Hugging Face's logo

qualcomm
/
FCN-ResNet50

Image Segmentation
PyTorch
android
Model card Files
xet
 Community
FCN-ResNet50 / README.md
qaihm-bot's picture
qaihm-bot
v0.51.0
0c452e8 verified
preview code
|
raw
history blame contribute delete
10.4 kB
metadata 
library_name: pytorch
license: other
tags:
  - android
pipeline_tag: image-segmentation

FCN-ResNet50: Optimized for Qualcomm Devices

FCN_ResNet50 is a machine learning model that can segment images from the COCO dataset. It uses ResNet50 as a backbone.

This is based on the implementation of FCN-ResNet50 found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime Precision Chipset SDK Versions Download
ONNX float Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
ONNX w8a8 Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a8 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download
TFLITE w8a8 Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit FCN-ResNet50 on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

  • Custom weights (e.g., fine-tuned checkpoints)
  • Custom input shapes
  • Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for FCN-ResNet50 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

  • Model checkpoint: COCO_WITH_VOC_LABELS_V1
  • Input resolution: 224x224
  • Number of output classes: 21
  • Number of parameters: 33.0M
  • Model size (float): 126 MB
  • Model size (w8a8): 32.2 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
FCN-ResNet50 ONNX float Snapdragon® 8 Elite Gen 5 Mobile 22.469 ms 4 - 325 MB NPU
FCN-ResNet50 ONNX float Snapdragon® X2 Elite 23.298 ms 63 - 63 MB NPU
FCN-ResNet50 ONNX float Snapdragon® X Elite 43.083 ms 62 - 62 MB NPU
FCN-ResNet50 ONNX float Snapdragon® 8 Gen 3 Mobile 32.662 ms 0 - 383 MB NPU
FCN-ResNet50 ONNX float Qualcomm® QCS8550 (Proxy) 43.797 ms 3 - 6 MB NPU
FCN-ResNet50 ONNX float Qualcomm® QCS9075 75.188 ms 3 - 9 MB NPU
FCN-ResNet50 ONNX float Snapdragon® 8 Elite For Galaxy Mobile 26.75 ms 1 - 307 MB NPU
FCN-ResNet50 ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 7.064 ms 1 - 249 MB NPU
FCN-ResNet50 ONNX w8a8 Snapdragon® X2 Elite 7.103 ms 33 - 33 MB NPU
FCN-ResNet50 ONNX w8a8 Snapdragon® X Elite 13.847 ms 32 - 32 MB NPU
FCN-ResNet50 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 10.021 ms 0 - 277 MB NPU
FCN-ResNet50 ONNX w8a8 Qualcomm® QCS6490 911.428 ms 68 - 111 MB CPU
FCN-ResNet50 ONNX w8a8 Qualcomm® QCS8550 (Proxy) 13.52 ms 1 - 4 MB NPU
FCN-ResNet50 ONNX w8a8 Qualcomm® QCS9075 15.133 ms 1 - 4 MB NPU
FCN-ResNet50 ONNX w8a8 Qualcomm® QCM6690 824.523 ms 64 - 73 MB CPU
FCN-ResNet50 ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 8.569 ms 1 - 206 MB NPU
FCN-ResNet50 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 705.859 ms 67 - 75 MB CPU
FCN-ResNet50 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 21.725 ms 3 - 332 MB NPU
FCN-ResNet50 QNN_DLC float Snapdragon® X2 Elite 22.868 ms 3 - 3 MB NPU
FCN-ResNet50 QNN_DLC float Snapdragon® X Elite 44.643 ms 3 - 3 MB NPU
FCN-ResNet50 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 33.614 ms 0 - 378 MB NPU
FCN-ResNet50 QNN_DLC float Qualcomm® QCS8275 (Proxy) 273.55 ms 1 - 308 MB NPU
FCN-ResNet50 QNN_DLC float Qualcomm® QCS8550 (Proxy) 44.098 ms 3 - 8 MB NPU
FCN-ResNet50 QNN_DLC float Qualcomm® SA8775P 72.852 ms 1 - 308 MB NPU
FCN-ResNet50 QNN_DLC float Qualcomm® QCS9075 78.907 ms 3 - 8 MB NPU
