User | mingchang137 |
Upload Date | January 05 2025 09:27 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
Model | MacBook Pro (16-inch, 2024) |
Model ID | Mac16,7 |
Motherboard | Mac16,7 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.49 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2074
385.7 IPS |
|
Image Classification (HP)
|
100% |
17744
3.30 KIPS |
|
Image Classification (Q)
|
97% |
22028
4.11 KIPS |
|
Image Segmentation (SP)
|
100% |
2462
39.9 IPS |
|
Image Segmentation (HP)
|
100% |
23258
377.0 IPS |
|
Image Segmentation (Q)
|
99% |
32206
522.1 IPS |
|
Pose Estimation (SP)
|
100% |
18958
22.1 IPS |
|
Pose Estimation (HP)
|
100% |
123402
144.0 IPS |
|
Pose Estimation (Q)
|
95% |
230812
270.5 IPS |
|
Object Detection (SP)
|
100% |
2479
196.7 IPS |
|
Object Detection (HP)
|
100% |
19628
1.56 KIPS |
|
Object Detection (Q)
|
91% |
23572
1.88 KIPS |
|
Face Detection (SP)
|
100% |
4490
53.3 IPS |
|
Face Detection (HP)
|
100% |
40018
475.5 IPS |
|
Face Detection (Q)
|
100% |
63754
757.5 IPS |
|
Depth Estimation (SP)
|
100% |
8810
67.9 IPS |
|
Depth Estimation (HP)
|
99% |
113136
871.6 IPS |
|
Depth Estimation (Q)
|
85% |
179876
1.41 KIPS |
|
Style Transfer (SP)
|
100% |
35209
45.3 IPS |
|
Style Transfer (HP)
|
100% |
237055
304.7 IPS |
|
Style Transfer (Q)
|
96% |
304367
392.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
7036
259.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
46652
1.72 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77224
2.85 KIPS |
|
Text Classification (SP)
|
100% |
2949
3.94 KIPS |
|
Text Classification (HP)
|
100% |
5197
6.94 KIPS |
|
Text Classification (Q)
|
93% |
4944
6.64 KIPS |
|
Machine Translation (SP)
|
100% |
5764
99.3 IPS |
|
Machine Translation (HP)
|
100% |
16453
283.4 IPS |
|
Machine Translation (Q)
|
98% |
16337
282.3 IPS |