User | HarshKarwal |
Upload Date | October 04 2024 08:45 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5055e) |
Model | MacBook Pro (14-inch, 2021) |
Model ID | MacBookPro18,3 |
Motherboard | MacBookPro18,3 |
CPU Information | |
---|---|
Name | Apple M1 Pro |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M1 Pro |
Base Frequency | 3.21 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3582
666.1 IPS |
|
Image Classification (HP)
|
100% |
3675
683.5 IPS |
|
Image Classification (Q)
|
97% |
3039
567.1 IPS |
|
Image Segmentation (SP)
|
100% |
5788
93.8 IPS |
|
Image Segmentation (HP)
|
100% |
5843
94.7 IPS |
|
Image Segmentation (Q)
|
99% |
5776
93.6 IPS |
|
Pose Estimation (SP)
|
100% |
29687
34.6 IPS |
|
Pose Estimation (HP)
|
100% |
31201
36.4 IPS |
|
Pose Estimation (Q)
|
95% |
28949
33.9 IPS |
|
Object Detection (SP)
|
100% |
3606
286.0 IPS |
|
Object Detection (HP)
|
100% |
3814
302.5 IPS |
|
Object Detection (Q)
|
91% |
3164
252.8 IPS |
|
Face Detection (SP)
|
100% |
12912
153.4 IPS |
|
Face Detection (HP)
|
100% |
13269
157.7 IPS |
|
Face Detection (Q)
|
100% |
9464
112.5 IPS |
|
Depth Estimation (SP)
|
100% |
17136
132.0 IPS |
|
Depth Estimation (HP)
|
99% |
17539
135.1 IPS |
|
Depth Estimation (Q)
|
85% |
14608
114.2 IPS |
|
Style Transfer (SP)
|
100% |
49732
63.9 IPS |
|
Style Transfer (HP)
|
100% |
58575
75.3 IPS |
|
Style Transfer (Q)
|
96% |
54617
70.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
10276
379.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
10610
391.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
8348
308.3 IPS |
|
Text Classification (SP)
|
100% |
2212
2.95 KIPS |
|
Text Classification (HP)
|
100% |
3782
5.05 KIPS |
|
Text Classification (Q)
|
93% |
3743
5.02 KIPS |
|
Machine Translation (SP)
|
100% |
1010
17.4 IPS |
|
Machine Translation (HP)
|
100% |
1004
17.3 IPS |
|
Machine Translation (Q)
|
98% |
928
16.0 IPS |