PaddlePaddle / PaddleSeg

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc.
https://arxiv.org/abs/2101.06175
Apache License 2.0
8.71k stars 1.68k forks source link

deeplabv3p_mobilenetv3_large_cityscapes.yaml文件中的参数含义 #625

Closed yukang123 closed 1 year ago

yukang123 commented 3 years ago

请问,configs/deeplabv3p_mobilenetv3_large_cityscapes.yaml中的 MODEL.DEEPLAB.ENCODER.ASPP_WITH_SE参数的含义是什么呢,是决定是否使用Squeeze-and-Excitation模块吗?但我在pdseg/models/modeling/deeplab.py里没找到这个参数,而在pdseg/models/backbone/mobilenet_v3.py里面已经根据model_name = large或small来指定各层是否使用SE模块,是不是这个参数已经没有意义了呢?

yaml文件有关模型的内容 MODEL: DEFAULT_NORM_TYPE: "bn" MODEL_NAME: "deeplabv3p" DEEPLAB: BACKBONE: "mobilenetv3_large" ASPP_WITH_SEP_CONV: True DECODER_USE_SEP_CONV: True ENCODER_WITH_ASPP: True ENABLE_DECODER: True OUTPUT_STRIDE: 32 BACKBONE_LR_MULT_LIST: [0.15,0.35,0.65,0.85,1] ENCODER: POOLING_STRIDE: (4, 5) POOLING_CROP_SIZE: (769, 769) ASPP_WITH_SE: True SE_USE_QSIGMOID: True ASPP_CONVS_FILTERS: 128 ASPP_WITH_CONCAT_PROJECTION: False ADD_IMAGE_LEVEL_FEATURE: False DECODER: USE_SUM_MERGE: True CONV_FILTERS: 19 OUTPUT_IS_LOGITS: True

nepeplwu commented 3 years ago

@yukang123 该配置主要用于判断是否要在ASPP模块中使用Squeeze-and-Excitation模块,代码见: https://github.com/PaddlePaddle/PaddleSeg/blob/release/v0.7.0/pdseg/models/modeling/deeplab.py#L160

github-actions[bot] commented 1 year ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.