FCN-ResNet50-Quantized
Quantized fully-convolutional network model for image segmentation.
FCN_ResNet50 is a quantized machine learning model that can segment images from the COCO dataset. It uses ResNet50 as a backbone.
Technical Details
Model checkpoint:COCO_WITH_VOC_LABELS_V1
Input resolution:512x512
Number of parameters:33.0M
Model size:32.2 MB
Number of output classes:21
Applicable Scenarios
- Anomaly Detection
- Inventory Management
Licenses
Source Model:BSD-3-CLAUSE
Deployable Model:AI Model Hub License
Tags
- quantizedA “quantized” model can run in low or mixed precision, which can substantially reduce inference latency.
Supported Compute Chipsets
- Snapdragon® X Elite