Skip to content

Sketch-SparseNet: A Novel Sparse-convolution-based Framework for Sketch Recognition

License

Notifications You must be signed in to change notification settings

kingbackyang/sketch-sparsenet

Repository files navigation

Sketch-SparseNet

This is the official implementation of "Sketch-SparseNet: A Novel Sparse-convolution-based Framework for Sketch Recognition"

Supported Backbone

  • ResNet 18/34/50/101
  • MnasNet
  • Mobilenet
  • DenseNet
  • Swin Transformer
  • GNN
  • RNN
  • Transformer

Supported Datasets

  • QuickDraw-414k
  • Tuberlin
  • CIFAR

Installation

Prerequisites

The code is built with following libraries:

Training

You can modify the config (e.g. configs/swin_image.yaml) to choose or define your model for training

Supported Distributed Training

CUDA_VISIBLE_DEVICES=0,1,2,3 torchpack dist-run -np 4 python train_img_single.py configs/swin_image.yaml --run-dir nbenchmark/swin_sce # 4 gpus
CUDA_VISIBLE_DEVICES=2,3 torchpack dist-run -np 2 python train_img2.py configs/quickdraw/sd3b1_image_stroke.yaml --run-dir nbenchmark/trans/resnet50_quickdraw_image_stroke_sd3b1_norm/

Single GPU Training

python train_img_single.py configs/swin_image.yaml --run-dir nbenchmark/swin_sce --distributed False
python train_img2.py configs/quickdraw/sd3b1_image_stroke.yaml --run-dir nbenchmark/trans/resnet50_quickdraw_image_stroke_sd3b1_norm/ --distributed False

Citation

Issues

If you have any problems, feel free to reach out to me in the issue.

About

Sketch-SparseNet: A Novel Sparse-convolution-based Framework for Sketch Recognition

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages