12345678900

Question

在model.fit这一步出现报错

我的代码为model.fit(X_train,Y_train,batch_size=600,epochs=1,verbose=1,validation_data=[X_test,Y_test])

对比了老师给的源代码一模一样

真愁人!

具体报错为

ValueError                                Traceback (most recent call last)
<ipython-input-16-960c89dbb231> in <module>
----> 1 model.fit(X_train,Y_train,batch_size=600,epochs=1,verbose=1,
      2           validation_data=[X_test,Y_test])

E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\keras\engine\training.py in _method_wrapper(self, *args, **kwargs)
    106   def _method_wrapper(self, *args, **kwargs):
    107     if not self._in_multi_worker_mode():  # pylint: disable=protected-access
--> 108       return method(self, *args, **kwargs)
    109 
    110     # Running inside `run_distribute_coordinator` already.

E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\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)
   1121                 model=self,
   1122                 steps_per_execution=self._steps_per_execution)
-> 1123           val_logs = self.evaluate(
   1124               x=val_x,
   1125               y=val_y,

E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\keras\engine\training.py in _method_wrapper(self, *args, **kwargs)
    106   def _method_wrapper(self, *args, **kwargs):
    107     if not self._in_multi_worker_mode():  # pylint: disable=protected-access
--> 108       return method(self, *args, **kwargs)
    109 
    110     # Running inside `run_distribute_coordinator` already.

E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\keras\engine\training.py in evaluate(self, x, y, batch_size, verbose, sample_weight, steps, callbacks, max_queue_size, workers, use_multiprocessing, return_dict)
   1377             with trace.Trace('TraceContext', graph_type='test', step_num=step):
   1378               callbacks.on_test_batch_begin(step)
-> 1379               tmp_logs = test_function(iterator)
   1380               if data_handler.should_sync:
   1381                 context.async_wait()

E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
    778       else:
    779         compiler = "nonXla"
--> 780         result = self._call(*args, **kwds)
    781 
    782       new_tracing_count = self._get_tracing_count()

E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
    812       # In this case we have not created variables on the first call. So we can
    813       # run the first trace but we should fail if variables are created.
--> 814       results = self._stateful_fn(*args, **kwds)
    815       if self._created_variables:
    816         raise ValueError("Creating variables on a non-first call to a function"

E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\eager\function.py in __call__(self, *args, **kwargs)
   2826     """Calls a graph function specialized to the inputs."""
   2827     with self._lock:
-> 2828       graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
   2829     return graph_function._filtered_call(args, kwargs)  # pylint: disable=protected-access
   2830 

E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
   3208           and self.input_signature is None
   3209           and call_context_key in self._function_cache.missed):
-> 3210         return self._define_function_with_shape_relaxation(args, kwargs)
   3211 
   3212       self._function_cache.missed.add(call_context_key)

E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\eager\function.py in _define_function_with_shape_relaxation(self, args, kwargs)
   3139           expand_composites=True)
   3140 
-> 3141     graph_function = self._create_graph_function(
   3142         args, kwargs, override_flat_arg_shapes=relaxed_arg_shapes)
   3143     self._function_cache.arg_relaxed[rank_only_cache_key] = graph_function

E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3063     arg_names = base_arg_names + missing_arg_names
   3064     graph_function = ConcreteFunction(
-> 3065         func_graph_module.func_graph_from_py_func(
   3066             self._name,
   3067             self._python_function,

E:\Software\Anaconda\envs\Env-CV\lib\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)
    984         _, original_func = tf_decorator.unwrap(python_func)
    985 
--> 986       func_outputs = python_func(*func_args, **func_kwargs)
    987 
    988       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
    598         # __wrapped__ allows AutoGraph to swap in a converted function. We give
    599         # the function a weak reference to itself to avoid a reference cycle.
--> 600         return weak_wrapped_fn().__wrapped__(*args, **kwds)
    601     weak_wrapped_fn = weakref.ref(wrapped_fn)
    602 

E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
    971           except Exception as e:  # pylint:disable=broad-except
    972             if hasattr(e, "ag_error_metadata"):
--> 973               raise e.ag_error_metadata.to_exception(e)
    974             else:
    975               raise

ValueError: in user code:

    E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\keras\engine\training.py:1224 test_function  *
        return step_function(self, iterator)
    E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\keras\engine\training.py:1215 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1211 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2585 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2945 _call_for_each_replica
        return fn(*args, **kwargs)
    E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\keras\engine\training.py:1208 run_step  **
        outputs = model.test_step(data)
    E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\keras\engine\training.py:1174 test_step
        y_pred = self(x, training=False)
    E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:975 __call__
        input_spec.assert_input_compatibility(self.input_spec, inputs,
    E:\Software\Anaconda\envs\Env-CV\lib\site-packages\tensorflow\python\keras\engine\input_spec.py:155 assert_input_compatibility
        raise ValueError('Layer ' + layer_name + ' expects ' +

    ValueError: Layer sequential expects 1 inputs, but it received 2 input tensors. Inputs received: [<tf.Tensor 'IteratorGetNext:0' shape=(100, 28, 28, 1) dtype=float32>, <tf.Tensor 'IteratorGetNext:1' shape=(100, 10) dtype=float32>]

Answer 1

让阿豪来帮你解答，本回答参考chatgpt3.5编写提供，如果还有疑问可以评论或留言

报错信息显示在model.fit这一步出现了ValueError，可能是因为参数传递有误。在您提供的代码中，您使用的是validation_data参数的赋值表达式是[...]，然而应该是元组(...)。 正确的写法是：

model.fit(X_train, Y_train, batch_size=600, epochs=1, verbose=1, validation_data=(X_test, Y_test))

您可以修改代码后再次运行，应该能够解决这个报错问题。 案例如下：

import numpy as np
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
# 构造训练和测试数据
X_train = np.random.rand(100, 10)
Y_train = np.random.randint(0, 2, size=(100, 1))
X_test = np.random.rand(20, 10)
Y_test = np.random.randint(0, 2, size=(20, 1))
# 创建模型
model = Sequential()
model.add(Dense(32, input_shape=(10,), activation='relu'))
model.add(Dense(1, activation='sigmoid'))
# 编译模型
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
# 模型训练
model.fit(X_train, Y_train, batch_size=32, epochs=3, verbose=1, validation_data=(X_test, Y_test))

在这个例子中，创建了一个简单的神经网络模型，并使用正确的validation_data参数传递方式进行了模型训练。您可以参考这个例子来调整您的代码，并解决报错问题。