Created by: flyinggx

2020-06-27 13:36:28 [INFO] 12 samples in file work/PaddleSeg/contrib/RemoteSensing/dataset/building/train.txt 2020-06-27 13:36:28 [INFO] 8 samples in file work/PaddleSeg/contrib/RemoteSensing/dataset/building/val.txt 2020-06-27 13:36:28,649-INFO: If regularizer of a Parameter has been set by 'fluid.ParamAttr' or 'fluid.WeightNormParamAttr' already. The Regularization[L2Decay, regularization_coeff=0.000500] in Optimizer will not take effect, and it will only be applied to other Parameters! W0627 13:36:28.812085 187 device_context.cc:252] Please NOTE: device: 0, CUDA Capability: 70, Driver API Version: 10.1, Runtime API Version: 9.0 W0627 13:36:28.816009 187 device_context.cc:260] device: 0, cuDNN Version: 7.3. /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py:1070: UserWarning: The following exception is not an EOF exception. "The following exception is not an EOF exception.") Traceback (most recent call last): File "work/PaddleSeg/contrib/RemoteSensing/train_demo.py", line 123, in use_vdl=True) File "/home/aistudio/work/PaddleSeg/contrib/RemoteSensing/models/unet.py", line 177, in train use_vdl=use_vdl) File "/home/aistudio/work/PaddleSeg/contrib/RemoteSensing/models/base.py", line 405, in train fetch_list=list(self.train_outputs.values())) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py", line 1071, in run six.reraise(*sys.exc_info()) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/six.py", line 703, in reraise raise value File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py", line 1066, in run return_merged=return_merged) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py", line 1167, in _run_impl return_merged=return_merged) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py", line 873, in _run_parallel check_feed_shape_type(var, tensor) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py", line 225, in check_feed_shape_type (var.name, len(var.shape), var.shape, diff_shape)) ValueError: The fed Variable 'label' should have dimensions = 4, shape = (-1, 1, -1, -1), but received fed shape [4, 1, 512, 512, 3] on each device label格式为单通道png,请问这个问题如何解决？敬谢！