User | edwardhchan |
Upload Date | November 14 2024 05:21 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2083) |
Model | Mac16,11 |
Model ID | Mac16,11 |
Motherboard | Mac16,11 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2103
391.1 IPS |
|
Image Classification (HP)
|
100% |
17585
3.27 KIPS |
|
Image Classification (Q)
|
99% |
18304
3.41 KIPS |
|
Image Segmentation (SP)
|
100% |
2505
40.6 IPS |
|
Image Segmentation (HP)
|
100% |
17925
290.6 IPS |
|
Image Segmentation (Q)
|
100% |
17960
291.1 IPS |
|
Pose Estimation (SP)
|
100% |
18920
22.1 IPS |
|
Pose Estimation (HP)
|
100% |
119018
138.9 IPS |
|
Pose Estimation (Q)
|
94% |
225180
264.1 IPS |
|
Object Detection (SP)
|
100% |
2428
192.6 IPS |
|
Object Detection (HP)
|
100% |
18323
1.45 KIPS |
|
Object Detection (Q)
|
91% |
23908
1.91 KIPS |
|
Face Detection (SP)
|
100% |
4350
51.7 IPS |
|
Face Detection (HP)
|
100% |
28143
334.4 IPS |
|
Face Detection (Q)
|
100% |
47585
565.4 IPS |
|
Depth Estimation (SP)
|
100% |
8769
67.6 IPS |
|
Depth Estimation (HP)
|
99% |
91718
706.6 IPS |
|
Depth Estimation (Q)
|
97% |
96412
745.5 IPS |
|
Style Transfer (SP)
|
100% |
34863
44.8 IPS |
|
Style Transfer (HP)
|
100% |
169954
218.5 IPS |
|
Style Transfer (Q)
|
100% |
169310
217.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
7059
260.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
46294
1.71 KIPS |
|
Image Super-Resolution (Q)
|
98% |
79371
2.94 KIPS |
|
Text Classification (SP)
|
100% |
2981
3.98 KIPS |
|
Text Classification (HP)
|
100% |
5426
7.24 KIPS |
|
Text Classification (Q)
|
93% |
5901
7.92 KIPS |
|
Machine Translation (SP)
|
100% |
5704
98.2 IPS |
|
Machine Translation (HP)
|
100% |
16679
287.3 IPS |
|
Machine Translation (Q)
|
98% |
16842
291.1 IPS |