如何解决“输入形状的预期轴 -1 的值为 1，但接收到的输入形状为 [None, 256, 256, 3]'”错误？

Question

我正在尝试使用 keras 模型。我训练了模型并想从网络摄像头中使用它。但是，据我了解，我在训练模型时使用的输入与从相机接收到的输入不匹配。我该如何解决这个问题？

这里是火车代码：

from keras.preprocessing.image import ImageDataGenerator
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Dropout
from keras.layers import Dense
from keras.layers import Flatten

from keras.callbacks import EarlyStopping, ModelCheckpoint
from keras.models import Sequential, load_model
import tensorflow as tf
import numpy as np
import os

# plot pretty figures
import matplotlib
import matplotlib.pyplot as plt

plt.rcParams['axes.labelsize'] = 14
plt.rcParams['xtick.labelsize'] = 12
plt.rcParams['ytick.labelsize'] = 12

nbatch=32

train_datagen = ImageDataGenerator ( rescale=1./255,
                                     rotation_range=12.,
                                     width_shift_range=0.2,
                                     height_shift_range=0.2,
                                     zoom_range=0.15,
                                     horizontal_flip=True)

test_datagen = ImageDataGenerator (rescale=1./255)

train_gen = train_datagen.flow_from_directory(
    'images/train/',
    target_size=(256,256),
    color_mode='grayscale',
    batch_size=nbatch,
    classes=['NONE','ONE','TWO','THREE','FOUR','FIVE'],
    class_mode='categorical'
)

test_gen = test_datagen.flow_from_directory(
    'images/test/',
    target_size=(256,256),
    color_mode='grayscale',
    batch_size=nbatch,
    classes=['NONE','ONE','TWO','THREE','FOUR','FIVE'],
    class_mode='categorical'
)

for X, y in train_gen:
    print(X.shape, y.shape)

    plt.figure(figsize=(16,16))
    for i in range(25):
        plt.subplot(5,5,i+1)
        plt.axis('off')
        plt.title('Label: {}'.format(np.argmax(y[i])))
        img= np.uint8(255*X[i,:,:,0])
        plt.imshow(img,cmap='gray')
    break

plt.show()

model = Sequential()
model.add(Conv2D(32,(3,3),activation='relu',input_shape=(256,256,1)))
model.add(MaxPooling2D((2,2)))
model.add(Conv2D(64,(3,3),activation='relu'))
model.add(Conv2D(64,(3,3),activation='relu'))
model.add(MaxPooling2D((2,2)))
model.add(Conv2D(128,(3,3),activation='relu'))
model.add(MaxPooling2D((2,2)))
model.add(Conv2D(256,(3,3),activation='relu'))
model.add(MaxPooling2D((2,2)))
model.add(Flatten())
model.add(Dense(150, activation='relu'))
model.add(Dropout(0.25))
model.add(Dense(6,activation='softmax'))

model.summary()

model.compile(optimizer='adam',loss='categorical_crossentropy',metrics=['acc'])

callback_list=[EarlyStopping(monitor='val_loss',patience=10),
               ModelCheckpoint(filepath='model_6cat_2.h6',monitor='val_loss',save_best_only=True),]

os.environ["CUDA_VISIBLE_DEVİCES"] = "0"
with tf.device('/GPU:0'):
    history = model.fit_generator(
        train_gen,
        steps_per_epoch=64,
        epochs=200,
        validation_data=test_gen,
        validation_steps=28,
        callbacks=callback_list
    )

plt.figure(figsize=(16,6))
plt.subplot(1,2,1)
nepochs=len(history.history['loss'])
plt.plot(range(nepochs),history.history['loss'], 'g-', label='train')
plt.plot(range(nepochs),history.history['val_loss'], 'c-', label='test')
plt.legend(prop={'size':20})
plt.ylabel('loss')
plt.xlabel('number of epochs')
plt.subplot(1,2,2)
plt.plot(range(nepochs),history.history['acc'], 'g-', label='train')
plt.plot(range(nepochs),history.history['val_acc'], 'c-', label='test')
plt.legend(prop={'size':20})
plt.ylabel('accuracy')
plt.xlabel('number of epochs')


X_test, y_test= [], []
for ibatch, (X,y) in enumerate(test_gen):
    X_test.append(X)
    y_test.append(y)
    ibatch+=1
    if (ibatch==5*28):break

X_test = np.concatenate(X_test)
y_test = np.concatenate(y_test)
y_test = np.int32([np.argmax(r) for  r in y_test])


y_pred = np.int32([np.argmax(r) for  r in model.predict(X_test)])
match=(y_test == y_pred)
print(("Testing Accuracy = {}").format(np.sum(match)*100/match.shape[0]))

这里是预测代码：

model = load_model("C://Users//90544//OneDrive//Masaüstü//Yusuf// 
ödevler//kerasGiris//model_6cat_2.h6", compile = True)

  cap = cv2.VideoCapture(0)
  while 1:
    ret, frame = cap.read()
    if ret:
        frame = cv2.flip(frame, 1)
        frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
        frame = cv2.resize(frame, (256, 256))
        frameNp = image.img_to_array(frame)
        frameNp = np.expand_dims(frameNp, axis=0)

        predictions = model.predict(frameNp)
        print(predictions)

        cv2.imshow("frame", frameNp)

        k = cv2.waitKey(1) & 0xff
        if k == 27: break  # ESC pressed

    cap.release()
    cv2.destroyAllWindows()

ValueError: Input 0 of layer sequential is incompatible with the layer: expected axis -1 of input shape to have value 1 but received input with shape [None, 256, 256, 3]

我尝试更改从相机获取的图像的形状，但无法确定尺寸。

Answer 1

你可以从这行告诉模型的输入形状：

model.add(Conv2D(32,(3,3),activation='relu',input_shape=(256,256,1)))

这条线表示模型根据 input_shape 参数获取形状为 (256, 256, 1) 的图像，因此模型期望获取该尺寸的图像。

您的错误消息意味着您使用了形状为 (256, 256, 3) 的图像，并且预期为 1 而不是 3，因此您需要将通道值设为 1，如灰度图像而不是 3，即 BGR .

在预测代码的while循环的第一行之后添加这一行：

frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

此行将图像的通道从 BGR 更改为灰度，以匹配模型的输入大小通道和模型请求的输入形状。