User | Leomotors |
Upload Date | August 19 2024 01:22 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,5 |
Motherboard | Mac14,5 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.47 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
5747
1.07 KIPS |
|
Image Classification (HP)
|
100% |
5978
1.11 KIPS |
|
Image Classification (Q)
|
99% |
5273
983.6 IPS |
|
Image Segmentation (SP)
|
100% |
10675
173.1 IPS |
|
Image Segmentation (HP)
|
100% |
10584
171.6 IPS |
|
Image Segmentation (Q)
|
100% |
10206
165.4 IPS |
|
Pose Estimation (SP)
|
100% |
60499
70.6 IPS |
|
Pose Estimation (HP)
|
100% |
63484
74.1 IPS |
|
Pose Estimation (Q)
|
96% |
56256
65.9 IPS |
|
Object Detection (SP)
|
100% |
5578
442.4 IPS |
|
Object Detection (HP)
|
100% |
5876
466.1 IPS |
|
Object Detection (Q)
|
92% |
4906
391.6 IPS |
|
Face Detection (SP)
|
100% |
21561
256.2 IPS |
|
Face Detection (HP)
|
100% |
22175
263.5 IPS |
|
Face Detection (Q)
|
100% |
15807
187.8 IPS |
|
Depth Estimation (SP)
|
100% |
28320
218.2 IPS |
|
Depth Estimation (HP)
|
99% |
28850
222.3 IPS |
|
Depth Estimation (Q)
|
97% |
28533
220.6 IPS |
|
Style Transfer (SP)
|
100% |
112233
144.3 IPS |
|
Style Transfer (HP)
|
100% |
125970
161.9 IPS |
|
Style Transfer (Q)
|
100% |
124051
159.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
20039
739.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
20526
757.9 IPS |
|
Image Super-Resolution (Q)
|
98% |
15021
556.5 IPS |
|
Text Classification (SP)
|
100% |
328
437.6 IPS |
|
Text Classification (HP)
|
100% |
782
1.04 KIPS |
|
Text Classification (Q)
|
93% |
779
1.05 KIPS |
|
Machine Translation (SP)
|
100% |
1042
18.0 IPS |
|
Machine Translation (HP)
|
100% |
1062
18.3 IPS |
|
Machine Translation (Q)
|
98% |
1090
18.8 IPS |