Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

software-mansion
/
LRASPP-MobileNetV3-Large-ExecuTorch

Image Segmentation
ExecuTorch
Model card Files Files and versions
xet
Community
LRASPP-MobileNetV3-Large-ExecuTorch / qnn
25.1 MB
Ctrl+K
Ctrl+K
  • 3 contributors
History: 3 commits
msluszniak's picture
msluszniak
Drop QNN a16w8 segmentation variants; a8w8 matches their mIoU at half the latency
f5bf5ab verified 4 days ago
  • config.json
    3.4 kB
    Export the LR-ASPP QNN variants as a8w8 (2.4x faster at the same mIoU) 19 days ago
  • lraspp_mobilenet_v3_large_qnn_a8w8_v69.pte
    6.98 MB
    xet
    Export the LR-ASPP QNN variants as a8w8 (2.4x faster at the same mIoU) 19 days ago
  • lraspp_mobilenet_v3_large_qnn_a8w8_v73.pte
    4.52 MB
    xet
    Export the LR-ASPP QNN variants as a8w8 (2.4x faster at the same mIoU) 19 days ago
  • lraspp_mobilenet_v3_large_qnn_a8w8_v75.pte
    4.52 MB
    xet
    Export the LR-ASPP QNN variants as a8w8 (2.4x faster at the same mIoU) 19 days ago
  • lraspp_mobilenet_v3_large_qnn_a8w8_v79.pte
    4.52 MB
    xet
    Export the LR-ASPP QNN variants as a8w8 (2.4x faster at the same mIoU) 19 days ago
  • lraspp_mobilenet_v3_large_qnn_a8w8_v81.pte
    4.56 MB
    xet
    Export the LR-ASPP QNN variants as a8w8 (2.4x faster at the same mIoU) 19 days ago