User | mitgeek |
Upload Date | September 10 2024 02:43 AM |
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 (14-inch, 2021) |
Model ID | MacBookPro18,3 |
Motherboard | MacBookPro18,3 |
CPU Information | |
---|---|
Name | Apple M1 Pro |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Pro |
Base Frequency | 3.22 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
933
173.6 IPS |
|
Image Classification (HP)
|
100% |
7128
1.33 KIPS |
|
Image Classification (Q)
|
96% |
6420
1.20 KIPS |
|
Image Segmentation (SP)
|
100% |
663
10.7 IPS |
|
Image Segmentation (HP)
|
100% |
3849
62.4 IPS |
|
Image Segmentation (Q)
|
99% |
469
7.60 IPS |
|
Pose Estimation (SP)
|
100% |
10153
11.8 IPS |
|
Pose Estimation (HP)
|
100% |
69274
80.8 IPS |
|
Pose Estimation (Q)
|
95% |
65267
76.5 IPS |
|
Object Detection (SP)
|
100% |
1014
80.4 IPS |
|
Object Detection (HP)
|
99% |
7377
586.9 IPS |
|
Object Detection (Q)
|
93% |
7256
579.0 IPS |
|
Face Detection (SP)
|
100% |
1871
22.2 IPS |
|
Face Detection (HP)
|
100% |
9738
115.7 IPS |
|
Face Detection (Q)
|
100% |
11642
138.3 IPS |
|
Depth Estimation (SP)
|
100% |
3605
27.8 IPS |
|
Depth Estimation (HP)
|
99% |
46408
357.5 IPS |
|
Depth Estimation (Q)
|
85% |
54832
428.5 IPS |
|
Style Transfer (SP)
|
100% |
12178
15.7 IPS |
|
Style Transfer (HP)
|
100% |
117165
150.6 IPS |
|
Style Transfer (Q)
|
96% |
114579
147.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
2429
89.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
18814
694.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
23267
859.2 IPS |
|
Text Classification (SP)
|
100% |
383
511.1 IPS |
|
Text Classification (HP)
|
100% |
3503
4.68 KIPS |
|
Text Classification (Q)
|
93% |
3442
4.62 KIPS |
|
Machine Translation (SP)
|
100% |
1276
22.0 IPS |
|
Machine Translation (HP)
|
100% |
2136
36.8 IPS |
|
Machine Translation (Q)
|
98% |
2117
36.6 IPS |