RNN_convLSTM structure Error

huxian0402 / ConvLSTM-Moving-mnist

Using convlstm to prediction moving mnist dataset.

MIT License

23 stars 7 forks source link

# RNN_convLSTM structure def RNN_convLSTM(x ): #(1,19,64,64,1) #num_filter, kernei_size x = tf.contrib.slim.conv2d(x, 1, 1, padding='SAME',activation_fn=tf.nn.relu) x = tf.contrib.slim.conv2d(x, 8, 1, padding='SAME', activation_fn=tf.nn.relu) x = tf.contrib.slim.conv2d(x, 16, 1, padding='SAME', activation_fn=tf.nn.relu) #(1,10,64,64,16) # [3 , 3] , 1024 rnn_cell = BasicConvLSTMCell([64, 64], [config.conv_filter_size, config.conv_filter_size], config.hidden_size, is_train, forget_bias=1.0, activation=tf.nn.tanh) state_size = rnn_cell.state_size #c(64,64,1024) ,h(64,64,1024)

# RNN_convLSTM  structure
def RNN_convLSTM(x ):

    #(1,19,64,64,1)     #num_filter, kernei_size
    x = tf.contrib.slim.conv2d(x, 1, 1, padding='SAME',activation_fn=tf.nn.relu)
    x = tf.contrib.slim.conv2d(x, 8, 1, padding='SAME', activation_fn=tf.nn.relu)
    x = tf.contrib.slim.conv2d(x, 16, 1, padding='SAME', activation_fn=tf.nn.relu)
    #(1,10,64,64,16)

                                      # [3 ,                       3]      ,                1024
    rnn_cell = BasicConvLSTMCell([64, 64], [config.conv_filter_size, config.conv_filter_size], config.hidden_size,
                                 is_train,
                                 forget_bias=1.0, activation=tf.nn.tanh)

    state_size = rnn_cell.state_size  #c(64,64,1024) ,h(64,64,1024)

我应该把tf.contrib.slim.conv2d改成tf.contrib.slim.conv3d吗？，因为前者的输入只能是一个4维tensor,会报错的！求解？

你解决了吗？我也是同样的问题

huxian0402 / ConvLSTM-Moving-mnist

RNN_convLSTM structure Error #1