FCN-ResNet50 QNN_DLC float Qualcomm® QCS8450 (Proxy) 83.944 ms 0 - 268 MB NPU
FCN-ResNet50 QNN_DLC float Qualcomm® SA7255P 273.55 ms 1 - 308 MB NPU
FCN-ResNet50 QNN_DLC float Qualcomm® SA8295P 77.778 ms 0 - 216 MB NPU
FCN-ResNet50 QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 26.555 ms 3 - 322 MB NPU
FCN-ResNet50 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 7.433 ms 1 - 245 MB NPU
FCN-ResNet50 QNN_DLC w8a8 Snapdragon® X2 Elite 7.793 ms 1 - 1 MB NPU
FCN-ResNet50 QNN_DLC w8a8 Snapdragon® X Elite 15.149 ms 1 - 1 MB NPU
FCN-ResNet50 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 11.204 ms 0 - 263 MB NPU
FCN-ResNet50 QNN_DLC w8a8 Qualcomm® QCS6490 93.525 ms 1 - 3 MB NPU
FCN-ResNet50 QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 39.465 ms 1 - 206 MB NPU
FCN-ResNet50 QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 14.805 ms 1 - 3 MB NPU
FCN-ResNet50 QNN_DLC w8a8 Qualcomm® SA8775P 14.727 ms 1 - 215 MB NPU
FCN-ResNet50 QNN_DLC w8a8 Qualcomm® QCS9075 17.216 ms 1 - 3 MB NPU
FCN-ResNet50 QNN_DLC w8a8 Qualcomm® QCM6690 389.473 ms 1 - 384 MB NPU
FCN-ResNet50 QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 24.406 ms 1 - 266 MB NPU
FCN-ResNet50 QNN_DLC w8a8 Qualcomm® SA7255P 39.465 ms 1 - 206 MB NPU
FCN-ResNet50 QNN_DLC w8a8 Qualcomm® SA8295P 21.887 ms 1 - 209 MB NPU
FCN-ResNet50 QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 8.926 ms 0 - 200 MB NPU
FCN-ResNet50 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 25.967 ms 1 - 284 MB NPU
FCN-ResNet50 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 20.875 ms 0 - 368 MB NPU
FCN-ResNet50 TFLITE float Snapdragon® 8 Gen 3 Mobile 33.054 ms 0 - 428 MB NPU
FCN-ResNet50 TFLITE float Qualcomm® QCS8275 (Proxy) 273.485 ms 0 - 353 MB NPU
FCN-ResNet50 TFLITE float Qualcomm® QCS8550 (Proxy) 44.407 ms 0 - 3 MB NPU
FCN-ResNet50 TFLITE float Qualcomm® SA8775P 72.835 ms 0 - 354 MB NPU
FCN-ResNet50 TFLITE float Qualcomm® QCS9075 79.293 ms 0 - 71 MB NPU
FCN-ResNet50 TFLITE float Qualcomm® QCS8450 (Proxy) 83.983 ms 0 - 323 MB NPU
FCN-ResNet50 TFLITE float Qualcomm® SA7255P 273.485 ms 0 - 353 MB NPU
FCN-ResNet50 TFLITE float Qualcomm® SA8295P 77.795 ms 0 - 268 MB NPU
FCN-ResNet50 TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 27.156 ms 0 - 358 MB NPU
FCN-ResNet50 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 7.358 ms 0 - 244 MB NPU
FCN-ResNet50 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 10.954 ms 0 - 264 MB NPU
FCN-ResNet50 TFLITE w8a8 Qualcomm® QCS6490 95.436 ms 0 - 39 MB NPU
FCN-ResNet50 TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 38.208 ms 0 - 205 MB NPU
FCN-ResNet50 TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 14.241 ms 0 - 3 MB NPU
FCN-ResNet50 TFLITE w8a8 Qualcomm® SA8775P 14.685 ms 0 - 207 MB NPU
FCN-ResNet50 TFLITE w8a8 Qualcomm® QCS9075 15.381 ms 0 - 35 MB NPU
FCN-ResNet50 TFLITE w8a8 Qualcomm® QCM6690 436.069 ms 0 - 382 MB NPU
FCN-ResNet50 TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 23.266 ms 0 - 265 MB NPU
FCN-ResNet50 TFLITE w8a8 Qualcomm® SA7255P 38.208 ms 0 - 205 MB NPU
FCN-ResNet50 TFLITE w8a8 Qualcomm® SA8295P 21.286 ms 0 - 210 MB NPU
FCN-ResNet50 TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 8.599 ms 0 - 198 MB NPU
FCN-ResNet50 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 27.95 ms 0 - 284 MB NPU

License

  • The license for the original implementation of FCN-ResNet50 can be found here.

References

Community