# 使用 TensorFlow 中預訓練的 VGG16 進行圖像分類 現在讓我們首先嘗試預測測試圖像的類別，而不進行再訓練。首先，我們清除默認圖并定義圖像的占位符： ```py tf.reset_default_graph() x_p = tf.placeholder(shape=(None,image_height, image_width,3), dtype=tf.float32,name='x_p') ``` 占位符 `x_p` 的形狀是 `(?, 224, 224, 3)`。接下來，加載`vgg16`模型： ```py with slim.arg_scope(vgg.vgg_arg_scope()): logits,_ = vgg.vgg_16(x_p,num_classes=inet.n_classes, is_training=False) ``` 添加 softmax 層以生成類的概率： ```py probabilities = tf.nn.softmax(logits) ``` 定義初始化函數以恢復變量，例如檢查點文件中的權重和偏差。 ```py init = slim.assign_from_checkpoint_fn( os.path.join(model_home, '{}.ckpt'.format(model_name)), slim.get_variables_to_restore()) ``` 在 TensorFlow 會話中，初始化變量并運行概率張量以獲取每個圖像的概率： ```py with tf.Session() as tfs: init(tfs) probs = tfs.run([probabilities],feed_dict={x_p:images_test}) probs=probs[0] ``` 讓我們看看我們得到的課程： ```py disp(images_test,id2label=inet.id2label,probs=probs,scale=True) ```  ```py Probability 99.15% of [zebra] Probability 0.37% of [tiger cat] Probability 0.33% of [tiger, Panthera tigris] Probability 0.04% of [goose] Probability 0.02% of [tabby, tabby cat] ``` ---  ```py Probability 99.50% of [horse cart, horse-cart] Probability 0.37% of [plow, plough] Probability 0.06% of [Arabian camel, dromedary, Camelus dromedarius] Probability 0.05% of [sorrel] Probability 0.01% of [barrel, cask] ``` ---  ```py Probability 19.32% of [Cardigan, Cardigan Welsh corgi] Probability 11.78% of [papillon] Probability 9.01% of [Shetland sheepdog, Shetland sheep dog, Shetland] Probability 7.09% of [Siamese cat, Siamese] Probability 6.27% of [Pembroke, Pembroke Welsh corgi] ``` ---  ```py Probability 97.09% of [chickadee] Probability 2.52% of [water ouzel, dipper] Probability 0.23% of [junco, snowbird] Probability 0.09% of [hummingbird] Probability 0.04% of [bulbul] ``` ---  ```py Probability 24.98% of [whippet] Probability 16.48% of [lion, king of beasts, Panthera leo] Probability 5.54% of [Saluki, gazelle hound] Probability 4.99% of [brown bear, bruin, Ursus arctos] Probability 4.11% of [wire-haired fox terrier] ``` ---  ```py Probability 98.56% of [brown bear, bruin, Ursus arctos] Probability 1.40% of [American black bear, black bear, Ursus americanus, Euarctos americanus] Probability 0.03% of [sloth bear, Melursus ursinus, Ursus ursinus] Probability 0.00% of [wombat] Probability 0.00% of [beaver] ``` ---  ```py Probability 20.84% of [leopard, Panthera pardus] Probability 12.81% of [cheetah, chetah, Acinonyx jubatus] Probability 12.26% of [banded gecko] Probability 10.28% of [jaguar, panther, Panthera onca, Felis onca] Probability 5.30% of [gazelle] ``` ---  ```py Probability 8.09% of [shower curtain] Probability 3.59% of [binder, ring-binder] Probability 3.32% of [accordion, piano accordion, squeeze box] Probability 3.12% of [radiator] Probability 1.81% of [abaya] ``` 從未見過我們數據集中的圖像，并且對數據集中的類沒有任何了解的預訓練模型已正確識別斑馬，馬車，鳥和熊。它沒能認出長頸鹿，因為它以前從未見過長頸鹿。我們將在我們的數據集上再訓練這個模型，只需要更少的工作量和 800 個圖像的較小數據集大小。但在我們這樣做之前，讓我們看看在 TensorFlow 中進行相同的圖像預處理。