爲什麼這個Loop似乎只處理一個圖像？

Question

有人可以幫助理解爲什麼此代碼不處理所有圖像？或者如何確保它處理所有圖像？請看看發生了什麼，當我打印出來的功能和標籤：

def extract_features(list_images): 
    nb_features = 2048 
    features = np.empty((len(list_images),nb_features)) 
    labels = [] 
    create_graph() 
    with tf.Session() as sess: 
     next_to_last_tensor = `sess.graph.get_tensor_by_name('pool_3:0')` 

     for ind, image in enumerate(list_images): 
      if (ind%100 == 0): 
       print('Processing %s...' % (image)) 
       if not gfile.Exists(image): 
         tf.logging.fatal('File does not exist %s', image) 
      image_data = gfile.FastGFile(image, 'rb').read() 
      predictions = sess.run(next_to_last_tensor, 
      {'DecodeJpeg/contents:0': image_data}) 
      features[ind,:] = np.squeeze(predictions) 
      labels.append(re.split('_\d+',image.split('/')[1])[0]) 
     return features, labels 

正如你看到下面的[11]：「處理圖像/揚 - 孟加拉 - tiger.jpg ......」似乎僅環proccesed ONE圖片。

In [11]: features,labels = extract_features(list_images) 

處理圖像/楊氏-孟加拉-tiger.jpg ..。 W tensorflow/core/framework/op_def_util.cc：332] Op BatchNormWithGlobalNormalization已棄用。它將在GraphDef版本9中停止工作。使用tf.nn.batch_normalization（）。

我應該看到：

Processing images/baby_shoe_0.jpg... 
Processing images/basketball_hoop_0.jpg... 
Processing images/bath_spa_0.jpg... 
Processing images/binocular_0.jpg... 
Processing images/birdcage_0.jpg... 
Processing images/birdhouse_0.jpg... 
Processing images/boot_0.jpg... 
Processing images/cabinet_0.jpg... 
Processing images/calculator_0.jpg... 
...etc... 

請參閱包含圖片：

1. 打印（功能）
2. 打印（標籤）

Answer 1

您已將它設置爲每處理100張圖像纔會打印「正在處理.....」。

刪除行if (ind%100 == 0):，它應該顯示你假設其餘的代碼工作後的內容。

做的if not i % number事情效果非常好，如果有成千上萬或上百萬的記錄，但對於一些圖像應該沒有多少需要。

def extract_features(list_images): 
    nb_features = 2048 
    features = np.empty((len(list_images),nb_features)) 
    labels = [] 
    create_graph() 
    with tf.Session() as sess: 
     next_to_last_tensor = `sess.graph.get_tensor_by_name('pool_3:0')` 

     for ind, image in enumerate(list_images): 
      print('Processing %s...' % (image)) 
      if not gfile.Exists(image): 
       tf.logging.fatal('File does not exist %s', image) 
      image_data = gfile.FastGFile(image, 'rb').read() 
      predictions = sess.run(next_to_last_tensor, 
      {'DecodeJpeg/contents:0': image_data}) 
      features[ind,:] = np.squeeze(predictions) 
      labels.append(re.split('_\d+',image.split('/')[1])[0]) 
     return features, labels