User | dokidoki0802 |
Upload Date | August 18 2024 02:19 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5024e) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,7 |
Motherboard | Mac15,7 |
CPU Information | |
---|---|
Name | Apple M3 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M3 Pro |
Base Frequency | 3.84 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1413
262.9 IPS |
|
Image Classification (HP)
|
100% |
15196
2.83 KIPS |
|
Image Classification (Q)
|
99% |
17099
3.19 KIPS |
|
Image Segmentation (SP)
|
100% |
1707
27.7 IPS |
|
Image Segmentation (HP)
|
100% |
13792
223.6 IPS |
|
Image Segmentation (Q)
|
100% |
13733
222.6 IPS |
|
Pose Estimation (SP)
|
100% |
8147
9.51 IPS |
|
Pose Estimation (HP)
|
100% |
111943
130.6 IPS |
|
Pose Estimation (Q)
|
94% |
110807
130.0 IPS |
|
Object Detection (SP)
|
100% |
1671
132.5 IPS |
|
Object Detection (HP)
|
100% |
15389
1.22 KIPS |
|
Object Detection (Q)
|
91% |
19029
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3300
39.2 IPS |
|
Face Detection (HP)
|
100% |
24605
292.4 IPS |
|
Face Detection (Q)
|
100% |
35098
417.0 IPS |
|
Depth Estimation (SP)
|
100% |
6553
50.5 IPS |
|
Depth Estimation (HP)
|
99% |
78550
605.2 IPS |
|
Depth Estimation (Q)
|
97% |
88099
681.2 IPS |
|
Style Transfer (SP)
|
100% |
19788
25.4 IPS |
|
Style Transfer (HP)
|
100% |
163201
209.8 IPS |
|
Style Transfer (Q)
|
100% |
163911
210.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4819
177.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
44025
1.63 KIPS |
|
Image Super-Resolution (Q)
|
98% |
52773
1.96 KIPS |
|
Text Classification (SP)
|
100% |
2566
3.43 KIPS |
|
Text Classification (HP)
|
100% |
4433
5.92 KIPS |
|
Text Classification (Q)
|
93% |
4410
5.92 KIPS |
|
Machine Translation (SP)
|
100% |
3148
54.2 IPS |
|
Machine Translation (HP)
|
100% |
2483
42.8 IPS |
|
Machine Translation (Q)
|
98% |
2461
42.5 IPS |