unet_plusplus 训练验证时出现数据维度问题

[yuemengrui]

Traceback (most recent call last): File "train.py", line 142, in main(args) File "train.py", line 137, in main losses=losses) File "/home/aistudio/PaddleSeg/paddleseg/core/train.py", line 179, in train model, val_dataset, num_workers=num_workers) File "/home/aistudio/PaddleSeg/paddleseg/core/val.py", line 110, in evaluate crop_size=crop_size) File "/home/aistudio/PaddleSeg/paddleseg/core/infer.py", line 169, in inference logits = model(im) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 891, in call outputs = self.forward(*inputs, *kwargs) File "/home/aistudio/PaddleSeg/paddleseg/models/unet_plusplus.py", line 158, in forward X1_1 = self.up_cat1_1(X2_0, X1_0) # n,64,h/2,w/2 File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 891, in call outputs = self.forward(inputs, **kwargs) File "/home/aistudio/PaddleSeg/paddleseg/models/unet_plusplus.py", line 233, in forward cat_features = paddle.concat(features, axis=1) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/tensor/manipulation.py", line 124, in concat return paddle.fluid.layers.concat(input=x, axis=axis, name=name) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/tensor.py", line 306, in concat return core.ops.concat(input, 'axis', axis) ValueError: (InvalidArgument) The 2-th dimension of input[0] and input[1] is expected to be equal.But received input[0]'s shape = [1, 64, 466, 960], input[1]'s shape = [1, 64, 467, 960].

[operator < concat > error] 上面是报错信息 同样的训练验证数据在deeplabv3p上是没问题的。

[haoyuying]

您好，可参考https://github.com/PaddlePaddle/PaddleSeg/issues/812

[github-actions[bot]]

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.