图片生成器错误：要求检索元素0，但序列的长度为0 我的问题是：我得到了错误：我生成错误的代码是：

问题描述

• 我正在尝试计算二元类彩色图像分类问题中的正，真负，假正，假负比率。

• 我有二进制类，面部和背景彩色图像，并且必须使用MLP对其进行分类。

我的问题是：我得到了错误：

ValueError：要求检索元素0，但序列的长度为0

编辑：完全追溯

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self,*args,**kwargs)
    128       raise ValueError('{} is not supported in multi-worker mode.'.format(
    129           method.__name__))
--> 130     return method(self,**kwargs)
    131 
    132   return tf_decorator.make_decorator(

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in predict(self,x,batch_size,verbose,steps,callbacks,max_queue_size,workers,use_multiprocessing)
   1577           use_multiprocessing=use_multiprocessing,1578           model=self,-> 1579           steps_per_execution=self._steps_per_execution)
   1580 
   1581       # 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,y,sample_weight,steps_per_epoch,initial_epoch,epochs,shuffle,class_weight,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,sample_weights,**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,**kwargs)
    784     # Since we have to kNow the dtype of the python generator when we build the
    785     # dataset,we have to look at a batch to infer the structure.
--> 786     peek,x = self._peek_and_restore(x)
    787     peek = self._standardize_batch(peek)
    788     peek = _process_tensorlike(peek)

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/data_adapter.py in _peek_and_restore(x)
    918   @staticmethod
    919   def _peek_and_restore(x):
--> 920     return x[0],x
    921 
    922   def _handle_multiprocessing(self,/usr/local/lib/python3.6/dist-packages/keras_preprocessing/image/iterator.py in __getitem__(self,idx)
     55                              'but the Sequence '
     56                              'has length {length}'.format(idx=idx,---> 57                                                           length=len(self)))
     58         if self.seed is not None:
     59             np.random.seed(self.seed + self.total_batches_seen)

ValueError: Asked to retrieve element 0,but the Sequence has length 0

• 尝试分别从2个类别中预测每个文件夹时（（而不是包含2个文件夹的根文件夹，在培训中每个类别一个））。

我生成错误的代码是：

test_face_dir = "/content/test/TESTSET/face"
test_background_dir = "/content/test/TESTSET/background"
# Face DG
test_datagen_face = ImageDataGenerator(rescale=1./255)

test_generator_face = test_datagen_face.flow_from_directory(
    test_face_dir,target_size=img_window[:2],batch_size=batch_size,class_mode='binary',color_mode='rgb'
    )
# Background DG
test_datagen_background = ImageDataGenerator(rescale=1./255)

test_generator_background = test_datagen_background.flow_from_directory(
    test_background_dir,color_mode='rgb'
    )
#-----------------------------------------
prediction_face = simpleMLP.predict(test_generator_face)
prediction_background = simpleMLP.predict(test_generator_background)
#-----------------------------------------
# th = 0.5 #threshold
# Face
prediction_face[prediction_face>=th]=1 
prediction_face[prediction_face<th]=0
pred_face = np.squeeze(prediction_face)
print('pred shape: ',pred_face.shape,int(np.sum(pred_face)))
# Background
prediction_background[prediction_background>=th]=1 
prediction_background[prediction_background<th]=0
pred_background = np.squeeze(prediction_background)
print('pred shape: ',pred_background.shape,int(np.sum(pred_background)))

解决方法

生成错误是因为我正在使用html { font-size: 62.5%; background-color: var(--color-tertiary); overflow-x: hidden; // My svg is really big and it overflows page,so I need to use this } /***************** HEADER **********************/ .header{ width: 100vw; height: 100vh; background-position: center; background-size: cover; position: relative; &__logo{ // this is the svg position: absolute; top: 0; left: 30rem; width: 180rem; z-index: -1; // I use z-index to make sure that moving svg is in the background of the page -webkit-animation:spin 4s linear infinite; -moz-animation:spin 4s linear infinite; animation:spin 500s linear infinite; @-moz-keyframes spin { 100% { -moz-transform: rotate(360deg); } } @-webkit-keyframes spin { 100% { -webkit-transform: rotate(360deg); } } @keyframes spin { 100% { -webkit-transform: rotate(360deg);} } } &__wrapper{ z-index: 10; } } ，而我在其中指定的是一个图像文件夹而不是两个文件夹人脸和背景就我而言，当我选择包含两个文件夹的父文件夹时，这个问题就消失了。

任何一种计算真阳性，真阴性，假阳性，假阴性的方法地面真相如下：

class_mode='binary'