Tensorflowインセプションresnet v2の入力テンソル

Question

私はこのコード

import os 
import tensorflow as tf 
from datasets import imagenet 
from nets import inception_resnet_v2 
from preprocessing import inception_preprocessing 

checkpoints_dir = 'model' 

slim = tf.contrib.slim 

batch_size = 3 
image_size = 299 

with tf.Graph().as_default(): 

with slim.arg_scope(inception_resnet_v2.inception_resnet_v2_arg_scope()): 
    logits, _ = inception_resnet_v2.inception_resnet_v2([1, 299, 299, 3], num_classes=1001, is_training=False) 
    probabilities = tf.nn.softmax(logits) 

    init_fn = slim.assign_from_checkpoint_fn(
    os.path.join(checkpoints_dir, 'inception_resnet_v2_2016_08_30.ckpt'), 
    slim.get_model_variables('InceptionResnetV2')) 

    with tf.Session() as sess: 
     init_fn(sess) 

     imgPath = '.../image_3.jpeg' 
     testImage_string = tf.gfile.FastGFile(imgPath, 'rb').read() 
     testImage = tf.image.decode_jpeg(testImage_string, channels=3) 

     np_image, probabilities = sess.run([testImage, probabilities]) 
     probabilities = probabilities[0, 0:] 
     sorted_inds = [i[0] for i in sorted(enumerate(-probabilities), key=lambda x:x[1])] 

     names = imagenet.create_readable_names_for_imagenet_labels() 
     for i in range(15): 
      index = sorted_inds[i] 
      print((probabilities[index], names[index])) 

を実行しようとしている。しかしTFは、エラーが表示されます。ValueError: rank of shape must be at least 4 not: 1

私はその問題は、入力テンソル形状[1, 299, 299, 3]であると考えています。 3チャンネルのJPEG画像のテンソルを入力する方法は？

同様の質問もあります（Using pre-trained inception_resnet_v2 with Tensorflow）。私はコードinput_tensorで見ました - unfortunatelly説明は何ですかinput_tensorです。たぶん私は何か自明であることを求めているが、私は立ち往生している！アドバイスをいただきありがとうございます。

Answer 1

イメージを前処理する必要があります。ここでは、コードは次のようになります。

import os 
import tensorflow as tf 
from datasets import imagenet 
from nets import inception_resnet_v2 
from preprocessing import inception_preprocessing 

checkpoints_dir = 'model' 

slim = tf.contrib.slim 

batch_size = 3 
image_size = 299 

with tf.Graph().as_default(): 
    with slim.arg_scope(inception_resnet_v2.inception_resnet_v2_arg_scope()): 

     imgPath = '.../cat.jpg' 
     testImage_string = tf.gfile.FastGFile(imgPath, 'rb').read() 
     testImage = tf.image.decode_jpeg(testImage_string, channels=3) 
     processed_image = inception_preprocessing.preprocess_image(testImage, image_size, image_size, is_training=False) 
     processed_images = tf.expand_dims(processed_image, 0) 

     logits, _ = inception_resnet_v2.inception_resnet_v2(processed_images, num_classes=1001, is_training=False) 
     probabilities = tf.nn.softmax(logits) 

     init_fn = slim.assign_from_checkpoint_fn(
     os.path.join(checkpoints_dir, 'inception_resnet_v2_2016_08_30.ckpt'), slim.get_model_variables('InceptionResnetV2')) 

     with tf.Session() as sess: 
      init_fn(sess) 

      np_image, probabilities = sess.run([processed_images, probabilities]) 
      probabilities = probabilities[0, 0:] 
      sorted_inds = [i[0] for i in sorted(enumerate(-probabilities), key=lambda x: x[1])] 

      names = imagenet.create_readable_names_for_imagenet_labels() 
      for i in range(15): 
       index = sorted_inds[i] 
       print((probabilities[index], names[index])) 

答えは：あなたは、バッチ形式に展開するtf.expand_dims(your_tensor_3channel, axis=0)を使用することができ

(0.1131034, 'tiger cat') 
(0.079478227, 'tabby, tabby cat') 
(0.052777905, 'Cardigan, Cardigan Welsh corgi') 
(0.030195976, 'laptop, laptop computer') 
(0.027841948, 'bathtub, bathing tub, bath, tub') 
(0.026694898, 'television, television system') 
(0.024981709, 'carton') 
(0.024039172, 'Egyptian cat') 
(0.018425584, 'tub, vat') 
(0.018221909, 'Pembroke, Pembroke Welsh corgi') 
(0.015066789, 'skunk, polecat, wood pussy') 
(0.01377619, 'screen, CRT screen') 
(0.012509955, 'monitor') 
(0.012224807, 'mouse, computer mouse') 
(0.012188354, 'refrigerator, icebox') 

Answer 2

。