User | pakitt |
Upload Date | August 01 2024 09:27 PM |
Views | 8 |
System Information | |
---|---|
Operating System | iOS 17.6 |
Model | iPhone 15 Pro Max |
Model ID | iPhone16,2 |
Motherboard | D84AP |
CPU Information | |
---|---|
Name | Apple A17 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
L1 Instruction Cache | 128 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 4.00 MB x 1 |
Memory Information | |
---|---|
Size | 7.44 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1748
327.0 IPS |
|
Image Classification (F16)
|
100% |
6224
1.16 KIPS |
|
Image Classification (I8)
|
99% |
6659
1.25 KIPS |
|
Image Segmentation (F32)
|
100% |
1399
23.4 IPS |
|
Image Segmentation (F16)
|
100% |
1735
29.0 IPS |
|
Image Segmentation (I8)
|
100% |
1797
30.0 IPS |
|
Pose Estimation (F32)
|
100% |
14532
17.6 IPS |
|
Pose Estimation (F16)
|
100% |
82317
99.7 IPS |
|
Pose Estimation (I8)
|
100% |
85960
104.1 IPS |
|
Object Detection (F32)
|
100% |
1468
109.6 IPS |
|
Object Detection (F16)
|
100% |
3826
285.6 IPS |
|
Object Detection (I8)
|
97% |
2303
171.9 IPS |
|
Face Detection (F32)
|
100% |
6383
75.9 IPS |
|
Face Detection (F16)
|
97% |
10531
125.2 IPS |
|
Face Detection (I8)
|
96% |
10525
125.1 IPS |
|
Depth Estimation (F32)
|
100% |
12203
94.6 IPS |
|
Depth Estimation (F16)
|
100% |
37206
288.5 IPS |
|
Depth Estimation (I8)
|
37% |
40663
315.3 IPS |
|
Style Transfer (F32)
|
100% |
28005
36.8 IPS |
|
Style Transfer (F16)
|
100% |
120439
158.4 IPS |
|
Style Transfer (I8)
|
100% |
122392
161.0 IPS |
|
Image Super-Resolution (F32)
|
100% |
6952
248.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
18018
643.5 IPS |
|
Image Super-Resolution (I8)
|
100% |
18428
658.1 IPS |
|
Text Classification (F32)
|
100% |
452
649.8 IPS |
|
Text Classification (F16)
|
100% |
483
693.8 IPS |
|
Text Classification (I8)
|
96% |
490
703.7 IPS |
|
Machine Translation (F32)
|
100% |
752
13.8 IPS |
|
Machine Translation (F16)
|
100% |
1572
28.9 IPS |
|
Machine Translation (I8)
|
99% |
676
12.4 IPS |