User | gbenchgs |
Upload Date | August 15 2024 06:20 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | ARM |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad16,6 |
Model ID | iPad16,6 |
Motherboard | J721AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 10 Cores |
Identifier | ARM |
Base Frequency | 4.45 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 15.07 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1972
366.7 IPS |
|
Image Classification (HP)
|
100% |
17909
3.33 KIPS |
|
Image Classification (Q)
|
99% |
19680
3.67 KIPS |
|
Image Segmentation (SP)
|
100% |
2046
33.2 IPS |
|
Image Segmentation (HP)
|
100% |
14025
227.4 IPS |
|
Image Segmentation (Q)
|
100% |
14017
227.2 IPS |
|
Pose Estimation (SP)
|
100% |
9964
11.6 IPS |
|
Pose Estimation (HP)
|
100% |
118644
138.4 IPS |
|
Pose Estimation (Q)
|
94% |
225062
264.0 IPS |
|
Object Detection (SP)
|
100% |
2218
176.0 IPS |
|
Object Detection (HP)
|
100% |
16758
1.33 KIPS |
|
Object Detection (Q)
|
91% |
25545
2.04 KIPS |
|
Face Detection (SP)
|
100% |
3944
46.9 IPS |
|
Face Detection (HP)
|
100% |
26347
313.1 IPS |
|
Face Detection (Q)
|
100% |
45721
543.3 IPS |
|
Depth Estimation (SP)
|
100% |
8274
63.7 IPS |
|
Depth Estimation (HP)
|
99% |
82496
635.6 IPS |
|
Depth Estimation (Q)
|
97% |
92355
714.1 IPS |
|
Style Transfer (SP)
|
100% |
25116
32.3 IPS |
|
Style Transfer (HP)
|
100% |
167992
216.0 IPS |
|
Style Transfer (Q)
|
100% |
167963
215.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5844
215.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
48458
1.79 KIPS |
|
Image Super-Resolution (Q)
|
98% |
84275
3.12 KIPS |
|
Text Classification (SP)
|
100% |
2983
3.98 KIPS |
|
Text Classification (HP)
|
100% |
5970
7.97 KIPS |
|
Text Classification (Q)
|
93% |
6128
8.22 KIPS |
|
Machine Translation (SP)
|
100% |
3886
66.9 IPS |
|
Machine Translation (HP)
|
100% |
16346
281.6 IPS |
|
Machine Translation (Q)
|
98% |
18007
311.2 IPS |