python - 使用 Cnn 和 Lstm 提取图像字幕生成器的特征？

Question

1.本节我得到的输出是创建了一个“descriptions.txt”文件

# Set these path according to project folder in you system
dataset_text = 'C:\\Users\Srikanth Bhattu\Project\Flickr8k_text\Flickr8k.token.txt'
dataset_images = 'C:\\Users\Srikanth Bhattu\Project\Flickr8k_Dataset\Flicker8k_Dataset'
#we prepare our text data
filename = dataset_text + "/" + 'C:\\Users\Srikanth Bhattu\Project\Flickr8k_text\Flickr8k.token.txt'
#loading the file that contains all data
#mapping them into descriptions dictionary img to 5 captions
descriptions = all_img_captions()
print("Length of descriptions =" ,len(descriptions))
#cleaning the descriptions
clean_descriptions = cleaning_text(descriptions)
#building vocabulary 
vocabulary = text_vocabulary()
print("Length of vocabulary = ", len(vocabulary))
#saving each description to file 
save_descriptions()

2.帮助我加载图像数据集并生成如下给定的输出

def extract_features(directory):
        model = Xception( include_top=False, pooling='avg' )
        features = {}
        for img in tqdm(os.listdir(directory)):
            filename = directory + "/" + img
            image = Image.open(filename)
            image = image.resize((299,299))
            image = np.expand_dims(image, axis=0)
            #image = preprocess_input(image)
            image = image/127.5
            image = image - 1.0
            feature = model.predict(image)
            features[img] = feature
        return features
#2048 feature vector
features = extract_features(dataset_images)
dump(features, open("features.p","wb"))

错误:

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-246-e6797fb99786> in <module>
      1 #2048 feature vector
----> 2 features = extract_features(dataset_images)
      3 dump(features, open('C:\\Users\Srikanth Bhattu\Project\features.p','wb'))

<ipython-input-242-ab5029ed6c28> in extract_features(directory)
      1 def extract_features(directory):
----> 2         model = Xception( include_top=False, pooling='avg' )
      3         features = {}
      4         for img in tqdm(os.listdir(directory)):
      5             filename = directory + "/" + img

NameError: name 'Xception' is not defined.

我需要这个输出图像: Click here to Open output Image

我正在与 一起工作“使用 CNN 和 LSTM 的图像字幕生成器” .我有所有的源代码和数据集，但我无法在我的代码中包含我的数据集和路径。
如果有人有兴趣帮助我完成我的项目，请评论我将向他们支付一些费用。
谢谢你...!!!

Answer 1

您在共享的代码片段中没有定义名为“Xception”的模型。因此，除非您定义模型或导入它，否则它将无法工作。我猜你正在学习本教程 https://data-flair.training/blogs/python-based-project-image-caption-generator-cnn/

正确阅读它，您会看到他们在文章开头导入了模型，执行它应该没问题。按顺序阅读文章，您将不会遇到问题。

import string
import numpy as np
from PIL import Image
import os
from pickle import dump, load
import numpy as np
from keras.applications.xception import Xception, preprocess_input
from keras.preprocessing.image import load_img, img_to_array
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
from keras.utils import to_categorical
from keras.layers.merge import add
from keras.models import Model, load_model
from keras.layers import Input, Dense, LSTM, Embedding, Dropout
# small library for seeing the progress of loops.
from tqdm import tqdm_notebook as tqdm
tqdm().pandas()

这些必须在运行代码段之前执行。它导入 Xception模型以及您正在使用的其他库。