Keras 如何在不同形状的数据集上实现VGG网络？

我试图使用Fashion MNIST数据集使用VGG16模型的一部分进行迁移学习。数据处理和模型指定如下：

    data = keras.datasets.fashion_mnist
    (train_img, train_labels), (test_img, test_labels) = data.load_data()

    train_img.shape, train_labels.shape, test_img.shape, test_labels.shape
    #((60000, 28, 28), (60000,), (10000, 28, 28), (10000,))

    # transform to rgb as required by VGG
    train_img=tf.image.grayscale_to_rgb(tf.expand_dims(train_img, axis=3)) 
    test_img=tf.image.grayscale_to_rgb(tf.expand_dims(test_img, axis=3))

    #resize to minimum size of (32x32
    train_img=tf.image.resize_with_pad(train_img,32,32)
    test_img=tf.image.resize_with_pad(train_img,32,32)

    train_img = train_img / 255.
    test_img = test_img / 255.

    from keras.applications.vgg16 import preprocess_input
    train_img = tf.expand_dims(train_img, axis=0)
    test_img = tf.expand_dims(test_img, axis=0)

    #preprocessing as required by VGG16
    train_img=preprocess_input(train_img)
    test_img=preprocess_input(test_img)

    #using model without last layers
    vgg16=tf.keras.applications.VGG16(include_top=False, weights='imagenet', input_shape=(32,32,3))

    layer_dict = dict([(layer.name, layer) for layer in vgg16.layers])
    #stop at block3_pool and get output
    output = layer_dict['block3_pool'].output

    x = keras.layers.Flatten()(output)
    ...add some fully connected layers  here...
    x = keras.layers.Dense(10, activation='softmax')(x)

    final = keras.models.Model(inputs=vgg16.input, outputs=model)
    for layer in final.layers[:7]:
    layer.trainable = False

    final.fit(train_img, train_labels, epochs=50, validation_split=0.2)

当我尝试拟合模型时，会出现以下错误：

   UnboundLocalError Traceback (most recent call last)
<ipython-input-65-6a0b99b56337> in <module>()
      1 early_stopping_cb=keras.callbacks.EarlyStopping(patience=3, verbose=1,restore_best_weights=True)
----> 2 vgg16_1.fit(train_img, train_labels, epochs=50, validation_split=0.2, callbacks=[early_stopping_cb])

1 frames
/usr/local/lib/python3.6/dist-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, **kwargs)
    857               logs = tmp_logs  # No error, now safe to assign to logs.
    858               callbacks.on_train_batch_end(step, logs)
--> 859         epoch_logs = copy.copy(logs)
    860 
    861         # Run validation.

UnboundLocalError: local variable 'logs' referenced before assignment

UnboundLocalError回溯（最近一次调用）
在（）
1提前停止\u cb=keras.callbacks.earlystoping（耐心=3，详细=1，恢复\u最佳\u权重=True）
---->2 vgg16\u 1.fit（列车img、列车标签、历元=50、验证\u拆分=0.2、回调=[提前停止\u cb]）
1帧
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in-fit（self、x、y、批大小、历元、冗余、回调、验证拆分、验证数据、洗牌、类权重、样本权重、初始历元、每历元步数、验证步骤、验证批大小、验证频率、最大队列大小、工作者、使用多处理、**kwargs）
857日志=tmp#U日志#无错误，现在可以安全地分配给日志。
858回拨。在列车上批处理结束（步骤，日志）
-->859历元日志=复制。复制（日志）
860
861#运行验证。
UnboundLocalError:分配前引用的局部变量“logs”

我认为这可能是因为训练集形状有问题，但是如果我使用train_img[0]，它有形状（60000,32,32,3），那么我会得到以下错误：

ValueError Traceback (most recent call last)
<ipython-input-66-2b893ccd9ac9> in <module>()
      1 early_stopping_cb=keras.callbacks.EarlyStopping(patience=3, verbose=1,restore_best_weights=True)
----> 2 vgg16_1.fit(train_img[0], train_labels, epochs=50, validation_split=0.2, callbacks=[early_stopping_cb])

10 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self, *args, **kwargs)
     64   def _method_wrapper(self, *args, **kwargs):
     65     if not self._in_multi_worker_mode():  # pylint: disable=protected-access
---> 66       return method(self, *args, **kwargs)
     67 
     68     # Running inside `run_distribute_coordinator` already.

/usr/local/lib/python3.6/dist-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, **kwargs)
    849                 batch_size=batch_size):
    850               callbacks.on_train_batch_begin(step)
--> 851               tmp_logs = train_function(iterator)
    852               # Catch OutOfRangeError for Datasets of unknown size.
    853               # This blocks until the batch has finished executing.

