open-mmlab
Why does using Pad in the test_pipeline lead to a significant decrease in IoU and Acc?
my mmseg version：0.30.0
_base_ = './cityscapes.py' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) crop_size = (1024, 1024) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations'), dict(type='Resize', img_scale=(1024, 1024), ratio_range=(0.5, 2.0)), dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75), dict(type='RandomFlip', prob=0.5), dict(type='PhotoMetricDistortion'), dict(type='Normalize', **img_norm_cfg), dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_semantic_seg']), ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1024, 1024), # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75], flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict(type='Normalize', **img_norm_cfg), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']), ]) ] data = dict( train=dict(pipeline=train_pipeline), val=dict(pipeline=test_pipeline), test=dict(pipeline=test_pipeline))
在transforms里加入pad后：
加入前：
我对模型内加入了上采样，由于图像尺寸的缘故，如果不进行pad，会导致上采样后与下采样前的图片尺寸对不上，所以要怎么正确的在test-pipeline里使用Pad？如果您能解答我的问题我将非常感谢！
Hello, do you mind sharing the config of how you got these results. I've been trying to attempt binary segmentation and have not gotten anything like this. It would help me out alot. Also for padding make sure the padding stays white after being normalized or else it will not be ignored.
