User | jwillemsen |
Upload Date | September 06 2024 07:57 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Pro |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Pro (16-inch, 2021) |
Model ID | MacBookPro18,1 |
Motherboard | MacBookPro18,1 |
CPU Information | |
---|---|
Name | Apple M1 Pro |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Pro |
Base Frequency | 3.21 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
908
168.9 IPS |
|
Image Classification (HP)
|
100% |
7288
1.36 KIPS |
|
Image Classification (Q)
|
96% |
6602
1.23 KIPS |
|
Image Segmentation (SP)
|
100% |
673
10.9 IPS |
|
Image Segmentation (HP)
|
100% |
3876
62.8 IPS |
|
Image Segmentation (Q)
|
99% |
481
7.79 IPS |
|
Pose Estimation (SP)
|
100% |
9343
10.9 IPS |
|
Pose Estimation (HP)
|
100% |
69162
80.7 IPS |
|
Pose Estimation (Q)
|
95% |
65491
76.8 IPS |
|
Object Detection (SP)
|
100% |
1011
80.2 IPS |
|
Object Detection (HP)
|
99% |
7577
602.8 IPS |
|
Object Detection (Q)
|
93% |
7324
584.4 IPS |
|
Face Detection (SP)
|
100% |
1782
21.2 IPS |
|
Face Detection (HP)
|
100% |
11556
137.3 IPS |
|
Face Detection (Q)
|
100% |
11626
138.1 IPS |
|
Depth Estimation (SP)
|
100% |
3456
26.6 IPS |
|
Depth Estimation (HP)
|
99% |
46787
360.5 IPS |
|
Depth Estimation (Q)
|
85% |
54540
426.2 IPS |
|
Style Transfer (SP)
|
100% |
12190
15.7 IPS |
|
Style Transfer (HP)
|
100% |
117227
150.7 IPS |
|
Style Transfer (Q)
|
96% |
115156
148.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
2584
95.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
18882
697.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
23544
869.4 IPS |
|
Text Classification (SP)
|
100% |
586
781.7 IPS |
|
Text Classification (HP)
|
100% |
3418
4.56 KIPS |
|
Text Classification (Q)
|
93% |
3339
4.48 KIPS |
|
Machine Translation (SP)
|
100% |
1559
26.8 IPS |
|
Machine Translation (HP)
|
100% |
2129
36.7 IPS |
|
Machine Translation (Q)
|
98% |
2137
36.9 IPS |