我们从Python开源项目中，提取了以下4个代码示例，用于说明如何使用theano.TensorType()。
def get_output_for(self, inputs, **kwargs): """ Compute this layer's output function given a symbolic input variable Parameters ---------- inputs : list of theano.TensorType `inputs[0]` should always be the symbolic input variable. When this layer has a mask input (i.e. was instantiated with `mask_input != None`, indicating that the lengths of sequences in each batch vary), `inputs` should have length 2, where `inputs[1]` is the `mask`. The `mask` should be supplied as a Theano variable denoting whether each time step in each sequence in the batch is part of the sequence or not. `mask` should be a matrix of shape ``(n_batch, n_time_steps)`` where ``mask[i, j] = 1`` when ``j <= (length of sequence i)`` and ``mask[i, j] = 0`` when ``j > (length of sequence i)``. When the hidden state of this layer is to be pre-filled (i.e. was set to a :class:`Layer` instance) `inputs` should have length at least 2, and `inputs[-1]` is the hidden state to prefill with. When the cell state of this layer is to be pre-filled (i.e. was set to a :class:`Layer` instance) `inputs` should have length at least 2, and `inputs[-1]` is the hidden state to prefill with. When both the cell state and the hidden state are being pre-filled `inputs[-2]` is the hidden state, while `inputs[-1]` is the cell state. Returns ------- hid_out : theano.TensorType Symbolic output variable. """ _, hid_out = self.__lstm_fun__(inputs, **kwargs) # When it is requested that we only return the final sequence step, # we need to slice it out immediately after scan is applied if self.only_return_final: hid_out = hid_out[-1] else: # dimshuffle back to (n_batch, n_time_steps, n_features)) hid_out = hid_out.dimshuffle(1, 0, 2) # if scan is backward reverse the output if self.backwards: hid_out = hid_out[:, ::-1] return hid_out
def get_hid_cell_for(self, inputs, **kwargs): """ Compute this layer's final hidden output and cell given a symbolic input variable Parameters ---------- inputs : list of theano.TensorType `inputs[0]` should always be the symbolic input variable. When this layer has a mask input (i.e. was instantiated with `mask_input != None`, indicating that the lengths of sequences in each batch vary), `inputs` should have length 2, where `inputs[1]` is the `mask`. The `mask` should be supplied as a Theano variable denoting whether each time step in each sequence in the batch is part of the sequence or not. `mask` should be a matrix of shape ``(n_batch, n_time_steps)`` where ``mask[i, j] = 1`` when ``j <= (length of sequence i)`` and ``mask[i, j] = 0`` when ``j > (length of sequence i)``. When the hidden state of this layer is to be pre-filled (i.e. was set to a :class:`Layer` instance) `inputs` should have length at least 2, and `inputs[-1]` is the hidden state to prefill with. When the cell state of this layer is to be pre-filled (i.e. was set to a :class:`Layer` instance) `inputs` should have length at least 2, and `inputs[-1]` is the hidden state to prefill with. When both the cell state and the hidden state are being pre-filled `inputs[-2]` is the hidden state, while `inputs[-1]` is the cell state. Returns ------- hid_out : theano.TensorType Symbolic output variable. cell_out : theano.TensorType Symbolic output variable. """ cell_out, hid_out = self.__lstm_fun__(inputs, **kwargs) # When it is requested that we only return the final sequence step, # we need to slice it out immediately after scan is applied if self.only_return_final: hid_out = hid_out[-1] cell_out = cell_out[-1] else: # dimshuffle back to (n_batch, n_time_steps, n_features)) hid_out = hid_out.dimshuffle(1, 0, 2) cell_out = cell_out.dimshuffle(1, 0, 2) # if scan is backward reverse the output if self.backwards: hid_out = hid_out[:, ::-1] cell_out = cell_out[:, ::-1] return hid_out, cell_out
