User | aeonsim |
Upload Date | September 08 2024 08:44 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,9 |
Motherboard | Mac14,9 |
CPU Information | |
---|---|
Name | Apple M2 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Pro |
Base Frequency | 3.47 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1104
205.3 IPS |
|
Image Classification (HP)
|
100% |
8299
1.54 KIPS |
|
Image Classification (Q)
|
96% |
8802
1.64 KIPS |
|
Image Segmentation (SP)
|
100% |
747
12.1 IPS |
|
Image Segmentation (HP)
|
100% |
5132
83.2 IPS |
|
Image Segmentation (Q)
|
99% |
8698
141.0 IPS |
|
Pose Estimation (SP)
|
100% |
11354
13.2 IPS |
|
Pose Estimation (HP)
|
100% |
92990
108.5 IPS |
|
Pose Estimation (Q)
|
95% |
89593
105.0 IPS |
|
Object Detection (SP)
|
100% |
1262
100.1 IPS |
|
Object Detection (HP)
|
99% |
9423
749.6 IPS |
|
Object Detection (Q)
|
93% |
10363
826.9 IPS |
|
Face Detection (SP)
|
100% |
2039
24.2 IPS |
|
Face Detection (HP)
|
100% |
11615
138.0 IPS |
|
Face Detection (Q)
|
100% |
13377
158.9 IPS |
|
Depth Estimation (SP)
|
100% |
3872
29.8 IPS |
|
Depth Estimation (HP)
|
99% |
55630
428.6 IPS |
|
Depth Estimation (Q)
|
85% |
69104
540.0 IPS |
|
Style Transfer (SP)
|
100% |
13177
16.9 IPS |
|
Style Transfer (HP)
|
100% |
145228
186.7 IPS |
|
Style Transfer (Q)
|
95% |
135142
174.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
2487
91.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
21233
784.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
28673
1.06 KIPS |
|
Text Classification (SP)
|
100% |
877
1.17 KIPS |
|
Text Classification (HP)
|
100% |
4040
5.39 KIPS |
|
Text Classification (Q)
|
93% |
4143
5.56 KIPS |
|
Machine Translation (SP)
|
100% |
1811
31.2 IPS |
|
Machine Translation (HP)
|
100% |
2253
38.8 IPS |
|
Machine Translation (Q)
|
98% |
2253
38.9 IPS |