ValueError：输入形状的预期轴 -1 的值为 51948，但接收到的输入形状为（无，52）

Question

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.model_selection import train_test_split
import tensorflow.keras as keras

dataset = pd.read_csv('C:\\Users\\Maxie\\MyStuff\\FinalDatasetEng.csv')
inputs = dataset.iloc[:, 2:54].values
targets = dataset.iloc[:, 55].values

from sklearn.model_selection import train_test_split
inputs_train, inputs_test, targets_train, targets_test = train_test_split(inputs, targets, 
test_size = 0.20, random_state = 0)

import keras
from keras.models import Sequential
from keras.layers import Dense

model = keras.Sequential([

        # input layer
        keras.layers.Flatten(input_shape=(inputs.shape[0], inputs.shape[1])),

        # 1st dense layer
        keras.layers.Dense(520, activation='relu'),

        # 2nd dense layer
        keras.layers.Dense(208, activation='relu'),

        # 3rd dense layer
        keras.layers.Dense(52, activation='relu'),

        # output layer
        keras.layers.Dense(4, activation='softmax')
    ])

optimiser = keras.optimizers.Adam(learning_rate=0.0001)
model.compile(optimizer=optimiser,
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

history = model.fit(inputs_train, targets_train, validation_data=(inputs_test, targets_test), 
batch_size=32, epochs=50)

This is my code, I am getting this error: ValueError: Input 0 of layer dense_20 is incompatible with the layer: expected axis -1 of input shape to have value 51948 but received input with shape (None, 52). Anyone please help me resolve this issue.

Answer 1

You have a 1D array as your features input, But you Flattened number of samples and number of features that gives the model 51948 input features (999 samples input.shape[0] * 52 Features input.shape[1] = 51948). So your model expects an array of 51948 input, but you have passed inputs_train which has 52 columns.

Inference:

You should not to flatten your input in the case you have 1D array as input features. Your input features is an array of 52 columns ans 999 samples. Instead of Flatten layer, use of an InputLayer .

So, modified code should be like this:

model = keras.Sequential([

        # input layer
        #change this line to input layer and set the input shape to the shape of your input features
        #keras.layers.Flatten(input_shape=(inputs.shape[0], inputs.shape[1])),
        keras.layers.InputLayer(input_shape=(inputs.shape[1],)), 

        # 1st dense layer
        keras.layers.Dense(520, activation='relu'),

        # 2nd dense layer
        keras.layers.Dense(208, activation='relu'),

        # 3rd dense layer
        keras.layers.Dense(52, activation='relu'),

        # output layer
        keras.layers.Dense(4, activation='softmax')
    ])

optimiser = keras.optimizers.Adam(learning_rate=0.0001)
model.compile(optimizer=optimiser,
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

history = model.fit(inputs_train, targets_train, validation_data=(inputs_test, targets_test), 
batch_size=32, epochs=50)