Keras/TensorFlow 中,call(self, inputs, training=None, **kwargs)的使用说明

在 Keras/TensorFlow 中,call(self, inputs, training=None, **kwargs) 是自定义层(Layer 子类)的核心方法,它定义了层的前向传播逻辑。以下是其工作原理的详细解析,分多个维度展开:


1. 核心作用

  • 前向传播‌:将输入张量 inputs 转换为输出张量。
  • 动态行为控制‌:通过 training 参数区分训练和推理模式(例如 Dropout、BatchNorm 层的行为差异)。
  • 扩展功能‌:通过 **kwargs 支持额外的参数(如 mask 用于序列模型)。

2. 参数详解

(1) inputs
  • 类型‌:单个张量(tf.Tensor)或张量列表/字典。
  • 作用‌:接收前一层的输出作为输入。
  • 示例‌:
    def call(self, inputs):
        # 假设 inputs 是单个张量
        return tf.matmul(inputs, self.weights) + self.bias
    
(2) training=None
NotImplementedError: Cannot convert a symbolic Tensor (lstm_1/strided_slice:0) to a numpy array. --------------------------------------------------------------------------- NotImplementedError Traceback (most recent call last) Cell In[20], line 51 48 start_time = time.time() 50 # 选择要训练的模型类型(rnn/lstm/gru) ---> 51 train_model(model_type='lstm') 53 # 计算总耗时 54 total_time = time.time() - start_time Cell In[20], line 13, in train_model(model_type) 11 model = build_gru_model() 12 else: # 默认使用LSTM ---> 13 model = build_lstm_model() 15 # 打印模型结构 16 model.summary() Cell In[16], line 2, in build_lstm_model() 1 def build_lstm_model(): ----> 2 model = keras.Sequential([ 3 layers.Embedding(total_words, embedding_len, input_length=max_review_len), 4 layers.LSTM(64, return_sequences=False), 5 layers.Dense(1, activation='sigmoid') 6 ]) 7 return model File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/training/tracking/base.py:457, in no_automatic_dependency_tracking.<locals>._method_wrapper(self, *args, **kwargs) 455 self._self_setattr_tracking = False # pylint: disable=protected-access 456 try: --> 457 result = method(self, *args, **kwargs) 458 finally: 459 self._self_setattr_tracking = previous_value # pylint: disable=protected-access File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/keras/engine/sequential.py:113, in Sequential.__init__(self, layers, name) 111 tf_utils.assert_no_legacy_layers(layers) 112 for layer in layers: --> 113 self.add(layer) File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/training/tracking/base.py:457, in no_automatic_dependency_tracking.<locals>._method_wrapper(self, *args, **kwargs) 455 self._self_setattr_tracking = False # pylint: disable=protected-access 456 try: --> 457 result = method(self, *args, **kwargs) 458 finally: 459 self._self_setattr_tracking = previous_value # pylint: disable=protected-access File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/keras/engine/sequential.py:195, in Sequential.add(self, layer) 190 self.inputs = layer_utils.get_source_inputs(self.outputs[0]) 192 elif self.outputs: 193 # If the model is being built continuously on top of an input layer: 194 # refresh its output. --> 195 output_tensor = layer(self.outputs[0]) 196 if len(nest.flatten(output_tensor)) != 1: 197 raise TypeError('All layers in a Sequential model ' 198 'should have a single output tensor. ' 199 'For multi-output layers, ' 200 'use the functional API.') File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/keras/layers/recurrent.py:623, in RNN.__call__(self, inputs, initial_state, constants, **kwargs) 617 inputs, initial_state, constants = _standardize_args(inputs, 618 initial_state, 619 constants, 620 self._num_constants) 622 if initial_state is None and constants is None: --> 623 return super(RNN, self).__call__(inputs, **kwargs) 625 # If any of `initial_state` or `constants` are specified and are Keras 626 # tensors, then add them to the inputs and temporarily modify the 627 # input_spec to include them. 629 additional_inputs = [] File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/keras/engine/base_layer.py:854, in Layer.__call__(self, inputs, *args, **kwargs) 852 outputs = base_layer_utils.mark_as_return(outputs, acd) 853 else: --> 854 outputs = call_fn(cast_inputs, *args, **kwargs) 856 except errors.OperatorNotAllowedInGraphError as e: 857 raise TypeError('You are attempting to use Python control ' 858 'flow in a layer that was not declared to be ' 859 'dynamic. Pass `dynamic=True` to the class ' 860 'constructor.\nEncountered error:\n"""\n' + 861 str(e) + '\n"""') File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/keras/layers/recurrent.py:2548, in LSTM.call(self, inputs, mask, training, initial_state) 2546 self.cell.reset_dropout_mask() 2547 self.cell.reset_recurrent_dropout_mask() -> 2548 return super(LSTM, self).call( 2549 inputs, mask=mask, training=training, initial_state=initial_state) File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/keras/layers/recurrent.py:681, in RNN.call(self, inputs, mask, training, initial_state, constants) 675 def call(self, 676 inputs, 677 mask=None, 678 training=None, 679 initial_state=None, 680 constants=None): --> 681 inputs, initial_state, constants = self._process_inputs( 682 inputs, initial_state, constants) 684 if mask is not None: 685 # Time step masks must be the same for each input. 686 # TODO(scottzhu): Should we accept multiple different masks? 