0
我正在使用tfprof來獲取模型轉發路徑所需的觸發器數量。 我的模型之後是3層LSTM和完全連接層。 我觀察到完全連接層的計算數量線性增長,而LSTM層的計算數量沒有變化。這怎麼可能?Tensorflow tfprof LSTMCell
tfprof Report for 1 timestamp forward path。
==================Model Analysis Report======================
_TFProfRoot (0/2.71m flops)
rnn/while/multi_rnn_cell/cell_1/lstm_cell/lstm_cell_1/MatMul (1.05m/1.05m flops)
rnn/while/multi_rnn_cell/cell_2/lstm_cell/lstm_cell_1/MatMul (1.05m/1.05m flops)
rnn/while/multi_rnn_cell/cell_0/lstm_cell/lstm_cell_1/MatMul (606.21k/606.21k flops)
fc_layer/MatMul (1.54k/1.54k flops)
rnn/while/multi_rnn_cell/cell_0/lstm_cell/lstm_cell_1/BiasAdd (1.02k/1.02k flops)
rnn/while/multi_rnn_cell/cell_1/lstm_cell/lstm_cell_1/BiasAdd (1.02k/1.02k flops)
rnn/while/multi_rnn_cell/cell_2/lstm_cell/lstm_cell_1/BiasAdd (1.02k/1.02k flops)
fc_layer/BiasAdd (3/3 flops)
tfprof報告2個時間戳正向路徑。
==================Model Analysis Report======================
_TFProfRoot (0/2.71m flops)
rnn/while/multi_rnn_cell/cell_1/lstm_cell/lstm_cell_1/MatMul (1.05m/1.05m flops)
rnn/while/multi_rnn_cell/cell_2/lstm_cell/lstm_cell_1/MatMul (1.05m/1.05m flops)
rnn/while/multi_rnn_cell/cell_0/lstm_cell/lstm_cell_1/MatMul (606.21k/606.21k flops)
fc_layer/MatMul (3.07k/3.07k flops)
rnn/while/multi_rnn_cell/cell_0/lstm_cell/lstm_cell_1/BiasAdd (1.02k/1.02k flops)
rnn/while/multi_rnn_cell/cell_1/lstm_cell/lstm_cell_1/BiasAdd (1.02k/1.02k flops)
rnn/while/multi_rnn_cell/cell_2/lstm_cell/lstm_cell_1/BiasAdd (1.02k/1.02k flops)
fc_layer/BiasAdd (6/6 flops)
感謝您的明確解釋。我確實使用dynamic_rnn。 –