如何解決“輸入形狀的預期軸 -1 的值為 1，但收到的輸入形狀為 [None, 256, 256, 3]'”錯誤？

Question

我正在嘗試使用 keras 模型。 我訓練了模型並想通過網絡攝像頭使用它。 但是，據我所知，我在訓練模型時使用的輸入與我從相機接收到的輸入不匹配。 我該如何解決這個問題？

這里的火車代碼：

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]))

這里預測的代碼：

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]

我試圖改變從相機獲得的圖像的形狀，但我無法決定尺寸應該是多少。

Answer 1

您可以從這一行判斷模型的輸入形狀：

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

此行表示模型根據 input_shape 參數拍攝形狀為 (256, 256, 1) 的圖像，因此模型期望拍攝該尺寸的圖像。

您的錯誤消息意味着您使用了形狀為 (256, 256, 3) 的圖像，它預期為 1 而不是 3，因此您需要將通道值設置為灰度圖像中的 1 而不是 BGR 中的 3。

在預測代碼中 while 循環的第一行之后添加此行：

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

該行將圖像的通道從 BGR 更改為灰度，以匹配模型的輸入尺寸通道和模型請求的輸入形狀。