User | ESPD |
Upload Date | December 15 2024 05:02 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPad Pro 11-inch (M4) |
Model ID | iPad16,3 |
Motherboard | J717AP |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 9 Cores |
Identifier | ARM |
Base Frequency | 4.41 GHz |
Cluster 1 | 3 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 7.29 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2016
375.0 IPS |
|
Image Classification (HP)
|
100% |
17274
3.21 KIPS |
|
Image Classification (Q)
|
97% |
25338
4.73 KIPS |
|
Image Segmentation (SP)
|
100% |
2153
34.9 IPS |
|
Image Segmentation (HP)
|
100% |
22158
359.2 IPS |
|
Image Segmentation (Q)
|
99% |
30609
496.2 IPS |
|
Pose Estimation (SP)
|
100% |
10076
11.8 IPS |
|
Pose Estimation (HP)
|
100% |
124433
145.2 IPS |
|
Pose Estimation (Q)
|
95% |
233224
273.4 IPS |
|
Object Detection (SP)
|
100% |
2265
179.7 IPS |
|
Object Detection (HP)
|
100% |
19186
1.52 KIPS |
|
Object Detection (Q)
|
91% |
25898
2.07 KIPS |
|
Face Detection (SP)
|
100% |
4034
47.9 IPS |
|
Face Detection (HP)
|
100% |
42245
502.0 IPS |
|
Face Detection (Q)
|
100% |
63049
749.2 IPS |
|
Depth Estimation (SP)
|
100% |
8332
64.2 IPS |
|
Depth Estimation (HP)
|
99% |
99532
766.8 IPS |
|
Depth Estimation (Q)
|
85% |
168436
1.32 KIPS |
|
Style Transfer (SP)
|
100% |
25152
32.3 IPS |
|
Style Transfer (HP)
|
100% |
231181
297.2 IPS |
|
Style Transfer (Q)
|
96% |
298128
384.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5850
216.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
48947
1.81 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84089
3.11 KIPS |
|
Text Classification (SP)
|
100% |
2950
3.94 KIPS |
|
Text Classification (HP)
|
100% |
6046
8.07 KIPS |
|
Text Classification (Q)
|
93% |
6205
8.33 KIPS |
|
Machine Translation (SP)
|
100% |
3897
67.1 IPS |
|
Machine Translation (HP)
|
100% |
16437
283.1 IPS |
|
Machine Translation (Q)
|
98% |
18135
313.4 IPS |