HP)
|
99% |
15144
1.20 KIPS |
|
Object Detection (Q)
|
91% |
16619
1.33 KIPS |
|
Face Detection (SP)
|
100% |
3652
43.4 IPS |
|
Face Detection (HP)
|
100% |
35550
422.4 IPS |
|
Face Detection (Q)
|
100% |
41022
487.4 IPS |
|
Depth Estimation (SP)
|
100% |
6264
48.3 IPS |
|
Depth Estimation (HP)
|
99% |
87386
673.3 IPS |
|
Depth Estimation (Q)
|
85% |
108353
846.7 IPS |
|
Style Transfer (SP)
|
100% |
25174
32.4 IPS |
|
Style Transfer (HP)
|
100% |
203753
261.9 IPS |
|
Style Transfer (Q)
|
96% |
192734
248.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5109
188.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
40614
1.50 KIPS |
|
Image Super-Resolution (Q)
|
99% |
48355
1.79 KIPS |
|
Text Classification (SP)
|
100% |
2278
3.04 KIPS |
|
Text Classification (HP)
|
100% |
3990
5.33 KIPS |
|
Text Classification (Q)
|
93% |
3949
5.30 KIPS |
|
Machine Translation (SP)
|
100% |
4538
78.2 IPS |
|
Machine Translation (HP)
|
100% |
4572
78.7 IPS |
|
Machine Translation (Q)
|
98% |
4993
86.3 IPS |