hi,
I want to use _dynamicrnn to train my convLSTM, the original data should be videos with dimension: [batch_size, max_time_step, high, width,channel]. But i failed to feed the data to dynamic_rnn.
I get such error:
ValueError: Dimension must be 5 but is 3 for 'transpose' (op: 'Transpose') with input shapes: [16,?,11,40,1], [3].
what should i do to use dynamic rnn?
version: tf 1.0
thanks
hi, I want to use _dynamicrnn to train my convLSTM, the original data should be videos with dimension: [batch_size, max_time_step, high, width,channel]. But i failed to feed the data to dynamic_rnn. I get such error:
ValueError: Dimension must be 5 but is 3 for 'transpose' (op: 'Transpose') with input shapes: [16,?,11,40,1], [3].
what should i do to use dynamic rnn? version: tf 1.0 thanks