Upload Date | November 17 2024 07:21 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2083) |
Model | Mac16,10 |
Model ID | Mac16,10 |
Motherboard | Mac16,10 |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M4 |
Base Frequency | 4.41 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1984
369.1 IPS |
|
Image Classification (HP)
|
100% |
18250
3.39 KIPS |
|
Image Classification (Q)
|
97% |
26685
4.98 KIPS |
|
Image Segmentation (SP)
|
100% |
2054
33.3 IPS |
|
Image Segmentation (HP)
|
100% |
21986
356.4 IPS |
|
Image Segmentation (Q)
|
99% |
30345
491.9 IPS |
|
Pose Estimation (SP)
|
100% |
9922
11.6 IPS |
|
Pose Estimation (HP)
|
100% |
124141
144.9 IPS |
|
Pose Estimation (Q)
|
95% |
232539
272.5 IPS |
|
Object Detection (SP)
|
100% |
2292
181.8 IPS |
|
Object Detection (HP)
|
100% |
18755
1.49 KIPS |
|
Object Detection (Q)
|
91% |
26304
2.10 KIPS |
|
Face Detection (SP)
|
100% |
3900
46.3 IPS |
|
Face Detection (HP)
|
100% |
44177
524.9 IPS |
|
Face Detection (Q)
|
100% |
61560
731.5 IPS |
|
Depth Estimation (SP)
|
100% |
8334
64.2 IPS |
|
Depth Estimation (HP)
|
99% |
99426
766.0 IPS |
|
Depth Estimation (Q)
|
85% |
169786
1.33 KIPS |
|
Style Transfer (SP)
|
100% |
25177
32.4 IPS |
|
Style Transfer (HP)
|
100% |
234845
301.9 IPS |
|
Style Transfer (Q)
|
96% |
299325
386.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5728
211.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
49647
1.83 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85622
3.16 KIPS |
|
Text Classification (SP)
|
100% |
3115
4.16 KIPS |
|
Text Classification (HP)
|
100% |
6448
8.61 KIPS |
|
Text Classification (Q)
|
93% |
6537
8.77 KIPS |
|
Machine Translation (SP)
|
100% |
3860
66.5 IPS |
|
Machine Translation (HP)
|
100% |
16068
276.8 IPS |
|
Machine Translation (Q)
|
98% |
17649
305.0 IPS |