software-mansion/react-native-executorch-deeplab-v3

deeplab-v3

This repository hosts the deeplab-v3 models exported for the React Native ExecuTorch library as ExecuTorch .pte programs, ready to run on device.

Upstream model: DeepLabV3

Variants

Path	Backend	Precision
coreml/deeplab_v3_mobilenet_v3_large_coreml_fp16.pte	coreml	fp16
coreml/deeplab_v3_resnet50_coreml_fp16.pte	coreml	fp16
coreml/deeplab_v3_resnet101_coreml_fp16.pte	coreml	fp16
xnnpack/deeplab_v3_mobilenet_v3_large_xnnpack_fp32.pte	xnnpack	fp32
xnnpack/deeplab_v3_mobilenet_v3_large_xnnpack_int8.pte	xnnpack	int8
xnnpack/deeplab_v3_resnet50_xnnpack_fp32.pte	xnnpack	fp32
xnnpack/deeplab_v3_resnet50_xnnpack_int8.pte	xnnpack	int8
xnnpack/deeplab_v3_resnet101_xnnpack_fp32.pte	xnnpack	fp32
xnnpack/deeplab_v3_resnet101_xnnpack_int8.pte	xnnpack	int8
qnn/deeplab_v3_mobilenet_v3_large_qnn_a16w8_v69.pte	qnn	a16w8
qnn/deeplab_v3_mobilenet_v3_large_qnn_a16w8_v73.pte	qnn	a16w8
qnn/deeplab_v3_mobilenet_v3_large_qnn_a16w8_v75.pte	qnn	a16w8
qnn/deeplab_v3_mobilenet_v3_large_qnn_a16w8_v79.pte	qnn	a16w8
qnn/deeplab_v3_mobilenet_v3_large_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                                             32 B
coreml/config.json                                      2.1 kB
coreml/deeplab_v3_mobilenet_v3_large_coreml_fp16.pte    21.5 MB
coreml/deeplab_v3_resnet101_coreml_fp16.pte             112 MB
coreml/deeplab_v3_resnet50_coreml_fp16.pte              75.9 MB
mlx/NOTES.md                                            2.0 kB
xnnpack/config.json                                     5.0 kB
xnnpack/deeplab_v3_mobilenet_v3_large_xnnpack_fp32.pte  42.1 MB
xnnpack/deeplab_v3_mobilenet_v3_large_xnnpack_int8.pte  10.8 MB
xnnpack/deeplab_v3_resnet101_xnnpack_fp32.pte           224 MB
xnnpack/deeplab_v3_resnet101_xnnpack_int8.pte           58.9 MB
xnnpack/deeplab_v3_resnet50_xnnpack_fp32.pte            151 MB
xnnpack/deeplab_v3_resnet50_xnnpack_int8.pte            40.4 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.