687 mask = nest.flatten(mask)[0] File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/keras/layers/recurrent.py:798, in RNN._process_inputs(self, inputs, initial_state, constants) 796 initial_state = self.states 797 else: --> 798 initial_state = self.get_initial_state(inputs) 800 if len(initial_state) != len(self.states): 801 raise ValueError('Layer has ' + str(len(self.states)) + 802 ' states but was passed ' + str(len(initial_state)) + 803 ' initial states.') File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/keras/layers/recurrent.py:605, in RNN.get_initial_state(self, inputs) 603 dtype = inputs.dtype 604 if get_initial_state_fn: --> 605 init_state = get_initial_state_fn( 606 inputs=None, batch_size=batch_size, dtype=dtype) 607 else: 608 init_state = _generate_zero_filled_state(batch_size, self.cell.state_size, 609 dtype) File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/keras/layers/recurrent.py:2313, in LSTMCell.get_initial_state(self, inputs, batch_size, dtype) 2312 def get_initial_state(self, inputs=None, batch_size=None, dtype=None): -> 2313 return list(_generate_zero_filled_state_for_cell( 2314 self, inputs, batch_size, dtype)) File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/keras/layers/recurrent.py:2752, in _generate_zero_filled_state_for_cell(cell, inputs, batch_size, dtype) 2750 batch_size = array_ops.shape(inputs)[0] 2751 dtype = inputs.dtype -> 2752 return _generate_zero_filled_state(batch_size, cell.state_size, dtype) File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/keras/layers/recurrent.py:2768, in _generate_zero_filled_state(batch_size_tensor, state_size, dtype) 2765 return array_ops.zeros(init_state_size, dtype=dtype) 2767 if nest.is_sequence(state_size): -> 2768 return nest.map_structure(create_zeros, state_size) 2769 else: 2770 return create_zeros(state_size) File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/util/nest.py:536, in map_structure(func, *structure, **kwargs) 532 flat_structure = [flatten(s, expand_composites) for s in structure] 533 entries = zip(*flat_structure) 535 return pack_sequence_as( --> 536 structure[0], [func(*x) for x in entries], 537 expand_composites=expand_composites) File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/util/nest.py:536, in <listcomp>(.0) 532 flat_structure = [flatten(s, expand_composites) for s in structure] 533 entries = zip(*flat_structure) 535 return pack_sequence_as( --> 536 structure[0], [func(*x) for x in entries], 537 expand_composites=expand_composites) File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/keras/layers/recurrent.py:2765, in _generate_zero_filled_state.<locals>.create_zeros(unnested_state_size) 2763 flat_dims = tensor_shape.as_shape(unnested_state_size).as_list() 2764 init_state_size = [batch_size_tensor] + flat_dims -> 2765 return array_ops.zeros(init_state_size, dtype=dtype) File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/ops/array_ops.py:2338, in zeros(shape, dtype, name) 2334 if not isinstance(shape, ops.Tensor): 2335 try: 2336 # Create a constant if it won't be very big. Otherwise create a fill op 2337 # to prevent serialized GraphDefs from becoming too large. -> 2338 output = _constant_if_small(zero, shape, dtype, name) 2339 if output is not None: 2340 return output File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/ops/array_ops.py:2295, in _constant_if_small(value, shape, dtype, name) 2293 def _constant_if_small(value, shape, dtype, name): 2294 try: -> 2295 if np.prod(shape) < 1000: 2296 return constant(value, shape=shape, dtype=dtype, name=name) 2297 except TypeError: 2298 # Happens when shape is a Tensor, list with Tensor elements, etc. File <__array_function__ internals>:180, in prod(*args, **kwargs) File /opt/conda/lib/python3.8/site-packages/numpy/core/fromnumeric.py:3088, in prod(a, axis, dtype, out, keepdims, initial, where) 2970 @array_function_dispatch(_prod_dispatcher) 2971 def prod(a, axis=None, dtype=None, out=None, keepdims=np._NoValue, 2972 initial=np._NoValue, where=np._NoValue): 2973 """ 2974 Return the product of array elements over a given axis. 2975 (...) 3086 10 3087 """ -> 3088 return _wrapreduction(a, np.multiply, 'prod', axis, dtype, out, 3089 keepdims=keepdims, initial=initial, where=where) File /opt/conda/lib/python3.8/site-packages/numpy/core/fromnumeric.py:86, in _wrapreduction(obj, ufunc, method, axis, dtype, out, **kwargs) 83 else: 84 return reduction(axis=axis, out=out, **passkwargs) ---> 86 return ufunc.reduce(obj, axis, dtype, out, **passkwargs) File /opt/conda/lib/python3.8/site-packages/tensorflow_core/python/framework/ops.py:735, in Tensor.__array__(self) 734 def __array__(self): --> 735 raise NotImplementedError("Cannot convert a symbolic Tensor ({}) to a numpy" 736 " array.".format(self.name)) NotImplementedError: Cannot convert a symbolic Tensor (lstm_1/strided_slice:0) to a numpy array. + Code + Markdown ​ + Code + Markdown 4.使用训练好的模型预测文本类型 + Code + Markdown #选做 ​ + Code + Markdown keras关于fit方法中的参数定义如下 def fit(self, x=None, y=None, batch_size=None, epochs=1, verbose=‘auto’, callbacks=None, validation_split=0., validation_data=None, shuffle=True, class_weight=None, sample_weight=None, initial_epoch=0, steps_per_epoch=None, validation_steps=None, validation_batch_size=None, validation_freq=1, max_queue_size=10, workers=1, use_multiprocessing=False): + Code + Markdown
最新发布
06-22
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值