User | zedkiel |
Upload Date | August 17 2024 07:24 AM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 15.0 (Build 24A5320a) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,9 |
Motherboard | Mac14,9 |
CPU Information | |
---|---|
Name | Apple M2 Pro |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M2 Pro |
Base Frequency | 3.47 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1381
256.9 IPS |
|
Image Classification (HP)
|
100% |
13508
2.51 KIPS |
|
Image Classification (Q)
|
99% |
15694
2.93 KIPS |
|
Image Segmentation (SP)
|
100% |
1667
27.0 IPS |
|
Image Segmentation (HP)
|
100% |
9213
149.3 IPS |
|
Image Segmentation (Q)
|
100% |
9149
148.3 IPS |
|
Pose Estimation (SP)
|
100% |
12664
14.8 IPS |
|
Pose Estimation (HP)
|
100% |
102874
120.0 IPS |
|
Pose Estimation (Q)
|
94% |
97833
114.8 IPS |
|
Object Detection (SP)
|
100% |
1681
133.3 IPS |
|
Object Detection (HP)
|
99% |
13718
1.09 KIPS |
|
Object Detection (Q)
|
91% |
16367
1.31 KIPS |
|
Face Detection (SP)
|
100% |
3626
43.1 IPS |
|
Face Detection (HP)
|
100% |
23744
282.1 IPS |
|
Face Detection (Q)
|
100% |
36631
435.3 IPS |
|
Depth Estimation (SP)
|
100% |
6333
48.8 IPS |
|
Depth Estimation (HP)
|
99% |
73630
567.3 IPS |
|
Depth Estimation (Q)
|
97% |
82258
636.0 IPS |
|
Style Transfer (SP)
|
100% |
24691
31.7 IPS |
|
Style Transfer (HP)
|
100% |
156071
200.6 IPS |
|
Style Transfer (Q)
|
100% |
157159
202.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5064
187.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
40736
1.50 KIPS |
|
Image Super-Resolution (Q)
|
98% |
47692
1.77 KIPS |
|
Text Classification (SP)
|
100% |
2248
3.00 KIPS |
|
Text Classification (HP)
|
100% |
3827
5.11 KIPS |
|
Text Classification (Q)
|
93% |
3819
5.13 KIPS |
|
Machine Translation (SP)
|
100% |
4535
78.1 IPS |
|
Machine Translation (HP)
|
100% |
2304
39.7 IPS |
|
Machine Translation (Q)
|
98% |
2299
39.7 IPS |