Total runs:
1.8K
Run Growth:
1.6K
Growth Rate:
89.76%
Sponsored by
Vmake Labs Video Enhancer
Arm / nitec-resnet-18-int8-xnnpack-executorch
Model's Last Updated: September 23 2026
image-classification
Introduction of nitec-resnet-18-int8-xnnpack-executorch
Model Details of nitec-resnet-18-int8-xnnpack-executorch
NITEC ResNet-18 INT8 — Camera Contact
This model classifies an RGB face crop as camera contact or no camera contact. It is the NITEC ResNet-18 checkpoint converted to an A8W8, statically quantized ExecuTorch program using the XNNPACK backend.
Artifact
| Item | Value |
|---|---|
| File |
cam_contact_nitec_rs18-a8w8-xnnpack.pte
|
| SHA-256 |
8e36c9127ce32827f44c5a25deaff6a642472672ab68b8a311fe0cda7f43fa4d
|
| Size | 11,260,424 bytes |
| Runtime | ExecuTorch 1.1.0, XNNPACK backend |
| Input |
FLOAT
[1, 3, 224, 224]
, RGB NCHW
|
| Output |
FLOAT
[1, 2]
logits
|
| Classes |
0
: no contact;
1
: contact
|
See
config.yaml
for the complete inference recipe.
Example
By default, the example runs every face crop under
samples/
and writes its
predicted classification under
assets/
. The bundled inputs cover both camera
contact and no camera contact.
| Input | Inferred visualization |
|---|---|
|
|
|
|
|
|
|
|
python -m pip install --extra-index-url https://download.pytorch.org/whl/cpu \
executorch==1.1.0 torch==2.10.0 numpy pillow pyyaml
python example.py
python example.py samples/face-crop-0.png assets/custom-classification.png
The script parses
config.yaml
, making its shapes, resize and center-crop
behavior, normalization, class labels, and softmax postprocessing an executable
inference recipe. Image loading, preprocessing, ExecuTorch inference, output
postprocessing, visualization, and saving remain separate steps for reuse.
With ExecuTorch 1.1.0 on x86-64 CPU, this artifact classified crops 0 and 1 as
contact
with probabilities
0.9793
and
0.9442
, and crops 2 and 3 as
no contact
with probabilities
1.0000
and
1.0000
. These are the observed
artifact outputs and are not an accuracy or performance measurement.
Download
hf download Arm/nitec-resnet-18-int8-xnnpack-executorch \
cam_contact_nitec_rs18-a8w8-xnnpack.pte \
--local-dir .
Intended use and limitations
- Intended for camera-contact classification on already detected, tightly cropped faces.
- It is not a face detector and does not accept a full scene directly.
- Performance may vary with pose, occlusion, lighting, crop quality, and camera placement.
References
About this version
Original Model: NITEC ResNet-18 by Thorsten Hempel et al. - Repository
Optimization/conversion: Arm-Optimized version for execution on Arm-based platforms.
Converted/optimized by: Arm
License: The published artifacts in this repository are distributed under Apache-2.0 .
This repository contains a converted or optimized version of the Original Model (the “Optimized Model”). The Original Model has been converted or optimized as described above for execution on Arm-based platforms.
No retraining or fine-tuning of the Original Model was performed as part of the conversion or optimization. The conversion or optimization was not intended to change the Original Model’s behavior or intended use.
Original Model and Documentation
For information about the Original Model, including its development, training data, intended uses, limitations and other relevant information, please refer to the Original Model repository . Information in that repository was provided by the original developer or other third parties and, unless expressly stated otherwise, has not been independently verified by Arm.
Licenses and Third-Party Terms
Use of the Original Model and the Optimized Model is subject to the applicable licenses, usage restrictions and other terms identified above and in the relevant repositories. Publication of the Optimized Model does not grant any rights beyond those provided under the applicable license terms.
You are responsible for reviewing those terms and ensuring that your use of the Original Model and the Optimized Model is permitted.
Purpose of this Release
The Optimized Model is provided as a reference implementation to demonstrate and evaluate execution and performance on Arm-based systems. It is not a production-ready or supported solution.
Arm’s publication of the Optimized Model does not constitute an endorsement or certification of the Original Model or a representation that the Optimized Model is suitable for production use or any particular purpose.
To the fullest extent permitted by applicable law (i) the Optimized Model is provided “as is.” Arm makes no representations or warranties that the Original Model, the Optimized Model or their outputs are accurate, safe, secure, non-infringing, legally compliant, suitable for production use or fit for any particular purpose; and (ii) Arm will not be liable for any loss or damage arising from or in connection with the Optimized Model, its use or its outputs.
You are responsible for independently evaluating the Optimized Model, its outputs and its suitability for your intended use, including compliance with applicable legal, regulatory, safety and security requirements.
