react-native-executorch-fcn

software-mansion/react-native-executorch-fcn

react-native-executorch-fcn is a image segmentation model from software-mansion. Use it for the image segmentation task on the model card, and read the license before you ship it in a product. It is set up for executorch. The card lists the license as bsd-3-clause.

This repository hosts the fcn models exported for the React Native ExecuTorch library as ExecuTorch .pte programs, ready to run on device.

Downloads · 30 days

484

46% of all-time downloads

All-time downloads

Public

Repo size

2.3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pte1 GB · 100%

At a glance

Task: Image Segmentation
Library: executorch
License: bsd-3-clause
Access: Public
Created: Feb 24, 2026
Updated: Sep 25, 2026
SHA: e2b9f1d7

Model card

From the Hugging Face model README

fcn

This repository hosts the fcn models exported for the React Native ExecuTorch library as ExecuTorch .pte programs, ready to run on device.

Upstream model: FCN

Variants

Path	Backend	Precision
`coreml/fcn_resnet50_coreml_fp16.pte`	coreml	fp16
`coreml/fcn_resnet101_coreml_fp16.pte`	coreml	fp16
`xnnpack/fcn_resnet50_xnnpack_fp32.pte`	xnnpack	fp32
`xnnpack/fcn_resnet50_xnnpack_int8.pte`	xnnpack	int8
`xnnpack/fcn_resnet101_xnnpack_fp32.pte`	xnnpack	fp32
`xnnpack/fcn_resnet101_xnnpack_int8.pte`	xnnpack	int8
`qnn/fcn_resnet50_qnn_a16w8_v69.pte`	qnn	a16w8
`qnn/fcn_resnet50_qnn_a16w8_v73.pte`	qnn	a16w8
`qnn/fcn_resnet50_qnn_a16w8_v75.pte`	qnn	a16w8
`qnn/fcn_resnet50_qnn_a16w8_v79.pte`	qnn	a16w8
`qnn/fcn_resnet50_qnn_a16w8_v81.pte`	qnn	a16w8
`qnn/fcn_resnet101_qnn_a16w8_v69.pte`	qnn	a16w8
`qnn/fcn_resnet101_qnn_a16w8_v73.pte`	qnn	a16w8
`qnn/fcn_resnet101_qnn_a16w8_v75.pte`	qnn	a16w8
`qnn/fcn_resnet101_qnn_a16w8_v79.pte`	qnn	a16w8
`qnn/fcn_resnet101_qnn_a16w8_v81.pte`	qnn	a16w8

QNN variants

A QNN .pte embeds an HTP context binary compiled for one Hexagon version, so there is one file per version and the runtime picks the one matching the device. These return a class index per pixel, (1, 520, 520) int32, rather than (1, 21, 520, 520) logits.

Hexagon	Example SoC
v69	Snapdragon 8 Gen 1
v73	Snapdragon 8 Gen 2
v75	Snapdragon 8 Gen 3
v79	Snapdragon 8 Elite
v81	Snapdragon 8 Elite Gen 5

Unshipped backends

A backend directory carrying a NOTES.md and no .pte was exported and not published. Its note records what went wrong.

mlx (why)

Repository structure

config.json                             25 B
coreml/config.json                      1.5 kB
coreml/fcn_resnet101_coreml_fp16.pte    99.6 MB
coreml/fcn_resnet50_coreml_fp16.pte     63.1 MB
mlx/NOTES.md                            2.0 kB
xnnpack/config.json                     3.4 kB
xnnpack/fcn_resnet101_xnnpack_fp32.pte  198 MB
xnnpack/fcn_resnet101_xnnpack_int8.pte  52.5 MB
xnnpack/fcn_resnet50_xnnpack_fp32.pte   126 MB
xnnpack/fcn_resnet50_xnnpack_int8.pte   34.0 MB

Compatibility

These files are published for the ExecuTorch v1.4.1 runtime. ExecuTorch gives no forward compatibility guarantee, so an older runtime may fail to load them.

To use them in React Native ExecuTorch, pass the model constant shipped in the library's model registry to the corresponding task pipeline. See the documentation.

To load these files in your own ExecuTorch runtime, read the compatibility note first.

Task: Image Segmentation
Library: executorch
License: bsd-3-clause
Created: Feb 24, 2026
Updated: Sep 25, 2026