User | andriyfedorov |
Upload Date | October 08 2024 04:05 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 |
System Information | |
---|---|
Operating System | macOS 15.0.1 (Build 24A348) |
Model | MacBook Air (2022) |
Model ID | Mac14,2 |
Motherboard | Mac14,2 |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M2 |
Base Frequency | 3.46 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3322
617.7 IPS |
|
Image Classification (HP)
|
100% |
3162
588.1 IPS |
|
Image Classification (Q)
|
97% |
2443
456.0 IPS |
|
Image Segmentation (SP)
|
100% |
3680
59.7 IPS |
|
Image Segmentation (HP)
|
100% |
4261
69.1 IPS |
|
Image Segmentation (Q)
|
99% |
4178
67.7 IPS |
|
Pose Estimation (SP)
|
100% |
19880
23.2 IPS |
|
Pose Estimation (HP)
|
100% |
21287
24.8 IPS |
|
Pose Estimation (Q)
|
95% |
19568
22.9 IPS |
|
Object Detection (SP)
|
100% |
3150
249.9 IPS |
|
Object Detection (HP)
|
100% |
3200
253.8 IPS |
|
Object Detection (Q)
|
91% |
2475
197.7 IPS |
|
Face Detection (SP)
|
100% |
9391
111.6 IPS |
|
Face Detection (HP)
|
100% |
10286
122.2 IPS |
|
Face Detection (Q)
|
100% |
7052
83.8 IPS |
|
Depth Estimation (SP)
|
100% |
13636
105.1 IPS |
|
Depth Estimation (HP)
|
99% |
14494
111.7 IPS |
|
Depth Estimation (Q)
|
85% |
11370
88.9 IPS |
|
Style Transfer (SP)
|
100% |
36170
46.5 IPS |
|
Style Transfer (HP)
|
100% |
40220
51.7 IPS |
|
Style Transfer (Q)
|
96% |
37444
48.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
7903
291.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
8300
306.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
6230
230.0 IPS |
|
Text Classification (SP)
|
100% |
2228
2.97 KIPS |
|
Text Classification (HP)
|
100% |
3807
5.08 KIPS |
|
Text Classification (Q)
|
93% |
3713
4.98 KIPS |
|
Machine Translation (SP)
|
100% |
651
11.2 IPS |
|
Machine Translation (HP)
|
100% |
621
10.7 IPS |
|
Machine Translation (Q)
|
98% |
895
15.5 IPS |