User | kunalkapoor |
Upload Date | November 09 2024 07:01 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
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% |
4006
745.1 IPS |
|
Image Classification (HP)
|
100% |
4027
748.8 IPS |
|
Image Classification (Q)
|
97% |
3468
647.1 IPS |
|
Image Segmentation (SP)
|
100% |
6306
102.2 IPS |
|
Image Segmentation (HP)
|
100% |
6437
104.4 IPS |
|
Image Segmentation (Q)
|
99% |
6420
104.1 IPS |
|
Pose Estimation (SP)
|
100% |
32941
38.4 IPS |
|
Pose Estimation (HP)
|
100% |
34892
40.7 IPS |
|
Pose Estimation (Q)
|
95% |
32388
38.0 IPS |
|
Object Detection (SP)
|
100% |
3921
311.0 IPS |
|
Object Detection (HP)
|
100% |
4126
327.3 IPS |
|
Object Detection (Q)
|
91% |
3409
272.4 IPS |
|
Face Detection (SP)
|
100% |
13944
165.7 IPS |
|
Face Detection (HP)
|
100% |
14700
174.7 IPS |
|
Face Detection (Q)
|
100% |
10473
124.4 IPS |
|
Depth Estimation (SP)
|
100% |
19788
152.5 IPS |
|
Depth Estimation (HP)
|
99% |
20533
158.2 IPS |
|
Depth Estimation (Q)
|
85% |
17331
135.4 IPS |
|
Style Transfer (SP)
|
100% |
53812
69.2 IPS |
|
Style Transfer (HP)
|
100% |
63831
82.1 IPS |
|
Style Transfer (Q)
|
96% |
59897
77.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
10767
397.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
11298
417.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
8831
326.1 IPS |
|
Text Classification (SP)
|
100% |
2289
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3987
5.32 KIPS |
|
Text Classification (Q)
|
93% |
3892
5.22 KIPS |
|
Machine Translation (SP)
|
100% |
1246
21.5 IPS |
|
Machine Translation (HP)
|
100% |
994
17.1 IPS |
|
Machine Translation (Q)
|
98% |
1116
19.3 IPS |