黑白图片训练和推理，yml文件如何配置

[WilliamChang192]

问题确认 Search before asking

• 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer.

请提出你的问题 Please ask your question

如下是我的yml配置文档，使用PPLiteSeg模型设置img_chnnels:1可以正常训练，但用tools/predict.py 推理图片会报错
ValueError: (InvalidArgument) The number of input's channels should be equal to filter's channels * groups for Op(Conv). But received: the input's channels is 3, the input's shape is [1, 3, 1200, 800]; the filter's channels is 1, the filter's shape is [32, 1, 3, 3]; the groups is 1, the data_format is NCHW. The error may come from wrong data_format setting.
[Hint: Expected input_channels == filter_channels * groups, but received input_channels:3 != filter_channels * groups:1.] (at ..\paddle\phi\infermeta\binary.cc:645)

yml文件内容如下：
batch_size: 12
iters: 90000
train_dataset:
type: Dataset
img_channels: 1
dataset_root: C:/Users/yx/PaddleSeg/data/Trains/113226
num_classes: 12
mode: train
train_path: C:/Users/yx/PaddleSeg/data/Trains/113226/train.txt
transforms:
- type: ResizeStepScaling
min_scale_factor: 0.5
max_scale_factor: 2.5
scale_step_size: 0.25
- type: RandomPaddingCrop
crop_size: [512, 512]
- type: RandomHorizontalFlip
- type: RandomDistort
brightness_range: 0.5
contrast_range: 0.5
saturation_range: 0.5
- type: Normalize
val_dataset:
type: Dataset
img_channels: 1
dataset_root: C:/Users/yx/PaddleSeg/data/Trains/113226
num_classes: 12
mode: val
val_path: C:/Users/yx/PaddleSeg/data/Trains/113226/val.txt
transforms:
- type: Normalize
optimizer:
type: SGD
momentum: 0.9
weight_decay: 5.0e-4
lr_scheduler:
type: PolynomialDecay
learning_rate: 0.005
end_lr: 0
power: 0.9
warmup_iters: 200
warmup_start_lr: 1.0e-5
loss:
types:
- type: OhemCrossEntropyLoss
min_kept: 250000 # batch_size * 960 * 720 // 16
- type: OhemCrossEntropyLoss
min_kept: 250000
- type: OhemCrossEntropyLoss
min_kept: 250000
coef: [1, 1, 1]
model:
type: PPLiteSeg
backbone:
type: STDC1
in_channels: 1
pretrained: https://bj.bcebos.com/paddleseg/dygraph/PP_STDCNet1.tar.gz
arm_out_chs: [32, 64, 128]
seg_head_inter_chs: [32, 64, 64]
num_classes: 12 # 修改为你的类别数

[manketon]

修改PaddleSeg/tools/predict.py中main函数：
transforms = Compose(builder.val_transforms, img_channels=cfg.train_dataset_cfg["img_channels"])

[BluebirdStory]

哈喽，感谢反馈，你的问题已经修复，只需要拉取新的develop分支代码即可正常运行。