Python 尝试执行model.fit（）时出现ValueError-：无法将NumPy数组转换为张量（不支持的对象类型NumPy.ndarray）

我正在尝试为边界盒回归训练网络。我创建了pd.DataFrame，如下所示：

以下是我的列车和验证图像生成器：

image_generator = tf.keras.preprocessing.image.ImageDataGenerator(
                                  rescale = 1./255,
                                  rotation_range = 25,
                                  zoom_range=[0.8, 1.2],
                                  vertical_flip=True,
                                  horizontal_flip=True,
                                  )
train_generator = image_generator.flow_from_dataframe(
            dataframe=train_df,
            directory=cbis_ddsm_train_images_dir,
            x_col="image file path",
            y_col="coordinates",
            class_mode="raw",
            batch_size=BATCH_SIZE,
            shuffle=True,
            seed=1,
            color_mode="grayscale",
            target_size=(1024, 1024))

val_gen = tf.keras.preprocessing.image.ImageDataGenerator(
                                  rescale = 1./255,
                                  )

val_generator = val_gen.flow_from_dataframe(
            dataframe=val_df,
            directory=cbis_ddsm_train_images_dir,
            x_col="image file path",
            y_col=None,
            class_mode="raw",
            batch_size=BATCH_SIZE,
            shuffle=False,
            seed=1,
            color_mode="grayscale",
             target_size=(1024, 1024))

请注意，我已将列表中的Y列（即bbox坐标）转换为numpy维度数组，如下所示：

for idx, row in train_df.iterrows():
  height, width = row['size']
  row['coordinates'] = np.asarray([normalize_bbox(c, height, width) for c in row['coordinates']][0]).astype('float32')

当我尝试执行以下代码时：

opt = Adam(lr=INIT_LR)
final_model.compile(optimizer=opt, loss="mse")
    
final_model.fit(train_generator, steps_per_epoch=steps_per_epoch, epochs=3,
                    validation_data=val_generator, validation_steps=val_steps, verbose=1)

我收到以下错误消息：

ValueError                                Traceback (most recent call last)
<ipython-input-46-90f3a1cd9c87> in <module>()
      8 
      9     final_model.fit(train_generator, steps_per_epoch=steps_per_epoch, epochs=3,
---> 10                     validation_data=val_generator, validation_steps=val_steps, verbose=1)
     11     final_model.save(os.path.join(experiment1_dir, "resnet_fine-tuned-head.h5"))
     12 

14 frames
/usr/local/lib/python3.6/dist-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.

/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)
   1061           use_multiprocessing=use_multiprocessing,
   1062           model=self,
-> 1063           steps_per_execution=self._steps_per_execution)
   1064 
   1065       # Container that configures and calls `tf.keras.Callback`s.

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/data_adapter.py in __init__(self, x, y, sample_weight, batch_size, steps_per_epoch, initial_epoch, epochs, shuffle, class_weight, max_queue_size, workers, use_multiprocessing, model, steps_per_execution)
   1115         use_multiprocessing=use_multiprocessing,
   1116         distribution_strategy=ds_context.get_strategy(),
-> 1117         model=model)
   1118 
   1119     strategy = ds_context.get_strategy()

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/data_adapter.py in __init__(self, x, y, sample_weights, shuffle, workers, use_multiprocessing, max_queue_size, model, **kwargs)
    914         max_queue_size=max_queue_size,
    915         model=model,
--> 916         **kwargs)
    917 
    918   @staticmethod

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/data_adapter.py in __init__(self, x, y, sample_weights, workers, use_multiprocessing, max_queue_size, model, **kwargs)
    786     peek, x = self._peek_and_restore(x)
    787     peek = self._standardize_batch(peek)
--> 788     peek = _process_tensorlike(peek)
    789 
    790     # Need to build the Model on concrete input shapes.

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/data_adapter.py in _process_tensorlike(inputs)
   1019     return x
   1020 
-> 1021   inputs = nest.map_structure(_convert_numpy_and_scipy, inputs)
   1022   return nest.list_to_tuple(inputs)
   1023 

/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/nest.py in map_structure(func, *structure, **kwargs)
    633 
    634   return pack_sequence_as(
--> 635       structure[0], [func(*x) for x in entries],
    636       expand_composites=expand_composites)
    637 

/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/nest.py in <listcomp>(.0)
    633 
    634   return pack_sequence_as(
--> 635       structure[0], [func(*x) for x in entries],
    636       expand_composites=expand_composites)
    637 

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/data_adapter.py in _convert_numpy_and_scipy(x)
   1014       if issubclass(x.dtype.type, np.floating):
   1015         dtype = backend.floatx()
-> 1016       return ops.convert_to_tensor(x, dtype=dtype)
   1017     elif scipy_sparse and scipy_sparse.issparse(x):
   1018       return _scipy_sparse_to_sparse_tensor(x)

/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py in convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, dtype_hint, ctx, accepted_result_types)
   1497 
   1498     if ret is None:
-> 1499       ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
   1500 
   1501     if ret is NotImplemented:

/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/tensor_conversion_registry.py in _default_conversion_function(***failed resolving arguments***)
     50 def _default_conversion_function(value, dtype, name, as_ref):
     51   del as_ref  # Unused.
---> 52   return constant_op.constant(value, dtype, name=name)
     53 
     54 

/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/constant_op.py in constant(value, dtype, shape, name)
    262   """
    263   return _constant_impl(value, dtype, shape, name, verify_shape=False,
--> 264                         allow_broadcast=True)
    265 
    266 

