Upload Date | July 19 2024 03:51 AM |
Views | 4 |
System Information | |
---|---|
Operating System | macOS 14.5 (Build 23F79) |
Model | Mac15,13 |
Model ID | Mac15,13 |
Motherboard | Mac15,13 |
CPU Information | |
---|---|
Name | Apple M3 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M3 |
Base Frequency | 4.05 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
L1 Instruction Cache | 128 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 4.00 MB x 1 |
Memory Information | |
---|---|
Size | 16.00 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
4130
772.9 IPS |
|
Image Classification (F16)
|
100% |
4374
818.6 IPS |
|
Image Classification (I8)
|
99% |
3901
730.0 IPS |
|
Image Segmentation (F32)
|
100% |
1734
29.0 IPS |
|
Image Segmentation (F16)
|
100% |
1906
31.8 IPS |
|
Image Segmentation (I8)
|
100% |
1795
30.0 IPS |
|
Pose Estimation (F32)
|
100% |
23684
28.7 IPS |
|
Pose Estimation (F16)
|
100% |
25603
31.0 IPS |
|
Pose Estimation (I8)
|
100% |
25001
30.3 IPS |
|
Object Detection (F32)
|
100% |
2464
183.9 IPS |
|
Object Detection (F16)
|
100% |
3600
268.7 IPS |
|
Object Detection (I8)
|
97% |
2872
214.4 IPS |
|
Face Detection (F32)
|
100% |
10582
125.8 IPS |
|
Face Detection (F16)
|
98% |
13578
161.4 IPS |
|
Face Detection (I8)
|
97% |
13127
156.1 IPS |
|
Depth Estimation (F32)
|
100% |
15500
120.2 IPS |
|
Depth Estimation (F16)
|
100% |
20338
157.7 IPS |
|
Depth Estimation (I8)
|
37% |
18653
144.7 IPS |
|
Style Transfer (F32)
|
100% |
50362
66.2 IPS |
|
Style Transfer (F16)
|
100% |
58320
76.7 IPS |
|
Style Transfer (I8)
|
100% |
58181
76.5 IPS |
|
Image Super-Resolution (F32)
|
100% |
6950
248.2 IPS |
|
Image Super-Resolution (F16)
|
100% |
7293
260.5 IPS |
|
Image Super-Resolution (I8)
|
100% |
7058
252.1 IPS |
|
Text Classification (F32)
|
100% |
1355
1.95 KIPS |
|
Text Classification (F16)
|
100% |
671
964.3 IPS |
|
Text Classification (I8)
|
96% |
668
960.6 IPS |
|
Machine Translation (F32)
|
100% |
707
13.0 IPS |
|
Machine Translation (F16)
|
100% |
760
14.0 IPS |
|
Machine Translation (I8)
|
99% |
663
12.2 IPS |