User | RafaelReverberi |
Upload Date | November 10 2024 08:59 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C5073e) |
Model | MacBook Pro (16-inch, 2021) |
Model ID | MacBookPro18,2 |
Motherboard | MacBookPro18,2 |
CPU Information | |
---|---|
Name | Apple M1 Max |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Max |
Base Frequency | 3.22 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1340
249.1 IPS |
|
Image Classification (HP)
|
100% |
6581
1.22 KIPS |
|
Image Classification (Q)
|
96% |
6313
1.18 KIPS |
|
Image Segmentation (SP)
|
100% |
1596
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
9693
157.1 IPS |
|
Image Segmentation (Q)
|
99% |
10274
166.6 IPS |
|
Pose Estimation (SP)
|
100% |
11101
13.0 IPS |
|
Pose Estimation (HP)
|
100% |
69973
81.6 IPS |
|
Pose Estimation (Q)
|
95% |
66742
78.2 IPS |
|
Object Detection (SP)
|
100% |
1586
125.8 IPS |
|
Object Detection (HP)
|
99% |
7772
618.2 IPS |
|
Object Detection (Q)
|
91% |
7253
579.5 IPS |
|
Face Detection (SP)
|
100% |
3367
40.0 IPS |
|
Face Detection (HP)
|
100% |
16086
191.1 IPS |
|
Face Detection (Q)
|
100% |
14866
176.6 IPS |
|
Depth Estimation (SP)
|
100% |
5825
44.9 IPS |
|
Depth Estimation (HP)
|
99% |
50607
389.9 IPS |
|
Depth Estimation (Q)
|
85% |
52653
411.5 IPS |
|
Style Transfer (SP)
|
100% |
22203
28.5 IPS |
|
Style Transfer (HP)
|
100% |
119871
154.1 IPS |
|
Style Transfer (Q)
|
96% |
115771
149.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4308
159.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
25251
932.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
27184
1.00 KIPS |
|
Text Classification (SP)
|
100% |
2229
2.98 KIPS |
|
Text Classification (HP)
|
100% |
3753
5.01 KIPS |
|
Text Classification (Q)
|
93% |
3751
5.03 KIPS |
|
Machine Translation (SP)
|
100% |
3389
58.4 IPS |
|
Machine Translation (HP)
|
100% |
3293
56.7 IPS |
|
Machine Translation (Q)
|
98% |
3352
57.9 IPS |