User | M1_MACBOOK |
Upload Date | November 16 2024 12:33 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | macOS 14.7.1 (Build 23H222) |
Model | MacBook Air (Late 2020) |
Model ID | MacBookAir10,1 |
Motherboard | MacBookAir10,1 |
CPU Information | |
---|---|
Name | Apple M1 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M1 |
Base Frequency | 1.10 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 8.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
245
45.5 IPS |
|
Image Classification (HP)
|
100% |
2630
489.2 IPS |
|
Image Classification (Q)
|
96% |
2576
481.1 IPS |
|
Image Segmentation (SP)
|
100% |
165
2.68 IPS |
|
Image Segmentation (HP)
|
100% |
1964
31.8 IPS |
|
Image Segmentation (Q)
|
99% |
135
2.18 IPS |
|
Pose Estimation (SP)
|
100% |
1301
1.52 IPS |
|
Pose Estimation (HP)
|
100% |
26819
31.3 IPS |
|
Pose Estimation (Q)
|
95% |
26064
30.5 IPS |
|
Object Detection (SP)
|
100% |
258
20.5 IPS |
|
Object Detection (HP)
|
99% |
2848
226.5 IPS |
|
Object Detection (Q)
|
93% |
2784
222.1 IPS |
|
Face Detection (SP)
|
100% |
504
5.98 IPS |
|
Face Detection (HP)
|
100% |
5532
65.7 IPS |
|
Face Detection (Q)
|
100% |
5011
59.5 IPS |
|
Depth Estimation (SP)
|
100% |
1163
8.96 IPS |
|
Depth Estimation (HP)
|
99% |
19401
149.5 IPS |
|
Depth Estimation (Q)
|
85% |
21649
169.2 IPS |
|
Style Transfer (SP)
|
100% |
2632
3.38 IPS |
|
Style Transfer (HP)
|
100% |
53143
68.3 IPS |
|
Style Transfer (Q)
|
96% |
50208
64.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
799
29.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
8517
314.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
9369
345.9 IPS |
|
Text Classification (SP)
|
100% |
152
202.6 IPS |
|
Text Classification (HP)
|
100% |
1671
2.23 KIPS |
|
Text Classification (Q)
|
93% |
1531
2.06 KIPS |
|
Machine Translation (SP)
|
100% |
382
6.58 IPS |
|
Machine Translation (HP)
|
100% |
696
12.0 IPS |
|
Machine Translation (Q)
|
98% |
663
11.5 IPS |