为什么我的ConvLSTM模型无法预测？

I have built a Convolutional LSTM model using Tensorflow ConvLSTMCell(), tf.nn.dynamic_rnn(), and tf.contrib.legacy_seq2seq.rnn_decoder(). I have 3 layers of encoder, and 3 layers of decoder, the initial states of decoders come from the final states of encoders. I have 128, 64, and 64 filters for layer 1, layer 2, and layer 3 respectively. finally, I concatenate the outputs of decoders and pass them through a convolution layer to decrease the number of channels to one. and then I apply the loss function. My dataset is Moving mnist dataset. in Moving mnist dataset each sequence has 20 frames, by this model I am trying to predict frame 11 to 20 based on the first 10 frames. But the output which is a 10-frame sequence is far from the ground truth and basically tries to reproduce the last input frame which is the 10th frame. I put the code here, thanks for your help.I have built a Convolutional LSTM model using T