ValueError: Argument must be a dense tensor:... got shape [6, 60, 160, 3], but wanted [6].

在将 列表或元组 数据转换成 dataset类型时

 

import numpy as np import tensorflow as tffrom sklearn.cross_validation import train_test_split

 

pic_array=np.ones((60,160,3)) #图片的长宽为60*160，每个像素点的由rgb3个值表示像素pic_txt_array=np.ones((26,4)) #表示单个字母的向量长为26，共4个字母data_x=[pic_array  for i in range(1000)] #1000张图片的集合data_y=[pic_txt_array for i in range(1000)]#1000长图片对应的字母的集合

#将装着样本的列表 转换成dataset格式train_dataset=tf.data.Dataset.from_tensor_slices((data_x,data_y))

 

发生异常：

File "tf_test.py", line 10, in <module>train_dataset=tf.data.Dataset.from_tensor_slices((data_x,data_y)) File "F:\Program Files\Python35\lib\site-packages\tensorflow\python\data\ops\dataset_ops.py", line 235, in from_tensor_slices return TensorSliceDataset(tensors) File "F:\Program Files\Python35\lib\site-packages\tensorflow\python\data\ops\dataset_ops.py", line 1030, in __init__ for i, t in enumerate(nest.flatten(tensors))........ File "F:\Program Files\Python35\lib\site-packages\tensorflow\python\framework\constant_op.py", line 214, in constant value, dtype=dtype, shape=shape, verify_shape=verify_shape)) File "F:\Program Files\Python35\lib\site-packages\tensorflow\python\framework\tensor_util.py", line 441, in make_tensor_proto _GetDenseDimensions(values)))ValueError: Argument must be a dense tensor: [array([[[1., 1., 1.],...

..., [1., 1., 1.], [1., 1., 1.], [1., 1., 1.]]])] - got shape [6, 60, 160, 3], but wanted [6].

 

解决：修改源数据的格式

 

data_x=np.asarray([pic_array for i in range(1000)]) #1000张图片的集合data_y=np.asarray([pic_txt_array for i in range(1000)]) #1000长图片对应的字母的集合

 

转载于:https://www.cnblogs.com/Ting-light/p/9239404.html