资源算法ladder-densenet

ladder-densenet

2020-02-05 | |  35 |   0 |   0

Dataset preparation

  1. Add this repository to your PYTHONPATH variable:

PYTHONPATH=$PYTHONPATH:/path/to/fork
  1. Run script:

  • for Cityscapes: Download the dataset here.

cd datasets/cityscapes
python prepare_dataset.py --data_dir=/path/to/data --gt_dir=/path/to/labels --save_dir=/path/to/save
  • for PASCAL VOC2012: Download the dataset here.

cd datasets/voc2012
python prepare_dataset.py --data_dir=/path/to/data --save_dir=/path/to/save

Training

  • for Cityscapes:

python train.py --config_path='/path/to/fork/config/cityscapes/densenet.py' --batch_size=5 --num_iters=3000
  • for PASCAL VOC2012:

python train.py --config_path='/path/to/fork/config/voc2012/densenet.py' --batch_size=5 --num_iters=3000

Evaluation


上一篇:DenseNet-Cifar10

下一篇:DenseNet-MURA-PyTorch

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...