# 使用 TensorFlow 中的再訓練的 VGG16 進行圖像分類 現在，我們將為 COCO 動物數據集再訓練 VGG16 模型。讓我們從定義三個占位符開始： * `is_training` 占位符指定我們是否將模型用于訓練或預測 * `x_p` 是輸入占位符，形狀為`(None, image_height, image_width, 3）` * `y_p` 是輸出占位符，形狀為`(None, 1)` ```py is_training = tf.placeholder(tf.bool,name='is_training') x_p = tf.placeholder(shape=(None,image_height, image_width,3), dtype=tf.float32,name='x_p') y_p = tf.placeholder(shape=(None,1),dtype=tf.int32,name='y_p') ``` 正如我們在策略部分中所解釋的那樣，我們將從檢查點文件中恢復除最后一層之外的層，這被稱為 `vgg/fc8` 層： ```py with slim.arg_scope(vgg.vgg_arg_scope()): logits, _ = vgg.vgg_16(x_p,num_classes=coco.n_classes, is_training=is_training) probabilities = tf.nn.softmax(logits) # restore except last last layer fc8 fc7_variables=tf.contrib.framework.get_variables_to_restore(exclude=['vgg_16/fc8']) fc7_init = tf.contrib.framework.assign_from_checkpoint_fn( os.path.join(model_home, '{}.ckpt'.format(model_name)), fc7_variables) ``` 接下來，定義要初始化但未恢復的最后一個層的變量： ```py # fc8 layer fc8_variables = tf.contrib.framework.get_variables('vgg_16/fc8') fc8_init = tf.variables_initializer(fc8_variables) ``` 正如我們在前面章節中所學到的，用`tf.losses.` `sparse_softmax_cross_entropy()`定義損失函數。 ```py tf.losses.sparse_softmax_cross_entropy(labels=y_p, logits=logits) loss = tf.losses.get_total_loss() ``` 訓練最后一層幾個周期，然后訓練整個網絡幾層。因此，定義兩個單獨的優化器和訓練操作。 ```py learning_rate = 0.001 fc8_optimizer = tf.train.GradientDescentOptimizer(learning_rate) fc8_train_op = fc8_optimizer.minimize(loss, var_list=fc8_variables) full_optimizer = tf.train.GradientDescentOptimizer(learning_rate) full_train_op = full_optimizer.minimize(loss) ``` 我們決定對兩個優化器函數使用相同的學習率，但如果您決定進一步調整超參數，則可以定義單獨的學習率。 像往常一樣定義精度函數： ```py y_pred = tf.to_int32(tf.argmax(logits, 1)) n_correct_pred = tf.equal(y_pred, y_p) accuracy = tf.reduce_mean(tf.cast(n_correct_pred, tf.float32)) ``` 最后，我們運行最后一層 10 個周期的訓練，然后使用批量大小為 32 的 10 個周期的完整網絡。我們還使用相同的會話來預測類： ```py fc8_epochs = 10 full_epochs = 10 coco.y_onehot = False coco.batch_size = 32 coco.batch_shuffle = True total_images = len(x_train_files) n_batches = total_images // coco.batch_size with tf.Session() as tfs: fc7_init(tfs) tfs.run(fc8_init) for epoch in range(fc8_epochs): print('Starting fc8 epoch ',epoch) coco.reset_index() epoch_accuracy=0 for batch in range(n_batches): x_batch, y_batch = coco.next_batch() images=np.array([coco.preprocess_for_vgg(x) \ for x in x_batch]) feed_dict={x_p:images,y_p:y_batch,is_training:True} tfs.run(fc8_train_op, feed_dict = feed_dict) feed_dict={x_p:images,y_p:y_batch,is_training:False} batch_accuracy = tfs.run(accuracy,feed_dict=feed_dict) epoch_accuracy += batch_accuracy except Exception as ex: epoch_accuracy /= n_batches print('Train accuracy in epoch {}:{}' .format(epoch,epoch_accuracy)) for epoch in range(full_epochs): print('Starting full epoch ',epoch) coco.reset_index() epoch_accuracy=0 for batch in range(n_batches): x_batch, y_batch = coco.next_batch() images=np.array([coco.preprocess_for_vgg(x) \ for x in x_batch]) feed_dict={x_p:images,y_p:y_batch,is_training:True} tfs.run(full_train_op, feed_dict = feed_dict ) feed_dict={x_p:images,y_p:y_batch,is_training:False} batch_accuracy = tfs.run(accuracy,feed_dict=feed_dict) epoch_accuracy += batch_accuracy epoch_accuracy /= n_batches print('Train accuracy in epoch {}:{}' .format(epoch,epoch_accuracy)) # now run the predictions feed_dict={x_p:images_test,is_training: False} probs = tfs.run([probabilities],feed_dict=feed_dict) probs=probs[0] ``` 讓我們看看打印我們的預測結果： ```py disp(images_test,id2label=coco.id2label,probs=probs,scale=True) ```  ```py Probability 100.00% of [zebra] ``` ---  ```py Probability 100.00% of [horse] ``` ---  ```py Probability 98.88% of [cat] ``` ---  ```py Probability 100.00% of [bird] ``` ---  ```py Probability 68.88% of [bear] Probability 31.06% of [sheep] Probability 0.02% of [dog] Probability 0.02% of [bird] Probability 0.01% of [horse] ``` ---  ```py Probability 100.00% of [bear] Probability 0.00% of [dog] Probability 0.00% of [bird] Probability 0.00% of [sheep] Probability 0.00% of [cat] ``` ---  ```py Probability 100.00% of [giraffe] ``` ---  ```py Probability 61.36% of [cat] Probability 16.70% of [dog] Probability 7.46% of [bird] Probability 5.34% of [bear] Probability 3.65% of [giraffe] ``` 它正確識別了貓和長頸鹿，并將其他概率提高到 100%。它仍然犯了一些錯誤，因為最后一張照片被歸類為貓，這實際上是裁剪后的噪音圖片。我們會根據這些結果對您進行改進。