资源算法pytorch_random_erasing

pytorch_random_erasing

2020-02-25 | |  47 |   0 |   0

PyTorch Implementation of RandomErasing

Usage

$ python main.py --block_type basic --depth 110 --use_random_erase --random_erase_prob 0.5 --random_erase_area_ratio_range '[0.02, 0.4]' --random_erase_min_aspect_ratio 0.3 --random_erase_max_attempt 20 --outdir results

Results on CIFAR-10

ModelTest Error (median of 5 runs)Training Time
ResNet-preact-56 w/o RandomErasing5.8598 min
ResNet-preact-56 w/ RandomErasing5.2298 min

w/o RandomErasing

$ python -u main.py --depth 56 --block_type basic --base_lr 0.2 --seed 7 --outdir results/wo_random_erasing/00

w/ RandomErasing

$ python -u main.py --depth 56 --block_type basic --base_lr 0.2 --use_random_erase --seed 7 --outdir results/w_random_erasing/00

References





上一篇:Random-Erasing-tensorflow

下一篇: keras_random_erasing

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...