The inputs of dynamic_rnn must be 3-D tensor?

sherjilozair / char-rnn-tensorflow

Multi-layer Recurrent Neural Networks (LSTM, RNN) for character-level language models in Python using Tensorflow

MIT License

2.64k stars 964 forks source link

The inputs of dynamic_rnn must be 3-D tensor? #94

Closed NiHaoUCAS closed 7 years ago

NiHaoUCAS commented 7 years ago

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