/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
    578         xla_context.Exit()
    579     else:
--> 580       result = self._call(*args, **kwds)
    581 
    582     if tracing_count == self._get_tracing_count():

/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
    625       # This is the first call of __call__, so we have to initialize.
    626       initializers = []
--> 627       self._initialize(args, kwds, add_initializers_to=initializers)
    628     finally:
    629       # At this point we know that the initialization is complete (or less

/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
    504     self._concrete_stateful_fn = (
    505         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
--> 506             *args, **kwds))
    507 
    508     def invalid_creator_scope(*unused_args, **unused_kwds):

/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
   2444       args, kwargs = None, None
   2445     with self._lock:
-> 2446       graph_function, _, _ = self._maybe_define_function(args, kwargs)
   2447     return graph_function
   2448 

/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
   2775 
   2776       self._function_cache.missed.add(call_context_key)
-> 2777       graph_function = self._create_graph_function(args, kwargs)
   2778       self._function_cache.primary[cache_key] = graph_function
   2779       return graph_function, args, kwargs

/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   2665             arg_names=arg_names,
   2666             override_flat_arg_shapes=override_flat_arg_shapes,
-> 2667             capture_by_value=self._capture_by_value),
   2668         self._function_attributes,
   2669         # Tell the ConcreteFunction to clean up its graph once it goes out of

/usr/local/lib/python3.6/dist-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)
    979         _, original_func = tf_decorator.unwrap(python_func)
    980 
--> 981       func_outputs = python_func(*func_args, **func_kwargs)
    982 
    983       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
    439         # __wrapped__ allows AutoGraph to swap in a converted function. We give
    440         # the function a weak reference to itself to avoid a reference cycle.
--> 441         return weak_wrapped_fn().__wrapped__(*args, **kwds)
    442     weak_wrapped_fn = weakref.ref(wrapped_fn)
    443 

/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
    966           except Exception as e:  # pylint:disable=broad-except
    967             if hasattr(e, "ag_error_metadata"):
--> 968               raise e.ag_error_metadata.to_exception(e)
    969             else:
    970               raise

ValueError: in user code:

    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:571 train_function  *
        outputs = self.distribute_strategy.run(
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:951 run  **
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2290 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2649 _call_for_each_replica
        return fn(*args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:533 train_step  **
        y, y_pred, sample_weight, regularization_losses=self.losses)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:204 __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:143 __call__
        losses = self.call(y_true, y_pred)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:246 call
        return self.fn(y_true, y_pred, **self._fn_kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:1527 categorical_crossentropy
        return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py:4561 categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/tensor_shape.py:1117 assert_is_compatible_with
        raise ValueError("Shapes %s and %s are incompatible" % (self, other))

    ValueError: Shapes (32, 1) and (32, 10) are incompatible

ValueError回溯（最近一次调用）
在（）
1提前停止\u cb=keras.callbacks.earlystoping（耐心=3，详细=1，恢复\u最佳\u权重=True）
---->2 vgg16_1.拟合（序列img[0]，序列标签，历元=50，验证分割=0.2，回调=[early_stopping_cb]）
10帧
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in_method_包装（self，*args，**kwargs）
64定义方法包装（self，*args，**kwargs）：
65如果不是自己，则为多工作模式（）：#pylint:disable=受保护访问
--->66返回方法（self、*args、**kwargs）
67
68#已经在"运行分配协调器"内部运行。
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in-fit（self、x、y、批大小、历元、冗余、回调、验证拆分、验证数据、洗牌、类权重、样本权重、初始历元、每历元步数、验证步骤、验证批大小、验证频率、最大队列大小、工作者、使用多处理、**kwargs）
849批次大小=批次大小）：
850回拨。列车上批次开始（步骤）
-->851 tmp_日志=训练函数（迭代器）
852#捕获未知大小数据集的范围错误。
853#此块将一直阻塞，直到批处理完成执行。
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py在调用中（self，*args，**kwds）
578 xla_context.Exit（）
579其他：
-->580结果=自调用（*args，**kwds）
581
582如果跟踪计数==self.\u获取跟踪计数（）：
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in_调用（self，*args，**kwds）
625#这是u call u的第一个调用，因此我们必须初始化。
626初始值设定项=[]
-->627自我初始化（参数、KWD、添加初始化器到=初始化器）
628最后：
629#此时我们知道初始化已完成（或更少）
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in_initialize（self、args、kwds、add_initializer_to）
504自身.\u具体的\u有状态的\u fn=(
505 self._stateful_fn._get_concrete_function_internal_garbage_collected（#pylint:disable=受保护的访问
-->506*args，**科威特第纳尔）
507
508 def无效的创建者范围（*未使用的参数，**未使用的参数）：
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in\u get\u concrete\u function\u internal\u garbage\u collected（self，*args，**kwargs）
2444 args，kwargs=None，None
2445带自锁：
->2446图形函数，u，u=self._可能定义函数（args，kwargs）
2447返回图函数
2448
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py在函数（self、args、kwargs）中
2775
2776 self.\u function\u cache.missed.add（调用上下文键）
->2777图形函数=自身。创建图形函数（args、kwargs）
2778 self.\u function\u cache.primary[cache\u key]=图形函数
2779返回图_函数，args，kwargs
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py在创建图形函数（self、args、kwargs、override、flat、arg、shapes）中
2665 arg_name=arg_name，
2666覆盖平面形状=覆盖平面形状，
->2667按值捕获=自身。_按值捕获），
2668自我功能属性，
2669#告诉concrete函数在退出时清理其图形
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func\u graph.py从func\u py\u func（名称、python\u func、args、kwargs、签名、func\u图、autograph、autograph\u选项、添加控制依赖项、arg\u名称、op\u返回值、集合、按值捕获、覆盖平面arg\u形状）
979，original\u func=tf\u decorator.unwrap（python\u func）
980
-->981 func_outputs=python_func（*func_args，**func_kwargs）
982
983#不变量：`func_outputs`只包含张量、复合传感器、，
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in wrapped_fn（*args，**kwds）
439#uuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuu
440#函数对自身进行弱引用以避免引用循环。
-->441返回弱_-wrapped_-fn（）
442弱包裹fn=弱参考（wr
#train_img = tf.expand_dims(train_img, axis=0)
#test_img = tf.expand_dims(test_img, axis=0)