User | afisch |
Upload Date | August 18 2024 07:26 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5024e) |
Model | MacBook Pro (14-inch, 2021) |
Model ID | MacBookPro18,3 |
Motherboard | MacBookPro18,3 |
CPU Information | |
---|---|
Name | Apple M1 Pro |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M1 Pro |
Base Frequency | 2.44 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1168
217.3 IPS |
|
Image Classification (HP)
|
100% |
6101
1.13 KIPS |
|
Image Classification (Q)
|
99% |
6295
1.17 KIPS |
|
Image Segmentation (SP)
|
100% |
1393
22.6 IPS |
|
Image Segmentation (HP)
|
100% |
5594
90.7 IPS |
|
Image Segmentation (Q)
|
100% |
5618
91.1 IPS |
|
Pose Estimation (SP)
|
100% |
9421
11.0 IPS |
|
Pose Estimation (HP)
|
100% |
67782
79.1 IPS |
|
Pose Estimation (Q)
|
94% |
63125
74.0 IPS |
|
Object Detection (SP)
|
100% |
1380
109.4 IPS |
|
Object Detection (HP)
|
99% |
6563
522.1 IPS |
|
Object Detection (Q)
|
91% |
6633
530.0 IPS |
|
Face Detection (SP)
|
100% |
2873
34.1 IPS |
|
Face Detection (HP)
|
100% |
10886
129.3 IPS |
|
Face Detection (Q)
|
100% |
12078
143.5 IPS |
|
Depth Estimation (SP)
|
100% |
5027
38.7 IPS |
|
Depth Estimation (HP)
|
99% |
43793
337.4 IPS |
|
Depth Estimation (Q)
|
97% |
46806
361.9 IPS |
|
Style Transfer (SP)
|
100% |
19371
24.9 IPS |
|
Style Transfer (HP)
|
100% |
113206
145.5 IPS |
|
Style Transfer (Q)
|
100% |
118085
151.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
3871
142.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
24126
890.9 IPS |
|
Image Super-Resolution (Q)
|
98% |
25968
962.1 IPS |
|
Text Classification (SP)
|
100% |
1885
2.52 KIPS |
|
Text Classification (HP)
|
100% |
3168
4.23 KIPS |
|
Text Classification (Q)
|
93% |
3120
4.19 KIPS |
|
Machine Translation (SP)
|
100% |
2923
50.3 IPS |
|
Machine Translation (HP)
|
100% |
1767
30.4 IPS |
|
Machine Translation (Q)
|
98% |
1753
30.3 IPS |