User | dglow |
Upload Date | April 05 2025 02:06 AM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Pro |
System Information | |
---|---|
Operating System | macOS 15.4 (Build 24E248) |
Model | MacBook Pro (14-inch, 2021) |
Model ID | MacBookPro18,3 |
Motherboard | MacBookPro18,3 |
CPU Information | |
---|---|
Name | Apple M1 Pro |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Pro |
Base Frequency | 3.04 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1302
242.0 IPS |
|
Image Classification (HP)
|
100% |
6530
1.21 KIPS |
|
Image Classification (Q)
|
96% |
6330
1.18 KIPS |
|
Image Segmentation (SP)
|
100% |
1506
24.4 IPS |
|
Image Segmentation (HP)
|
100% |
9113
147.7 IPS |
|
Image Segmentation (Q)
|
99% |
9755
158.1 IPS |
|
Pose Estimation (SP)
|
100% |
10299
12.0 IPS |
|
Pose Estimation (HP)
|
100% |
71603
83.5 IPS |
|
Pose Estimation (Q)
|
95% |
67797
79.5 IPS |
|
Object Detection (SP)
|
100% |
1492
118.4 IPS |
|
Object Detection (HP)
|
99% |
7405
589.0 IPS |
|
Object Detection (Q)
|
91% |
7072
565.1 IPS |
|
Face Detection (SP)
|
100% |
2967
35.3 IPS |
|
Face Detection (HP)
|
100% |
15380
182.7 IPS |
|
Face Detection (Q)
|
100% |
14718
174.9 IPS |
|
Depth Estimation (SP)
|
100% |
5502
42.4 IPS |
|
Depth Estimation (HP)
|
99% |
51234
394.7 IPS |
|
Depth Estimation (Q)
|
85% |
53347
416.9 IPS |
|
Style Transfer (SP)
|
100% |
21166
27.2 IPS |
|
Style Transfer (HP)
|
100% |
120546
155.0 IPS |
|
Style Transfer (Q)
|
96% |
116320
150.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4366
161.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
25761
951.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
27845
1.03 KIPS |
|
Text Classification (SP)
|
100% |
2252
3.01 KIPS |
|
Text Classification (HP)
|
100% |
3923
5.24 KIPS |
|
Text Classification (Q)
|
93% |
3899
5.23 KIPS |
|
Machine Translation (SP)
|
100% |
2898
49.9 IPS |
|
Machine Translation (HP)
|
100% |
3304
56.9 IPS |
|
Machine Translation (Q)
|
98% |
3368
58.2 IPS |