User | zedkiel |
Upload Date | August 21 2024 04:01 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 15.0 (Build 24A5327a) |
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% |
1380
256.7 IPS |
|
Image Classification (HP)
|
100% |
13206
2.46 KIPS |
|
Image Classification (Q)
|
99% |
15439
2.88 KIPS |
|
Image Segmentation (SP)
|
100% |
1671
27.1 IPS |
|
Image Segmentation (HP)
|
100% |
9235
149.7 IPS |
|
Image Segmentation (Q)
|
100% |
9150
148.3 IPS |
|
Pose Estimation (SP)
|
100% |
12727
14.8 IPS |
|
Pose Estimation (HP)
|
100% |
102791
119.9 IPS |
|
Pose Estimation (Q)
|
94% |
97867
114.8 IPS |
|
Object Detection (SP)
|
100% |
1665
132.1 IPS |
|
Object Detection (HP)
|
99% |
13708
1.09 KIPS |
|
Object Detection (Q)
|
91% |
16501
1.32 KIPS |
|
Face Detection (SP)
|
100% |
3535
42.0 IPS |
|
Face Detection (HP)
|
100% |
23666
281.2 IPS |
|
Face Detection (Q)
|
100% |
36890
438.3 IPS |
|
Depth Estimation (SP)
|
100% |
6316
48.7 IPS |
|
Depth Estimation (HP)
|
99% |
73680
567.7 IPS |
|
Depth Estimation (Q)
|
97% |
82200
635.6 IPS |
|
Style Transfer (SP)
|
100% |
24890
32.0 IPS |
|
Style Transfer (HP)
|
100% |
156131
200.7 IPS |
|
Style Transfer (Q)
|
100% |
156213
200.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5092
188.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
40512
1.50 KIPS |
|
Image Super-Resolution (Q)
|
98% |
47523
1.76 KIPS |
|
Text Classification (SP)
|
100% |
2261
3.02 KIPS |
|
Text Classification (HP)
|
100% |
3830
5.11 KIPS |
|
Text Classification (Q)
|
93% |
3812
5.12 KIPS |
|
Machine Translation (SP)
|
100% |
4530
78.0 IPS |
|
Machine Translation (HP)
|
100% |
2316
39.9 IPS |
|
Machine Translation (Q)
|
98% |
2288
39.5 IPS |