/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/constant_op.py in _constant_impl(value, dtype, shape, name, verify_shape, allow_broadcast)
    273       with trace.Trace("tf.constant"):
    274         return _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
--> 275     return _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
    276 
    277   g = ops.get_default_graph()

/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/constant_op.py in _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
    298 def _constant_eager_impl(ctx, value, dtype, shape, verify_shape):
    299   """Implementation of eager constant."""
--> 300   t = convert_to_eager_tensor(value, ctx, dtype)
    301   if shape is None:
    302     return t

/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/constant_op.py in convert_to_eager_tensor(value, ctx, dtype)
     96       dtype = dtypes.as_dtype(dtype).as_datatype_enum
     97   ctx.ensure_initialized()
---> 98   return ops.EagerTensor(value, ctx.device_name, dtype)
     99 
    100 

ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type numpy.ndarray).

ValueError回溯（最近一次调用）
在（）
8.
9最终模型拟合（列车发电机，每个历元的步数=每个历元的步数，历元=3，
--->10验证\u数据=val\u生成器，验证\u步骤=val\u步骤，详细信息=1）
11最终的模型保存（os.path.join（experiment1\u dir，“resnet\u fine-tuned-head.h5”））
12
14帧
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in_method_包装（self，*args，**kwargs）
106定义方法包装（self，*args，**kwargs）：
107如果不是self._处于_multi_worker_模式（）：#pylint:disable=受保护的访问
-->108返回方法（self、*args、**kwargs）
109
110#已经在“运行分配协调器”内部运行了。
/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、无序、类权重、样本权重、初始历元、每历元的步长、验证步骤、验证批量大小、验证队列频率、最大大小、工作人员、使用多处理）
1061使用多处理=使用多处理，
1062型号=自我，
->1063步每执行=自。_步每执行）
1064
1065#配置和调用`tf.keras.Callback`的容器。
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/data\u adapter.py in\uuuuuu init\uuuuuuuuu（self，x，y，sample\u weight，batch\u size，steps\u per\u epoch，initial\u epoch，epoch，shuffle，class\u weight，max\u queue\u size，worker，use\u多处理，model，steps\u per\u执行）
1115使用多处理=使用多处理，
1116 distribution_strategy=ds_context.get_strategy（），
->1117型号=型号）
1118
1119 strategy=ds_context.get_strategy（）
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/data\u adapter.py in\uuuuuuu init\uuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuu
914最大队列大小=最大队列大小，
915型号=型号，
-->916**夸尔格）
917
918@staticmethod
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/data\u adapter.py in\uuuuuuu init\uuuuuuuuu（self，x，y，sample\u权重，worker，use\u多处理，最大队列大小，模型，**kwargs）
786窥视，x=自。窥视和还原（x）
787 peek=自标准化批次（peek）
-->788 peek=_过程_张力状（peek）
789
790#需要在具体的输入形状上构建模型。
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/data\u adapter.py in\u process\u tensorlike（输入）
1019返回x
1020
->1021 inputs=nest.map\u结构（\u convert\u numpy\u和\u scipy，inputs）
1022返回嵌套。列表到元组（输入）
1023
/映射结构中的usr/local/lib/python3.6/dist-packages/tensorflow/python/util/nest.py（func，*structure，**kwargs）
633
634返回包\u序列\u组件(
-->635结构[0]，[func（*x）表示条目中的x]，
636扩展_复合材料=扩展_复合材料）
637
/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/nest.py in（.0）
633
634返回包\u序列\u组件(
-->635结构[0]，[func（*x）表示条目中的x]，
636扩展_复合材料=扩展_复合材料）
637
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/data\u adapter.py in\u convert\u numpy\u和\u scipy（x）
1014如果issubclass（x.dtype.type，np.floating）：
1015 dtype=backend.floatx（）
->1016返回运算。将\u转换为\u张量（x，dtype=dtype）
1017 elif scipy_sparse和scipy_sparse.issparse（x）：
1018返回稀疏张量（x）
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py in convert_to_tensor（值、数据类型、名称、as_ref、首选数据类型、数据类型提示、ctx、接受的结果类型）
1497
1498如果ret为无：
->1499 ret=conversion\u func（值，dtype=dtype，name=name，as\u ref=as\u ref）
1500
1501如果未实施ret：
/函数中的usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/tensor\u conversion\u registry.py（***解析参数失败***）
50 def默认转换函数（值、数据类型、名称，作为参考）：
51 del as_ref#未使用。
--->52返回常量\运算常量（值，数据类型，名称=名称）
53
54
/常量中的usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/constant_op.py（值、数据类型、形状、名称）
262   """
263返回\u常量\u impl（值、数据类型、形状、名称、验证\u形状=False，
-->264允许_广播=真）
265
266
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/constant\u op.py in\u constant\u impl（值、数据类型、形状、名称、验证形状、允许广播）
273带有trace.trace（“tf.constant”）：
274返回_常量_eager _impl（ctx、值、数据类型、形状、验证形状）
-->275返回_常量_eager _impl（ctx、值、数据类型、形状、验证形状）
276
277 g=ops.get\u default\u graph（）
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/constant\u op.py in\u constant\u eager\u impl（ctx、值、数据类型、形状、验证形状）
298定义常量（ctx、值、数据类型、形状、验证形状）：
299“急切常数的实现”
-->300 t=转换为张量（值，ctx，数据类型
train_generator._targets = np.stack(train_generator._targets)
val_generator._targets = np.stack(val_generator._targets)