急！跪求

运行yolov3-train.py报错，跪求解答tensorflow.python.framework.errors_impl.InvalidArgumentError: Inputs to operation training/Adam/gradients/AddN_24 of type _MklAddN must have the same size and shape.  Input 0: [2768896] != input 1: [8,26,26,512]
  [[Node: training/Adam/gradients/AddN_24 = _MklAddN[N=2, T=DT_FLOAT, _kernel=“MklOp”, _device="/job:localhost/replica:0/task:0/device:CPU:0"](training/Adam/gradients/batch_normalization_65/FusedBatchNorm_grad/FusedBatchNormGrad, training/Adam/gradients/batch_normalization_65/cond/FusedBatchNorm/Switch_grad/cond_grad, training/Adam/gradients/batch_normalization_65/FusedBatchNorm_grad/FusedBatchNormGrad:5, DMT/_2595)]]