| User | Jloloew |
| Upload Date | August 16 2024 01:23 AM |
| Views | 7 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple M1 |
| System Information | |
|---|---|
| Operating System | iOS 18.0 |
| Model | iPad Pro (11-inch 3rd generation) |
| Model ID | iPad13,4 |
| Motherboard | J517AP |
| CPU Information | |
|---|---|
| Name | Apple M1 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.19 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 15.31 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1262
234.6 IPS |
|
|
Image Classification (HP)
|
100% |
2356
438.2 IPS |
|
|
Image Classification (Q)
|
99% |
2342
436.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
1377
22.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
2401
38.9 IPS |
|
|
Image Segmentation (Q)
|
100% |
2400
38.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
6435
7.51 IPS |
|
|
Pose Estimation (HP)
|
100% |
14392
16.8 IPS |
|
|
Pose Estimation (Q)
|
96% |
12691
14.9 IPS |
|
|
Object Detection (SP)
|
100% |
1434
113.8 IPS |
|
|
Object Detection (HP)
|
97% |
2793
222.4 IPS |
|
|
Object Detection (Q)
|
94% |
1980
157.8 IPS |
|
|
Face Detection (SP)
|
100% |
2794
33.2 IPS |
|
|
Face Detection (HP)
|
100% |
5553
66.0 IPS |
|
|
Face Detection (Q)
|
100% |
3280
39.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
5301
40.8 IPS |
|
|
Depth Estimation (HP)
|
98% |
10824
83.6 IPS |
|
|
Depth Estimation (Q)
|
97% |
10870
84.1 IPS |
|
|
Style Transfer (SP)
|
100% |
18084
23.2 IPS |
|
|
Style Transfer (HP)
|
100% |
28232
36.3 IPS |
|
|
Style Transfer (Q)
|
100% |
28290
36.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4056
149.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4905
181.1 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
3516
130.2 IPS |
|
|
Text Classification (SP)
|
100% |
2184
2.92 KIPS |
|
|
Text Classification (HP)
|
100% |
3784
5.05 KIPS |
|
|
Text Classification (Q)
|
93% |
3700
4.97 KIPS |
|
|
Machine Translation (SP)
|
100% |
3318
57.2 IPS |
|
|
Machine Translation (HP)
|
98% |
5584
96.5 IPS |
|
|
Machine Translation (Q)
|
98% |
5580
96.4 IPS |