keras.fit_generator KeyError: '"小'

Posted 2023-02-15

【中文标题】keras.fit_generator KeyError: \'"小\'

【英文标题】：keras.fit_generator KeyError: '"Small'keras.fit_generator KeyError: '"小'

【发布时间】：2022-01-19 18:36:21

【问题描述】：

我正在学习计算机视觉并尝试制作一个图像标题项目，我使用了来自 github 的这段代码，但我遇到了一个问题 谁能帮我解决这个错误：

当我运行这一行时：

***final_model.fit_generator(data_generator(batch_size=128), steps_per_epoch=samples_epoch, epochs=1, verbose=2)***

我明白了：

ValueError Traceback（最近一次调用最后一次） /tmp/ipykernel_34/3613360633.py 在 1 final_model.fit_generator(data_generator(batch_size=128)，steps_per_epoch=samples_epoch， ----> 2 epochs=1，详细=2)

/opt/conda/lib/python3.7/site-packages/keras/engine/training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
   1987         use_multiprocessing=use_multiprocessing,
   1988         shuffle=shuffle,
-> 1989         initial_epoch=initial_epoch)
   1990 
   1991   @doc_controls.do_not_generate_docs

/opt/conda/lib/python3.7/site-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1182                 _r=1):
   1183               callbacks.on_train_batch_begin(step)
-> 1184               tmp_logs = self.train_function(iterator)
   1185               if data_handler.should_sync:
   1186                 context.async_wait()

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
    883 
    884       with OptionalXlaContext(self._jit_compile):
--> 885         result = self._call(*args, **kwds)
    886 
    887       new_tracing_count = self.experimental_get_tracing_count()

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
    922       # In this case we have not created variables on the first call. So we can
    923       # run the first trace but we should fail if variables are created.
--> 924       results = self._stateful_fn(*args, **kwds)
    925       if self._created_variables and not ALLOW_DYNAMIC_VARIABLE_CREATION:
    926         raise ValueError("Creating variables on a non-first call to a function"

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/function.py in __call__(self, *args, **kwargs)
   3036     with self._lock:
   3037       (graph_function,
-> 3038        filtered_flat_args) = self._maybe_define_function(args, kwargs)
   3039     return graph_function._call_flat(
   3040         filtered_flat_args, captured_inputs=graph_function.captured_inputs)  # pylint: disable=protected-access

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
   3458               call_context_key in self._function_cache.missed):
   3459             return self._define_function_with_shape_relaxation(
-> 3460                 args, kwargs, flat_args, filtered_flat_args, cache_key_context)
   3461 
   3462           self._function_cache.missed.add(call_context_key)

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/function.py in _define_function_with_shape_relaxation(self, args, kwargs, flat_args, filtered_flat_args, cache_key_context)
   3380 
   3381     graph_function = self._create_graph_function(
-> 3382         args, kwargs, override_flat_arg_shapes=relaxed_arg_shapes)
   3383     self._function_cache.arg_relaxed[rank_only_cache_key] = graph_function
   3384 

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3306             arg_names=arg_names,
   3307             override_flat_arg_shapes=override_flat_arg_shapes,
-> 3308             capture_by_value=self._capture_by_value),
   3309         self._function_attributes,
   3310         function_spec=self.function_spec,

/opt/conda/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes, acd_record_initial_resource_uses)
   1005         _, original_func = tf_decorator.unwrap(python_func)
   1006 
-> 1007       func_outputs = python_func(*func_args, **func_kwargs)
   1008 
   1009       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
    666         # the function a weak reference to itself to avoid a reference cycle.
    667         with OptionalXlaContext(compile_with_xla):
--> 668           out = weak_wrapped_fn().__wrapped__(*args, **kwds)
    669         return out
    670 

/opt/conda/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
    992           except Exception as e:  # pylint:disable=broad-except
    993             if hasattr(e, "ag_error_metadata"):
--> 994               raise e.ag_error_metadata.to_exception(e)
    995             else:
    996               raise

ValueError: in user code:

    /opt/conda/lib/python3.7/site-packages/keras/engine/training.py:853 train_function  *
        return step_function(self, iterator)
    /opt/conda/lib/python3.7/site-packages/keras/engine/training.py:842 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/distribute/distribute_lib.py:1286 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/distribute/distribute_lib.py:2849 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/distribute/distribute_lib.py:3632 _call_for_each_replica
        return fn(*args, **kwargs)
    /opt/conda/lib/python3.7/site-packages/keras/engine/training.py:835 run_step  **
        outputs = model.train_step(data)
    /opt/conda/lib/python3.7/site-packages/keras/engine/training.py:787 train_step
        y_pred = self(x, training=True)
    /opt/conda/lib/python3.7/site-packages/keras/engine/base_layer.py:1020 __call__
        input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
    /opt/conda/lib/python3.7/site-packages/keras/engine/input_spec.py:202 assert_input_compatibility
        ' input tensors. Inputs received: ' + str(inputs))

    ValueError: Layer model_1 expects 2 input(s), but it received 3 input tensors. Inputs received: [<tf.Tensor 'IteratorGetNext:0' shape=(None, None) dtype=float32>, <tf.Tensor 'IteratorGetNext:1' shape=(None, None) dtype=int32>, <tf.Tensor 'IteratorGetNext:2' shape=(None, None) dtype=float32>]

这是 data_generator 函数：

***def data_generator(batch_size = 32):
        partial_caps = []
        next_words = []
        images = []
        
        df = pd.read_csv('flickr8k_training_dataset.txt', delimiter='\t')
        df = df.sample(frac=1)
        iter = df.iterrows()
        c = []
        imgs = []
        for i in range(df.shape[0]):
            x = next(iter)
            c.append(x[1][1])
            imgs.append(x[1][0])


        count = 0
        while True:
            for j, text in enumerate(c):
                current_image = encoding_train[imgs[j]]
                for i in range(len(text.split())-1):
                    count+=1
                    
                    partial = [word2idx[txt] for txt in text.split()[:i+1]]
                    partial_caps.append(partial)
                    
                    # Initializing with zeros to create a one-hot encoding matrix
                    # This is what we have to predict
                    # Hence initializing it with vocab_size length
                    n = np.zeros(vocab_size)
                    # Setting the next word to 1 in the one-hot encoded matrix
                    n[word2idx[text.split()[i+1]]] = 1
                    next_words.append(n)
                    
                    images.append(current_image)
                    
                    if count>=batch_size:
                        next_words = np.asarray(next_words)
                        images = np.asarray(images)
                        partial_caps = sequence.pad_sequences(partial_caps, maxlen=max_len, padding='post')
                        yield [[images, partial_caps], next_words]
                        partial_caps = []
                        next_words = []
                        images = []
                        count = 0***

【问题讨论】：

我也得到了这个：ValueError：Layer model_1 需要 2 个输入，但它接收到 3 个输入张量。收到的输入：[, , ]

欢迎来到 SO。请更新您的问题（正文）而不是对其发表评论，

【参考方案1】：

如您所见，错误是：

ValueError: 层 model_1 需要 2 个输入，但它收到 3 个输入 张量。

变化：

yield [[images, partial_caps], next_words]

到

yield [images, partial_caps], next_words

所以它应该可以工作