jqjjcp

Dear Arturus: I just use tf.nn.dynamic_rnn+GRUCell to place cudnn but come cross that error: "Input tensor 'rnn/while/Exit_3:0' enters the loop with shape (283, 128), but has shape (?, 128) after...

Dear Flavio, i think maybe we can capture above sequential behaviors and user general interests in a hybrid model, maybe we can combine the recurrsive neural network and FPMC. Here...