Official #TensorFlow implementation of Dense Transformer Networks

  • In this work, we propose Dense Transformer Networks to apply spatial transformation to semantic prediction tasks.
  • The third and fourth rows are the segmentation results of U-Net and DTN, respectively.
  • max_epoch: how many iterations or steps to train

    test_step: how many steps to perform a mini test or validation

    save_step: how many steps to save the model

    summary_step: how many steps to save the summary

    sampledir: where to store predicted samples, please add a / at the end for convinience

    model_name: the name prefix of saved models

    test_epoch: which step to test or predict

    network_depth: how deep of the U-Net including the bottom layer

    class_num: how many classes.

  • We have conv2d for standard convolutional layer, and ipixel_cl for input pixel convolutional layer proposed in our paper.
  • We have deconv for standard deconvolutional layer, ipixel_dcl for input pixel deconvolutional layer, and pixel_dcl for pixel deconvolutional layer proposed in our paper.

Contribute to dtn development by creating an account on GitHub.
Continue reading “GitHub”