| User | gbenchgs |
| Upload Date | August 15 2024 06:29 PM |
| Views | 9 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| 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% |
1999
371.8 IPS |
|
|
Image Classification (HP)
|
100% |
3384
629.4 IPS |
|
|
Image Classification (Q)
|
99% |
3373
629.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
2100
34.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
3214
52.1 IPS |
|
|
Image Segmentation (Q)
|
100% |
3173
51.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
10046
11.7 IPS |
|
|
Pose Estimation (HP)
|
100% |
19065
22.2 IPS |
|
|
Pose Estimation (Q)
|
96% |
16301
19.1 IPS |
|
|
Object Detection (SP)
|
100% |
2216
175.8 IPS |
|
|
Object Detection (HP)
|
97% |
3792
301.9 IPS |
|
|
Object Detection (Q)
|
94% |
2695
214.8 IPS |
|
|
Face Detection (SP)
|
100% |
3964
47.1 IPS |
|
|
Face Detection (HP)
|
100% |
7696
91.4 IPS |
|
|
Face Detection (Q)
|
100% |
4445
52.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
8252
63.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
14610
112.9 IPS |
|
|
Depth Estimation (Q)
|
96% |
14737
114.0 IPS |
|
|
Style Transfer (SP)
|
100% |
25139
32.3 IPS |
|
|
Style Transfer (HP)
|
100% |
38054
48.9 IPS |
|
|
Style Transfer (Q)
|
100% |
38162
49.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5798
214.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6835
252.4 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
4784
177.3 IPS |
|
|
Text Classification (SP)
|
100% |
2998
4.00 KIPS |
|
|
Text Classification (HP)
|
100% |
5202
6.94 KIPS |
|
|
Text Classification (Q)
|
93% |
5170
6.94 KIPS |
|
|
Machine Translation (SP)
|
100% |
3846
66.2 IPS |
|
|
Machine Translation (HP)
|
98% |
6889
119.0 IPS |
|
|
Machine Translation (Q)
|
98% |
6901
119.3 IPS |