我按照这个链接的指南构建了一个模型，并在微调部分之前停止，以使用以下代码在其他图像上测试模型：
img_width, img_height = 150, 150batch_size = 1test_model = load_model('dog_cat_model.h5')validation_data_dir = "test1"test_datagen = ImageDataGenerator(rescale=1. / 255)validation_generator = test_datagen.flow_from_directory( validation_data_dir, target_size=(img_width, img_height), batch_size=batch_size, shuffle=False, class_mode='binary')predictions = test_model.predict_generator(validation_generator, len(validation_generator.filenames));for i in range(len(validation_generator.filenames)): print(validation_generator.filenames[i], ": ", predictions[i])但是我得到了以下错误：
ValueError: Error when checking : expected flatten_1_input to have shape (None, 4, 4, 512) but got array with shape (1, 150, 150, 3)打印 test_model.summary 给出了以下输出：
_________________________________________________________________Layer (type) Output Shape Param #=================================================================flatten_1 (Flatten) (None, 8192) 0_________________________________________________________________dense_1 (Dense) (None, 256) 2097408_________________________________________________________________dropout_1 (Dropout) (None, 256) 0_________________________________________________________________dense_2 (Dense) (None, 1) 257=================================================================Total params: 2,097,665Trainable params: 2,097,665Non-trainable params: 0_________________________________________________________________None我完全不知道这意味着什么。
这是我用来创建模型的代码：
img_width, img_height = 150, 150top_model_weights_path = 'bottleneck_fc_model.h5'train_data_dir = 'data/train'validation_data_dir = 'data/validation'batch_size = 16train_samples = 2000validation_samples = 800epochs = 50def save_bottlebeck_features(): datagen = ImageDataGenerator(rescale=1. / 255) # build the VGG16 network model = applications.VGG16(include_top=False, weights='imagenet') train_generator = datagen.flow_from_directory( train_data_dir, target_size=(img_width, img_height), batch_size=batch_size, class_mode=None, shuffle=False) validation_generator = datagen.flow_from_directory( validation_data_dir, target_size=(img_width, img_height), batch_size=batch_size, class_mode=None, shuffle=False) predict_size_train = int(math.ceil(train_samples / batch_size)) bottleneck_features_train = model.predict_generator(train_generator, predict_size_train) np.save('bottleneck_features_train.npy', bottleneck_features_train) predict_size_validation = int(math.ceil(validation_samples / batch_size)) bottleneck_features_validation = model.predict_generator(validation_generator, predict_size_validation) np.save('bottleneck_features_validation.npy', bottleneck_features_validation)def train_top_model(): train_data = np.load('bottleneck_features_train.npy') train_labels = np.array([0] * (train_samples // 2) + [1] * (train_samples // 2)) validation_data = np.load('bottleneck_features_validation.npy') validation_labels = np.array([0] * (validation_samples // 2) + [1] * (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('dog_cat_model.h5')save_bottlebeck_features()train_top_model()希望有人能帮帮我 🙂
回答：
你在这行代码中混合了瓶颈模型和图像模型的逻辑：
test_model.predict_generator(...)你向瓶颈模型输入了图像，导致了形状错误。
