User | dipak |
Upload Date | December 04 2024 01:02 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad Pro (12.9-inch, 6th generation) |
Model ID | iPad14,5 |
Motherboard | J620AP |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3631
675.2 IPS |
|
Image Classification (HP)
|
100% |
3709
689.8 IPS |
|
Image Classification (Q)
|
97% |
3032
565.7 IPS |
|
Image Segmentation (SP)
|
100% |
4034
65.4 IPS |
|
Image Segmentation (HP)
|
100% |
5013
81.3 IPS |
|
Image Segmentation (Q)
|
99% |
5088
82.5 IPS |
|
Pose Estimation (SP)
|
100% |
24659
28.8 IPS |
|
Pose Estimation (HP)
|
100% |
26284
30.7 IPS |
|
Pose Estimation (Q)
|
95% |
24534
28.8 IPS |
|
Object Detection (SP)
|
100% |
3687
292.4 IPS |
|
Object Detection (HP)
|
100% |
3675
291.5 IPS |
|
Object Detection (Q)
|
91% |
3035
242.5 IPS |
|
Face Detection (SP)
|
100% |
10346
122.9 IPS |
|
Face Detection (HP)
|
100% |
11942
141.9 IPS |
|
Face Detection (Q)
|
100% |
8374
99.5 IPS |
|
Depth Estimation (SP)
|
100% |
16724
128.8 IPS |
|
Depth Estimation (HP)
|
99% |
17836
137.4 IPS |
|
Depth Estimation (Q)
|
85% |
14896
116.4 IPS |
|
Style Transfer (SP)
|
100% |
42968
55.2 IPS |
|
Style Transfer (HP)
|
100% |
48580
62.4 IPS |
|
Style Transfer (Q)
|
96% |
45426
58.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
9802
361.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
10100
372.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
7972
294.4 IPS |
|
Text Classification (SP)
|
100% |
2239
2.99 KIPS |
|
Text Classification (HP)
|
100% |
3642
4.86 KIPS |
|
Text Classification (Q)
|
93% |
3691
4.95 KIPS |
|
Machine Translation (SP)
|
100% |
1453
25.0 IPS |
|
Machine Translation (HP)
|
100% |
1157
19.9 IPS |
|
Machine Translation (Q)
|
98% |
1307
22.6 IPS |