User | Merlion |
Upload Date | December 24 2024 02:35 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 Pro |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B91) |
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 | 3.22 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3847
715.5 IPS |
|
Image Classification (HP)
|
100% |
3927
730.2 IPS |
|
Image Classification (Q)
|
97% |
3230
602.8 IPS |
|
Image Segmentation (SP)
|
100% |
5980
96.9 IPS |
|
Image Segmentation (HP)
|
100% |
5983
97.0 IPS |
|
Image Segmentation (Q)
|
99% |
5894
95.5 IPS |
|
Pose Estimation (SP)
|
100% |
29934
34.9 IPS |
|
Pose Estimation (HP)
|
100% |
31386
36.6 IPS |
|
Pose Estimation (Q)
|
95% |
29195
34.2 IPS |
|
Object Detection (SP)
|
100% |
3757
298.0 IPS |
|
Object Detection (HP)
|
100% |
3966
314.6 IPS |
|
Object Detection (Q)
|
91% |
3307
264.2 IPS |
|
Face Detection (SP)
|
100% |
13366
158.8 IPS |
|
Face Detection (HP)
|
100% |
13587
161.4 IPS |
|
Face Detection (Q)
|
100% |
9594
114.0 IPS |
|
Depth Estimation (SP)
|
100% |
17675
136.2 IPS |
|
Depth Estimation (HP)
|
99% |
18209
140.3 IPS |
|
Depth Estimation (Q)
|
85% |
14997
117.2 IPS |
|
Style Transfer (SP)
|
100% |
50347
64.7 IPS |
|
Style Transfer (HP)
|
100% |
59280
76.2 IPS |
|
Style Transfer (Q)
|
96% |
55287
71.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
10680
394.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
10997
406.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
8839
326.4 IPS |
|
Text Classification (SP)
|
100% |
2334
3.12 KIPS |
|
Text Classification (HP)
|
100% |
4104
5.48 KIPS |
|
Text Classification (Q)
|
93% |
3955
5.31 KIPS |
|
Machine Translation (SP)
|
100% |
1070
18.4 IPS |
|
Machine Translation (HP)
|
100% |
1522
26.2 IPS |
|
Machine Translation (Q)
|
98% |
1022
17.7 IPS |