Question

对于图像分类问题，我有以下代码。我一直遇到这个错误：

ValueError: Error when checking input: expected flatten_1_input to have shape (4, 4, 512) but got array with shape (128, 128, 3)

我遇到了一个类似的问题，这些人屠杀了他们的模型加载过程，但是我没有这样做。这是我的代码：

def save_bottlebeck_features():`
    datagen = ImageDataGenerator(rescale=1. / 255)
    
    # build the VGG16 network
    model = applications.VGG16(include_top=False, weights='imagenet')
    
    generator = datagen.flow_from_directory(
            train_data_dir,
            target_size=(img_width, img_height),
            batch_size=batch_size,
            class_mode=None,
            shuffle=False)

   bottleneck_features_train = model.predict_generator(
            generator, nb_train_samples // batch_size)
   np.save('bottleneck_features_train.npy', bottleneck_features_train)
    
   generator = datagen.flow_from_directory(
            validation_data_dir,
            target_size=(img_width, img_height),
            batch_size=batch_size,
            class_mode=None,
            shuffle=False)

   bottleneck_features_validation = model.predict_generator(
            generator, nb_validation_samples // batch_size)
   np.save('bottleneck_features_validation.npy',bottleneck_features_validation)

def train_top_model():

  train_data = np.load('bottleneck_features_train.npy',"r+")
  train_labels = np.array([0] * (nb_train_samples // 2) + [1] * (nb_train_samples // 2))
  validation_data = np.load('bottleneck_features_validation.npy',"r+")
  validation_labels = np.array([0] * (nb_validation_samples // 2) + [1] * (nb_validation_samples // 2))

  model = Sequential()
  model.add(Flatten(input_shape=train_data.shape[1:]))
  model.add(Dense(256, activation='relu'))
  model.add(Dropout(0.5))
  model.add(Dense(1, activation='sigmoid'))

  model.compile(optimizer='rmsprop',
                  loss='binary_crossentropy', metrics=['accuracy'])

  model.fit(train_data, train_labels,
              epochs=epochs,
              batch_size=batch_size,
              validation_data=(validation_data, validation_labels))
  model.save_weights(top_model_weights_path)

  model.save('my_model.model')

save_bottlebeck_features()
train_top_model()

from keras.preprocessing import image
import numpy as np
from keras.models import load_model
import os

resnet_50 = load_model("my_model.model")

TEST_DIR = 'test/'

with open('better_score.csv','w') as f:
    f.write('Id,Expected\n')
    for x in range(1,7091): 
        mystr = "test_" + str(x) +".jpg"
        path = os.path.join(TEST_DIR, mystr)

        if (os.path.exists(path)):
            img = image.load_img(path, target_size=(128, 128))
            img = image.img_to_array(img)
            img = np.expand_dims(img, axis=0)
            model_out  = resnet_50.predict(img/255)
            f.write('{},{}\n'.format(mystr, model_out[0][0]))

我已经打印了train_data形状，即(2000, 4, 4, 512) validation_data的形状为(800, 4, 4, 512)。我能够训练我的模型并保存它。当我尝试将结果输出到csv文件时，出现在上一行之前的问题。

Answer 1

您首先需要使用VGG模型提取输入图像的特征，然后将特征传递给resnet_50模型。所以看起来像这样：

model = applications.VGG16(include_top=False, weights='imagenet')
features = model.predict(img/255.0)
model_out = resnet_50.predict(features)

别忘了resent_50模型的输入就是VGG模型获得的图像的特征。

ValueError：检查输入时出错：预期flatten_1_input具有形状（4、4、512），但数组的形状为（128、128、3）

1 个答案: