ValueError：检查目标时出错：预期 main_prediction 有 3 个维度，但得到了形状为 (1128, 1) 的数组答案

【问题标题】：ValueError: Error when checking target: expected main_prediction to have 3 dimensions, but got array with shape (1128, 1)ValueError：检查目标时出错：预期 main_prediction 有 3 个维度，但得到了形状为 (1128, 1) 的数组
【发布时间】：2019-09-11 04:20:19
【问题描述】：

我正在尝试将使用 Python2.7 和 Keras 1.x 的旧代码改编为 Python3.7.3 和 Keras 2.2.4 和 TensorFlow 1.13.1。以下是代码的外观：

from keras.layers import Input, add, Dense, Flatten, concatenate
from keras import activations
from keras import models
from keras import backend as K
import numpy as np

import utils
from NGF.preprocessing import tensorise_smiles, tensorise_smiles_mp
from NGF.layers import NeuralGraphHidden, NeuralGraphOutput
from NGF.models import build_graph_conv_model
from NGF.sparse import GraphTensor, EpochIterator

# ==============================================================================
# ================================ Load the data ===============================
# ==============================================================================
print("{:=^100}".format(' Data preprocessing '))
data, labels = utils.load_delaney()

# Tensorise data
X_atoms, X_bonds, X_edges = tensorise_smiles_mp(data)
print('Atoms:', X_atoms.shape)
print('Bonds:', X_bonds.shape)
print('Edges:', X_edges.shape)

# Load sizes from data shape
num_molecules = X_atoms.shape[0]
max_atoms = X_atoms.shape[1]
max_degree = X_bonds.shape[2]
num_atom_features = X_atoms.shape[-1]
num_bond_features = X_bonds.shape[-1]

# ==============================================================================
# =============== Example 1: Building a 3-layer graph convnet  =================
# ==============================================================================
print("{:=^100}".format(' Example 1 '))

# Parameters
conv_width = 8
fp_length = 62

# Define the input layers
atoms0 = Input(name='atom_inputs', shape=(max_atoms, num_atom_features))
bonds = Input(name='bond_inputs', shape=(max_atoms, max_degree, num_bond_features))
edges = Input(name='edge_inputs', shape=(max_atoms, max_degree), dtype='int32')
print("DEBUG: edges=", K.print_tensor(edges))

# Define the convoluted atom feature layers
atoms1 = NeuralGraphHidden(conv_width, activation='relu', use_bias=False)([atoms0, bonds, edges])
atoms2 = NeuralGraphHidden(conv_width, activation='relu', use_bias=False)([atoms1, bonds, edges])

# Define the outputs of each (convoluted) atom feature layer to fingerprint
fp_out0 = NeuralGraphOutput(fp_length, activation='softmax')([atoms0, bonds, edges])
fp_out1 = NeuralGraphOutput(fp_length, activation='softmax')([atoms1, bonds, edges])
fp_out2 = NeuralGraphOutput(fp_length, activation='softmax')([atoms2, bonds, edges])

# Flatten the input before the Dense layer by summing the 3 outputs to obtain fingerprint
# final_fp = merge([fp_out0, fp_out1, fp_out2], mode='sum') # Old Keras 1.x syntax
print("DEBUG: fp_out0.get_shape()=", fp_out0.get_shape())
print("DEBUG: fp_out1.get_shape()=", fp_out1.get_shape())
print("DEBUG: fp_out2.get_shape()=", fp_out2.get_shape())
# final_fp = add([fp_out0, fp_out1, fp_out2])
final_fp = concatenate([fp_out0, fp_out1, fp_out2])
print("DEBUG: final_fp.get_shape()=", final_fp.get_shape())

# Build and compile model for regression.
main_pred = Dense(1, activation='linear', name='main_prediction')(final_fp)
print("DEBUG: main_pred.get_shape()=", main_pred.get_shape())
model = models.Model(inputs=[atoms0, bonds, edges], outputs=[main_pred])
model.compile(optimizer='adagrad', loss='mse')

# Show summary
model.summary()

# Train the model
print("DEBUG: labels.shape", labels.shape)
model.fit(x=[X_atoms, X_bonds, X_edges], y=labels, epochs=20, batch_size=32, validation_split=0.2)

本质上它是一个定制的卷积神经网络，它以 3 个不同的可变维度数组作为输入并返回一个标量预测。这是我执行时的输出：

======================================== Data preprocessing ========================================
Tensorising molecules in batches...
1128/1128 [==================================================] - 1s 740us/step
Merging batch tensors...    [DONE]
Atoms: (1128, 55, 62)
Bonds: (1128, 55, 5, 6)
Edges: (1128, 55, 5)
============================================ Example 1 =============================================
DEBUG: edges= Tensor("Print:0", shape=(?, 55, 5), dtype=int32)
DEBUG: fp_out0.get_shape()= (?, 62)
DEBUG: fp_out1.get_shape()= (?, 62)
DEBUG: fp_out2.get_shape()= (?, 62)
DEBUG: final_fp.get_shape()= (?, 186)
DEBUG: main_pred.get_shape()= (?, 1)
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
atom_inputs (InputLayer)        (None, 55, 62)       0                                            
__________________________________________________________________________________________________
bond_inputs (InputLayer)        (None, 55, 5, 6)     0                                            
__________________________________________________________________________________________________
edge_inputs (InputLayer)        (None, 55, 5)        0                                            
__________________________________________________________________________________________________
neural_graph_hidden_1 (NeuralGr [(None, 55, 62), (No 2720        atom_inputs[0][0]                
                                                                 bond_inputs[0][0]                
                                                                 edge_inputs[0][0]                
__________________________________________________________________________________________________
neural_graph_hidden_2 (NeuralGr [(None, 55, 62), (No 2720        neural_graph_hidden_1[0][0]      
                                                                 bond_inputs[0][0]                
                                                                 edge_inputs[0][0]                
__________________________________________________________________________________________________
neural_graph_output_1 (NeuralGr [(None, 55, 62), (No 4278        atom_inputs[0][0]                
                                                                 bond_inputs[0][0]                
                                                                 edge_inputs[0][0]                
__________________________________________________________________________________________________
neural_graph_output_2 (NeuralGr [(None, 55, 62), (No 4278        neural_graph_hidden_1[0][0]      
                                                                 bond_inputs[0][0]                
                                                                 edge_inputs[0][0]                
__________________________________________________________________________________________________
neural_graph_output_3 (NeuralGr [(None, 55, 62), (No 4278        neural_graph_hidden_2[0][0]      
                                                                 bond_inputs[0][0]                
                                                                 edge_inputs[0][0]                
__________________________________________________________________________________________________
concatenate_1 (Concatenate)     (None, 55, 186)      0           neural_graph_output_1[0][0]      
                                                                 neural_graph_output_2[0][0]      
                                                                 neural_graph_output_3[0][0]      
__________________________________________________________________________________________________
main_prediction (Dense)         (None, 55, 1)        187         concatenate_1[0][0]              
==================================================================================================
Total params: 18,461
Trainable params: 18,461
Non-trainable params: 0
__________________________________________________________________________________________________
DEBUG: labels.shape (1128,)
Traceback (most recent call last):
  File "/home/thomas/Programs/Anaconda3/lib/python3.7/site-packages/IPython/core/interactiveshell.py", line 3296, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-2-9a41784534dc>", line 1, in <module>
    runfile('/home2/thomas/Programs/keras-neural-graph-fingerprint_Py3/examples.py', wdir='/home2/thomas/Programs/keras-neural-graph-fingerprint_Py3')
  File "/home2/thomas/Programs/pycharm-2019.1.1/helpers/pydev/_pydev_bundle/pydev_umd.py", line 197, in runfile
    pydev_imports.execfile(filename, global_vars, local_vars)  # execute the script
  File "/home2/thomas/Programs/pycharm-2019.1.1/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "/home2/thomas/Programs/keras-neural-graph-fingerprint_Py3/examples.py", line 80, in <module>
    model.fit(x=[X_atoms, X_bonds, X_edges], y=labels, epochs=20, batch_size=32, validation_split=0.2)
  File "/home/thomas/Programs/Anaconda3/lib/python3.7/site-packages/keras/engine/training.py", line 952, in fit
    batch_size=batch_size)
  File "/home/thomas/Programs/Anaconda3/lib/python3.7/site-packages/keras/engine/training.py", line 789, in _standardize_user_data
    exception_prefix='target')
  File "/home/thomas/Programs/Anaconda3/lib/python3.7/site-packages/keras/engine/training_utils.py", line 128, in standardize_input_data
    'with shape ' + str(data_shape))
ValueError: Error when checking target: expected main_prediction to have 3 dimensions, but got array with shape (1128, 1)

我怀疑这个错误与“标签”数组的形状有关，它是扁平的。我究竟做错了什么？另外，为什么我会得到

调试：final_fp.get_shape()= (?, 186)

但 model.summary() 显示

concatenate_1（连接）（无、55、186）0

这个额外的维度 (55) 是从哪里来的？也许网络出于某种原因期望标签的尺寸为(1128, 55, 1) 而不是(1128, 1)。

如果您需要更多信息，请询问我，我将添加更多调试打印功能。

【问题讨论】：

拜托，有人吗？？？我正在尝试用随机数据整理一个更简洁的示例，希望有人能回答。

标签： python tensorflow keras conv-neural-network valueerror

【解决方案1】：

您的最后一个 Dense 层 main_predictions 没有提供二维输出，因为您没有将其输入展平。

您需要在卷积层之后使用Flatten 层，以便 Dense 的输出是二维的。

main_predictions 需要 3D 标签，但您提供的是 2D 标签。因此，您会收到错误消息。

您可以在代码中添加一个 Flatten 层，例如：

flatten = Flatten()( final_fp )
main_pred = Dense(1, activation='linear', name='main_prediction')( flatten )

然后编译模型。

【讨论】：

你的建议产生"ValueError: Input 0 is incompatible with layer flatten_1: expected min_ndim=3, found ndim=2"。事实上，我认为通过连接三个 2D 张量，我将输入扁平化到 Dense 层final_fp = concatenate([fp_out0, fp_out1, fp_out2])。但是为什么我仍然认为问题出在y 我喂给model.fit()..？
其实我不明白main_prediction (Dense) (None, 55, 1)中的那个55是从哪里来的！也许网络出于某种原因期望标签的尺寸为(1128, 55, 1) 而不是(1128, 1)。

【解决方案2】：

在您的代码中，您作为之前使用过的注释提到了 final_fp = merge([fp_out0, fp_out1, fp_out2], mode='sum')。因此，根据this，您将mode 的参数用作sum 而不是concat。您正在通过添加它们来合并图层。但在新代码中，您使用的是final_fp = concatenate([fp_out0, fp_out1, fp_out2])。因此，您的旧代码和新代码之间存在差异。在新代码中，您必须使用 keras.layers.Add() 才能获得相同的功能。

并且由于形状与您的标签数据和模型的输出节点不兼容而发生值错误。尝试将keras.layers.Concatenate 更改为keras.layers.Add。

更新

final_fp = Input(shape=(55,62)) # I had used as input which can be replace with your final_fp
flatten_1 = Flatten()(final_fp)
main_pred = Dense(1, activation='linear', name='main_prediction')(flatten_1)

model = Model(inputs=final_fp,outputs=main_pred)
print(model.summary())

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         (None, 55, 62)            0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 3410)              0         
_________________________________________________________________
main_prediction (Dense)      (None, 1)                 3411      
=================================================================
Total params: 3,411
Trainable params: 3,411
Non-trainable params: 0
_________________________________________________________________

【讨论】：

你有一只敏锐的眼睛。 :) 如果你有两个，那么你会注意到上面concatenate 我有一个使用add 注释掉的行。这两个操作都产生一维张量，我只是想检查用concatenate 替换add 是否有任何效果，但它没有。
顺便说一句，我的双眼都很好。我还看到您使用了add。那么，如果您使用add，您的代码是否有效？好的！我了解您想将add 替换为concatenate，但add and concatenate 之间存在差异。
没有效果。唯一的区别是我得到的不是 (None, 55, 186) 张量 (None, 55, 62)。
@tevang 因此，之后您可以使用 flatten 并连接到 Dense。请参阅答案中的更新。
我从一开始就不明白为什么 Keras 的Model() 认为 NeuralGraphOutput() 的输出，即fp_out0, fp_out1, fp_out2 具有形状(None, 55, 62)，而在将它们传递给之前Model() 他们的形状是(?,62)。 ``` DEBUG: fp_out0.get_shape()= (?, 62) DEBUG: fp_out1.get_shape()= (?, 62) DEBUG: fp_out2.get_shape()= (?, 62) ``` 问题从这里开始.我试图展平，但 Flatten() 抱怨输入必须有更多尺寸ValueError: Input 0 is incompatible with layer flatten_4: expected min_ndim=3, found ndim=2。