Upload Date | June 25 2025 03:02 AM |
Views | 2 |
System Information | |
---|---|
Operating System | iOS 16.3.1 |
Model | iPad Pro (10.5-inch) |
Model ID | iPad7,3 |
Motherboard | J207AP |
CPU Information | |
---|---|
Name | Apple A10X Fusion |
Topology | 1 Processor, 3 Cores |
Identifier | ARM |
Base Frequency | 2.34 GHz |
Cluster 1 | 3 Cores |
L1 Instruction Cache | 64.0 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 8.00 MB x 1 |
Memory Information | |
---|---|
Size | 3.91 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
407
76.2 IPS |
|
Image Classification (F16)
|
100% |
399
74.7 IPS |
|
Image Classification (I8)
|
99% |
377
70.6 IPS |
|
Image Segmentation (F32)
|
100% |
278
4.65 IPS |
|
Image Segmentation (F16)
|
100% |
277
4.62 IPS |
|
Image Segmentation (I8)
|
100% |
277
4.63 IPS |
|
Pose Estimation (F32)
|
100% |
2531
3.07 IPS |
|
Pose Estimation (F16)
|
100% |
2535
3.07 IPS |
|
Pose Estimation (I8)
|
100% |
2534
3.07 IPS |
|
Object Detection (F32)
|
100% |
583
43.5 IPS |
|
Object Detection (F16)
|
100% |
577
43.1 IPS |
|
Object Detection (I8)
|
97% |
601
44.9 IPS |
|
Face Detection (F32)
|
100% |
2218
26.4 IPS |
|
Face Detection (F16)
|
100% |
2161
25.7 IPS |
|
Face Detection (I8)
|
99% |
2122
25.2 IPS |
|
Depth Estimation (F32)
|
100% |
3343
25.9 IPS |
|
Depth Estimation (F16)
|
100% |
3269
25.4 IPS |
|
Depth Estimation (I8)
|
99% |
3321
25.8 IPS |
|
Style Transfer (F32)
|
100% |
7731
10.2 IPS |
|
Style Transfer (F16)
|
100% |
7454
9.80 IPS |
|
Style Transfer (I8)
|
100% |
7708
10.1 IPS |
|
Image Super-Resolution (F32)
|
100% |
1955
69.8 IPS |
|
Image Super-Resolution (F16)
|
100% |
1914
68.4 IPS |
|
Image Super-Resolution (I8)
|
100% |
1844
65.9 IPS |
|
Text Classification (F32)
|
100% |
59
84.4 IPS |
|
Text Classification (F16)
|
100% |
126
180.9 IPS |
|
Text Classification (I8)
|
96% |
125
179.8 IPS |
|
Machine Translation (F32)
|
100% |
352
6.48 IPS |
|
Machine Translation (F16)
|
100% |
274
5.05 IPS |
|
Machine Translation (I8)
|
99% |
352
6.48 IPS |