Ir para o conteúdo
ModelListadosExterno
Baixar

Mobilenetv2 140 Ra In1k Int8 Ov

Model creator: timm Original model: timm/mobilenetv2140.rain1k

Fontehuggingface.co/OpenVINO/mobilenetv2_140_ra_in1k-int8-ov/tree/85295a70dd05b3c83453e5e6d6fdf69e308d0ad7
TipoOtherModelo basetimm/mobilenetv2_140.ra_in1kVersãoRevision 85295a7Unratednota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
6,05 MB
Modelo base
timm/mobilenetv2_140.ra_in1k
Versão
vRevision 85295a7
Atualizado
5 de nov. de 2026
Downloads
14
Fonte
Hugging Face

Descrição da fonte

mobilenetv2_140_ra_in1k-int8-ov

Description

This is timm/mobilenetv2_140.ra_in1k model converted to the OpenVINOTM IR (Intermediate Representation) format with weights compressed to INT8 by NNCF.

Quantization Parameters

Weight compression was performed using nncf.quantize with the following parameters:

  • Quantization method: Post-Training Quantization (PTQ)
  • Precision: INT8 for both weights and activations

For more information on quantization, check the OpenVINO model optimization guide.

Compatibility

The provided OpenVINOTM IR model is compatible with:

  • OpenVINO version 2026.1.0 and higher
  • Model API 0.4.0 and higher

Running Model Inference with Model API

  1. Install required packages:
pip install openvino-model-api[huggingface]
  1. Run model inference:
import cv2
from model_api.models import Model
from model_api.visualizer import Visualizer

# 1. Load model
model = Model.from_pretrained("OpenVINO/mobilenetv2_140_ra_in1k-int8-ov")

# 2. Load image
image = cv2.imread("image.jpg")

# 3. Run inference
result = model(image)

# 4. Visualize and save results
vis = Visualizer().render(image, result)
cv2.imwrite("output.jpg", vis)

For more examples and possible optimizations, refer to the Model API Documentation.

Limitations

Check the original model card for limitations.

Legal information

The original model is distributed under the Apache-2.0 license. More details can be found in timm/mobilenetv2_140.ra_in1k

Disclaimer

Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See Intel’s Global Human Rights Principles. Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.

Fontes

1 fonte
Hugging FacePrimárioVersão 85295a70dd05b3c83453e5e6d6fdf69e308d0ad7
huggingface.co/OpenVINO/mobilenetv2_140_ra_in1k-int8-ov/tree/85295a70dd05b3c83453e5e6d6fdf69e308d0ad7

Verificado 5 de nov.

Download files

Repository files

File inventory only; completeness is unverified.

Artefatos de modelo

1 artefato

mobilenetv2_140_ra_in1k.bin

bin · 6,05 MB · SHA-256 1c49527bfa3b…5c93 · Hugging Face

Download file

Trechos de fonte

3 trechos
Readme27 de ago.huggingface.co/OpenVINO/mobilenetv2_140_ra_in1k-int8-ov

--- license: apache-2.0 tags: - image-classification - vision base_model: - timm/mobilenetv2_140.ra_in1k base_model_relation: quantized --- # mobilenetv2_140_ra_in1k-int8-ov - Model creator: [timm](https://huggingface.co/timm) - Original model: [timm/mobilenetv2_140.ra_in1k](https://huggingface.co/timm/mobilenetv2_140.ra_in1k) ## Description This is [timm/mobilenetv2_140.ra_in1k](https://huggingface.co/timm/mobilenetv2_140.ra_in1k) model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2026/documentation/openvino-ir-format.html) (Intermediate Representation) format with weights compressed to INT8 by [NNCF](https://github.com/openvinotoolkit/nncf). ## Quantization Parameters Weight compression was performed using nncf.quantize with the following parameters: - **Quantization method**: Post-Training Quantization (PTQ) - **Precision**: INT8 for both weights and activations For more information on quantization, check the [OpenVINO model optimization guide](https://docs.openvino.ai/2026/openvino-workflow/model-optimization-guide/quantizing-models-post-training.html). ## Compatibility The provided OpenVINO™ IR model is compatible with: - OpenVINO version 2026.1.0 and higher - Model API 0.4.0 and higher ## Running Model Inference with [Model API](https://github.com/open-edge-platform/model_api) 1. Install required packages: ```sh pip install openvino-model-api[huggingface] ``` <!-- markdownlint-disable MD029 --> 2. Run model inference: ```python import cv2 from model_api.models import Model from model_api.visualizer import Visualizer # 1. Load model model = Model.from_pretrained("OpenVINO/mobilenetv2_140_ra_in1k-int8-ov") # 2. Load image image = cv2.imread("image.jpg") # 3. Run inference result = model(image) # 4. Visualize and save results vis = Visualizer().render(image, result) cv2.imwrite("output.jpg", vis) ``` For more examples and possible optimizations, refer to the [Model API Documentation](https://open-edge-platform.github.io/model_api/latest/). ## Limitations Check the [original model card](https://huggingface.co/timm/mobilenetv2_140.ra_in1k) for limitations. ## Legal information The original model is distributed under the [Apache-2.0](https://spdx.org/licenses/Apache-2.0.html) license. More details can be found in [timm/mobilenetv2_140.ra_in1k](https://huggingface.co/timm/mobilenetv2_140.ra_in1k) ## Disclaimer Int...

Note5 de nov.huggingface.co/OpenVINO/mobilenetv2_140_ra_in1k-int8-ov

Source context: 14 downloads · 0 likes · Pipeline image-classification · Repo OpenVINO/mobilenetv2_140_ra_in1k-int8-ov

Note27 de ago.huggingface.co/OpenVINO/mobilenetv2_140_ra_in1k-int8-ov

Source context: 13 downloads · 0 likes · Pipeline image-classification · Repo OpenVINO/mobilenetv2_140_ra_in1k-int8-ov