User | mcolsen |
Upload Date | December 17 2024 11:48 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Pro |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
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% |
1346
250.4 IPS |
|
Image Classification (HP)
|
100% |
6350
1.18 KIPS |
|
Image Classification (Q)
|
96% |
6235
1.16 KIPS |
|
Image Segmentation (SP)
|
100% |
1596
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
9463
153.4 IPS |
|
Image Segmentation (Q)
|
99% |
10168
164.8 IPS |
|
Pose Estimation (SP)
|
100% |
11216
13.1 IPS |
|
Pose Estimation (HP)
|
100% |
68902
80.4 IPS |
|
Pose Estimation (Q)
|
95% |
64969
76.1 IPS |
|
Object Detection (SP)
|
100% |
1582
125.5 IPS |
|
Object Detection (HP)
|
99% |
7491
595.9 IPS |
|
Object Detection (Q)
|
91% |
7023
561.1 IPS |
|
Face Detection (SP)
|
100% |
3202
38.0 IPS |
|
Face Detection (HP)
|
100% |
14818
176.1 IPS |
|
Face Detection (Q)
|
100% |
13929
165.5 IPS |
|
Depth Estimation (SP)
|
100% |
5940
45.8 IPS |
|
Depth Estimation (HP)
|
99% |
49548
381.7 IPS |
|
Depth Estimation (Q)
|
85% |
52049
406.7 IPS |
|
Style Transfer (SP)
|
100% |
22317
28.7 IPS |
|
Style Transfer (HP)
|
100% |
119477
153.6 IPS |
|
Style Transfer (Q)
|
96% |
115469
149.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4319
159.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
25756
951.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
28008
1.03 KIPS |
|
Text Classification (SP)
|
100% |
2267
3.03 KIPS |
|
Text Classification (HP)
|
100% |
3964
5.29 KIPS |
|
Text Classification (Q)
|
93% |
4005
5.38 KIPS |
|
Machine Translation (SP)
|
100% |
3431
59.1 IPS |
|
Machine Translation (HP)
|
100% |
3304
56.9 IPS |
|
Machine Translation (Q)
|
98% |
3382
58.5 IPS |