User | jcontarino |
Upload Date | November 09 2024 08:06 PM |
Views | 12 |
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 | 3.94 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2146
399.0 IPS |
|
Image Classification (HP)
|
100% |
18806
3.50 KIPS |
|
Image Classification (Q)
|
99% |
19639
3.66 KIPS |
|
Image Segmentation (SP)
|
100% |
2468
40.0 IPS |
|
Image Segmentation (HP)
|
100% |
18307
296.8 IPS |
|
Image Segmentation (Q)
|
100% |
18339
297.3 IPS |
|
Pose Estimation (SP)
|
100% |
18437
21.5 IPS |
|
Pose Estimation (HP)
|
100% |
120057
140.1 IPS |
|
Pose Estimation (Q)
|
94% |
227494
266.8 IPS |
|
Object Detection (SP)
|
100% |
2491
197.6 IPS |
|
Object Detection (HP)
|
100% |
19013
1.51 KIPS |
|
Object Detection (Q)
|
91% |
25646
2.05 KIPS |
|
Face Detection (SP)
|
100% |
4524
53.8 IPS |
|
Face Detection (HP)
|
100% |
28767
341.8 IPS |
|
Face Detection (Q)
|
100% |
47386
563.0 IPS |
|
Depth Estimation (SP)
|
100% |
8723
67.2 IPS |
|
Depth Estimation (HP)
|
99% |
93841
723.0 IPS |
|
Depth Estimation (Q)
|
97% |
98023
757.9 IPS |
|
Style Transfer (SP)
|
100% |
36380
46.8 IPS |
|
Style Transfer (HP)
|
100% |
172953
222.3 IPS |
|
Style Transfer (Q)
|
100% |
173100
222.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
7023
259.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
48764
1.80 KIPS |
|
Image Super-Resolution (Q)
|
98% |
83279
3.09 KIPS |
|
Text Classification (SP)
|
100% |
2938
3.92 KIPS |
|
Text Classification (HP)
|
100% |
5867
7.83 KIPS |
|
Text Classification (Q)
|
93% |
5901
7.92 KIPS |
|
Machine Translation (SP)
|
100% |
5656
97.4 IPS |
|
Machine Translation (HP)
|
100% |
17449
300.6 IPS |
|
Machine Translation (Q)
|
98% |
17385
300.4 IPS |