User | Ricochet |
Upload Date | October 16 2024 10:20 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 15.0.1 (Build 24A348) |
Model | Mac mini (2023) |
Model ID | Mac14,12 |
Motherboard | Mac14,12 |
CPU Information | |
---|---|
Name | Apple M2 Pro |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M2 Pro |
Base Frequency | 3.38 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1380
256.6 IPS |
|
Image Classification (HP)
|
100% |
14126
2.63 KIPS |
|
Image Classification (Q)
|
96% |
16451
3.07 KIPS |
|
Image Segmentation (SP)
|
100% |
1657
26.9 IPS |
|
Image Segmentation (HP)
|
100% |
10125
164.1 IPS |
|
Image Segmentation (Q)
|
99% |
11150
180.7 IPS |
|
Pose Estimation (SP)
|
100% |
12735
14.9 IPS |
|
Pose Estimation (HP)
|
100% |
106345
124.1 IPS |
|
Pose Estimation (Q)
|
95% |
104189
122.1 IPS |
|
Object Detection (SP)
|
100% |
1667
132.2 IPS |
|
Object Detection (HP)
|
99% |
15363
1.22 KIPS |
|
Object Detection (Q)
|
91% |
16748
1.34 KIPS |
|
Face Detection (SP)
|
100% |
3614
42.9 IPS |
|
Face Detection (HP)
|
100% |
34966
415.5 IPS |
|
Face Detection (Q)
|
100% |
43687
519.1 IPS |
|
Depth Estimation (SP)
|
100% |
6321
48.7 IPS |
|
Depth Estimation (HP)
|
99% |
87681
675.5 IPS |
|
Depth Estimation (Q)
|
85% |
109263
853.8 IPS |
|
Style Transfer (SP)
|
100% |
25233
32.4 IPS |
|
Style Transfer (HP)
|
100% |
204934
263.4 IPS |
|
Style Transfer (Q)
|
96% |
191030
246.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5090
188.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
41903
1.55 KIPS |
|
Image Super-Resolution (Q)
|
99% |
49786
1.84 KIPS |
|
Text Classification (SP)
|
100% |
2264
3.02 KIPS |
|
Text Classification (HP)
|
100% |
3970
5.30 KIPS |
|
Text Classification (Q)
|
93% |
3949
5.30 KIPS |
|
Machine Translation (SP)
|
100% |
4527
78.0 IPS |
|
Machine Translation (HP)
|
100% |
2279
39.3 IPS |
|
Machine Translation (Q)
|
98% |
2259
39.0 IPS |