keras中的值错误

Question

大家好，请问有人可以帮我解决我的代码，找不到要更改的内容。请帮帮我，因为我是使用深度学习的新手。我知道形状是问题，但我不知道在 keras 中将其更改为什么或如何更改

import csv
import cv2
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

lines=[]
with open('/home/charan/Desktop/Car/Term1/CarND-Behavioral-Cloning-P3/data/data/driving_log.csv') as csvfile:
    reader = csv.reader(csvfile)
    #read = pd.read_csv(csvfile)
    for line in reader:
       lines.append(line)
images = []
measurements = []
for line in lines:
    source_path = line[0]
    #print(source_path)
    filename = source_path.split('/')[-1]
    current_path = "/home/charan/Desktop/Car/Term1/CarND-Behavioral-Cloning-P3/output/IMG/" + filename
    image = cv2.imread(current_path)
    img = images.append(image)
    measurement = float(line[3])
    measurements.append(measurement)
X_train = np.array(images) 
y_train = np.array(measurements)

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

model = Sequential()
model.add(Flatten(input_shape=(160,320,3)))
model.add(Dense(1))
model.compile(loss='mse', optimizer='adam')

model.fit(X_train, y_train, validation_split=0.2, shuffle=True, nb_epoch=7)
model.save('model.h5')

我收到这样的值错误：

ValueError: Error when checking model input: expected lambda_input_2 to have 3 dimensions, but got array with shape (8037, 1) 

排队

---> 50 model.fit(X_train, y_train, validation_split=0.2, shuffle=True)

Answer 1

问题可能出在您的图片大小上。 如果不是所有图像的大小都相同，则 X_train 的形状将与模型的输入不匹配。

尝试将所有图像调整为相同大小，如下所示：

改变这个：

image = cv2.imread(current_path)

进入：

image = cv2.resize(cv2.imread(current_path),(256,256))

还有这个：

model.add(Flatten(input_shape=(160,320,3)))

进入：

model.add(Flatten(input_shape=(256,256,3)))