User | zedkiel |
Upload Date | October 21 2024 05:06 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 15.0.1 (Build 24A348) |
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 | 3.47 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1378
256.3 IPS |
|
Image Classification (HP)
|
100% |
14632
2.72 KIPS |
|
Image Classification (Q)
|
96% |
16828
3.14 KIPS |
|
Image Segmentation (SP)
|
100% |
1673
27.1 IPS |
|
Image Segmentation (HP)
|
100% |
10079
163.4 IPS |
|
Image Segmentation (Q)
|
99% |
11211
181.7 IPS |
|
Pose Estimation (SP)
|
100% |
12706
14.8 IPS |
|
Pose Estimation (HP)
|
100% |
106165
123.9 IPS |
|
Pose Estimation (Q)
|
95% |
104210
122.1 IPS |
|
Object Detection (SP)
|
100% |
1672
132.7 IPS |
|
Object Detection (HP)
|
99% |
15219
1.21 KIPS |
|
Object Detection (Q)
|
91% |
16778
1.34 KIPS |
|
Face Detection (SP)
|
100% |
3540
42.1 IPS |
|
Face Detection (HP)
|
100% |
35519
422.0 IPS |
|
Face Detection (Q)
|
100% |
45056
535.4 IPS |
|
Depth Estimation (SP)
|
100% |
6283
48.4 IPS |
|
Depth Estimation (HP)
|
99% |
87711
675.8 IPS |
|
Depth Estimation (Q)
|
85% |
109167
853.1 IPS |
|
Style Transfer (SP)
|
100% |
24867
32.0 IPS |
|
Style Transfer (HP)
|
100% |
201843
259.5 IPS |
|
Style Transfer (Q)
|
96% |
189358
244.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
5105
188.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
41051
1.52 KIPS |
|
Image Super-Resolution (Q)
|
99% |
48598
1.79 KIPS |
|
Text Classification (SP)
|
100% |
2325
3.10 KIPS |
|
Text Classification (HP)
|
100% |
3963
5.29 KIPS |
|
Text Classification (Q)
|
93% |
3941
5.29 KIPS |
|
Machine Translation (SP)
|
100% |
4466
76.9 IPS |
|
Machine Translation (HP)
|
100% |
2296
39.6 IPS |
|
Machine Translation (Q)
|
98% |
2282
39.4 IPS |