search

hitzhangyu / Self-supervised-Image-Enhancement-Network-Training-With-Low-Light-Images-Only

Self-supervised Image Enhancement Network: Training With Low Light Images Only
137 stars 18 forks source link

测试时遇到的问题InvalidArgumentError (see above for traceback): ConcatOp #7

Open niujingyu139 opened 3 years ago

niujingyu139 commented 3 years ago

您好，我是一个深度学习小白，在用您训练好的模型直接测试时，遇到的下面的错误： tensorflow.python.framework.errors_impl.InvalidArgumentError: ConcatOp : Dimensions of inputs should match: shape[0] = [1,516,884,64] vs. shape[1] = [1,515,883,64] [[node DecomNet/concat………… InvalidArgumentError (see above for traceback): ConcatOp : Dimensions of inputs should match: shape[0] = [1,516,884,64] vs. shape[1] = [1,515,883,64] 请问这是什么原因呢？我用的是tf1.13，py3.7。

hitzhangyu commented 3 years ago

好像是下采样之后的数据和原来的数据的大小不匹配，可以对输入数据做一个裁剪，将图像尺寸变为4的整倍数

niujingyu139 commented 3 years ago

谢谢您，还有一个问题是我在训练的时候，每次结束时保存模型会提示错误： [*] Evaluating for phase Decom / epoch 100... [*] Saving model RetinexNet-Decom 2020-08-11 10:57:36.991719: W tensorflow/core/framework/op_kernel.cc:1401] OP_REQUIRES failed at save_restore_v2_ops.cc:109 : Not found: Failed to create a NewWriteableFile: ./checkpoint\Decom\RetinexNet-Decom-100.data-00000-of-00001.tempstate17276891056262347381 : ϵͳ�Ҳ���ָ����·���� ; No such process 请问这是为什么呀？

niujingyu139 commented 3 years ago

训练的时候我除了读图片的位置，别的都没有改。

hitzhangyu commented 3 years ago

这个不清楚，我好像没遇到过