Arm does not commit to provide ongoing support, maintenance or updates for the Optimized Model. Any use of or reliance on the Optimized Model or its outputs is at your own risk.
Runs of Arm nitec-resnet-18-int8-xnnpack-executorch on huggingface.co
824
Total runs
0
24-hour runs
11
3-day runs
106
7-day runs
824
30-day runs
More Information About nitec-resnet-18-int8-xnnpack-executorch huggingface.co Model
Url of nitec-resnet-18-int8-xnnpack-executorch
nitec-resnet-18-int8-xnnpack-executorch huggingface.co Url
Provider of nitec-resnet-18-int8-xnnpack-executorch huggingface.co
Other API from Arm
Updated:September 07 2026
Total runs:
903
Run Growth:
81
Growth Rate:
9.11%
Total runs:
834
Run Growth:
775
Growth Rate:
92.93%
Total runs:
829
Run Growth:
829
Growth Rate:
100.00%
Total runs:
806
Run Growth:
-483
Growth Rate:
-59.93%
Total runs:
750
Run Growth:
375
Growth Rate:
50.00%
Total runs:
698
Run Growth:
365
Growth Rate:
53.68%
Total runs:
677
Run Growth:
276
Growth Rate:
40.77%
Total runs:
672
Run Growth:
620
Growth Rate:
92.26%
Total runs:
629
Run Growth:
230
Growth Rate:
36.57%
Total runs:
599
Run Growth:
501
Growth Rate:
83.64%
Total runs:
558
Run Growth:
117
Growth Rate:
21.27%
Total runs:
484
Run Growth:
178
Growth Rate:
36.78%
Total runs:
466
Run Growth:
350
Growth Rate:
75.11%
Total runs:
385
Run Growth:
-8
Growth Rate:
-2.08%
Total runs:
375
Run Growth:
60
Growth Rate:
16.00%
Total runs:
361
Run Growth:
109
Growth Rate:
30.19%
Total runs:
320
Run Growth:
125
Growth Rate:
39.06%
Total runs:
316
Run Growth:
276
Growth Rate:
87.34%
Total runs:
295
Run Growth:
81
Growth Rate:
27.46%
Total runs:
262
Run Growth:
219
Growth Rate:
83.59%
Total runs:
253
Run Growth:
238
Growth Rate:
94.07%
Total runs:
242
Run Growth:
116
Growth Rate:
47.93%
Total runs:
231
Run Growth:
181
Growth Rate:
78.35%
Total runs:
227
Run Growth:
83
Growth Rate:
36.56%
Total runs:
216
Run Growth:
155
Growth Rate:
71.76%
Total runs:
199
Run Growth:
145
Growth Rate:
72.86%
Total runs:
174
Run Growth:
52
Growth Rate:
29.89%
Total runs:
163
Run Growth:
126
Growth Rate:
77.30%
Total runs:
161
Run Growth:
121
Growth Rate:
75.16%
Total runs:
154
Run Growth:
100
Growth Rate:
64.94%
Total runs:
154
Run Growth:
117
Growth Rate:
81.25%
Total runs:
150
Run Growth:
77
Growth Rate:
51.33%
Total runs:
140
Run Growth:
73
Growth Rate:
52.14%
Total runs:
133
Run Growth:
93
Growth Rate:
69.92%
Total runs:
131
Run Growth:
97
Growth Rate:
85.09%
Total runs:
121
Run Growth:
85
Growth Rate:
70.25%
Total runs:
121
Run Growth:
78
Growth Rate:
64.46%
Total runs:
109
Run Growth:
81
Growth Rate:
74.31%
Total runs:
102
Run Growth:
93
Growth Rate:
91.18%
Total runs:
96
Run Growth:
65
Growth Rate:
67.71%
Total runs:
94
Run Growth:
69
Growth Rate:
73.40%
Total runs:
91
Run Growth:
64
Growth Rate:
70.33%
Total runs:
91
Run Growth:
51
Growth Rate:
56.04%
Total runs:
85
Run Growth:
59
Growth Rate:
69.41%
Total runs:
77
Run Growth:
44
Growth Rate:
57.14%
Total runs:
76
Run Growth:
50
Growth Rate:
65.79%
Total runs:
71
Run Growth:
35
Growth Rate:
49.30%
Total runs:
69
Run Growth:
35
Growth Rate:
50.72%
Total runs:
66
Run Growth:
24
Growth Rate:
36.36%
Total runs:
60
Run Growth:
16
Growth Rate:
26.67%
Total runs:
48
Run Growth:
14
Growth Rate:
29.17%
Total runs:
45
Run Growth:
20
Growth Rate:
44.44%
Total runs:
35
Run Growth:
8
Growth Rate:
22.86%
Total runs:
34
Run Growth:
32
Growth Rate:
94.12%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%