User | EdwinValdezEXD |
Upload Date | October 11 2024 03:03 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5070a) |
Model | MacBook Pro (13-inch, 2022) |
Model ID | Mac14,7 |
Motherboard | Mac14,7 |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M2 |
Base Frequency | 3.45 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 8.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1363
253.4 IPS |
|
Image Classification (HP)
|
100% |
14295
2.66 KIPS |
|
Image Classification (Q)
|
96% |
14941
2.79 KIPS |
|
Image Segmentation (SP)
|
100% |
1498
24.3 IPS |
|
Image Segmentation (HP)
|
100% |
19048
308.8 IPS |
|
Image Segmentation (Q)
|
99% |
23664
383.6 IPS |
|
Pose Estimation (SP)
|
100% |
6811
7.95 IPS |
|
Pose Estimation (HP)
|
100% |
104554
122.0 IPS |
|
Pose Estimation (Q)
|
95% |
104332
122.3 IPS |
|
Object Detection (SP)
|
100% |
1536
121.8 IPS |
|
Object Detection (HP)
|
99% |
14899
1.19 KIPS |
|
Object Detection (Q)
|
91% |
18098
1.45 KIPS |
|
Face Detection (SP)
|
100% |
3047
36.2 IPS |
|
Face Detection (HP)
|
100% |
33718
400.6 IPS |
|
Face Detection (Q)
|
100% |
42100
500.2 IPS |
|
Depth Estimation (SP)
|
100% |
5618
43.3 IPS |
|
Depth Estimation (HP)
|
99% |
85711
660.4 IPS |
|
Depth Estimation (Q)
|
85% |
108142
845.1 IPS |
|
Style Transfer (SP)
|
100% |
18614
23.9 IPS |
|
Style Transfer (HP)
|
100% |
199742
256.8 IPS |
|
Style Transfer (Q)
|
96% |
192219
248.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4070
150.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
40428
1.49 KIPS |
|
Image Super-Resolution (Q)
|
99% |
48485
1.79 KIPS |
|
Text Classification (SP)
|
100% |
2171
2.90 KIPS |
|
Text Classification (HP)
|
100% |
3593
4.80 KIPS |
|
Text Classification (Q)
|
93% |
3583
4.81 KIPS |
|
Machine Translation (SP)
|
100% |
3501
60.3 IPS |
|
Machine Translation (HP)
|
100% |
6824
117.5 IPS |
|
Machine Translation (Q)
|
98% |
7012
121.2 IPS |