如何在十分钟内实现早停

Question

def train():
# Model
model = Model()

# Loss, Optimizer
global_step = tf.Variable(1, dtype=tf.int32, trainable=False, name='global_step')
loss_fn = model.loss()
optimizer = tf.train.AdamOptimizer(learning_rate=TrainConfig.LR).minimize(loss_fn, global_step=global_step)

# Summaries
summary_op = summaries(model, loss_fn)

with tf.Session(config=TrainConfig.session_conf) as sess:

    # Initialized, Load state
    sess.run(tf.global_variables_initializer())
    model.load_state(sess, TrainConfig.CKPT_PATH)

    writer = tf.summary.FileWriter(TrainConfig.GRAPH_PATH, sess.graph)

    # Input source
    data = Data(TrainConfig.DATA_PATH)

    loss = Diff()
    for step in xrange(global_step.eval(), TrainConfig.FINAL_STEP):

            mixed_wav, src1_wav, src2_wav, _ = data.next_wavs(TrainConfig.SECONDS, TrainConfig.NUM_WAVFILE, step)

            mixed_spec = to_spectrogram(mixed_wav)
            mixed_mag = get_magnitude(mixed_spec)

            src1_spec, src2_spec = to_spectrogram(src1_wav), to_spectrogram(src2_wav)
            src1_mag, src2_mag = get_magnitude(src1_spec), get_magnitude(src2_spec)

            src1_batch, _ = model.spec_to_batch(src1_mag)
            src2_batch, _ = model.spec_to_batch(src2_mag)
            mixed_batch, _ = model.spec_to_batch(mixed_mag)

            # Initializae our callback.
            #early_stopping_cb = EarlyStoppingCallback(val_acc_thresh=0.5)


            l, _, summary = sess.run([loss_fn, optimizer, summary_op],
                                     feed_dict={model.x_mixed: mixed_batch, model.y_src1: src1_batch,
                                                model.y_src2: src2_batch})

            loss.update(l)
            print('step-{}\td_loss={:2.2f}\tloss={}'.format(step, loss.diff * 100, loss.value))

            writer.add_summary(summary, global_step=step)

            # Save state
            if step % TrainConfig.CKPT_STEP == 0:
                tf.train.Saver().save(sess, TrainConfig.CKPT_PATH + '/checkpoint', global_step=step)

    writer.close()

我有一个神经网络代码，可以把音乐和.wav文件中的声音分开。 如何引入一种提前停车算法来停止列车区段？我看到一个关于ValidationMonitor的项目。有人能帮我吗？

Answer 1

以下是我对u可以适应的早期停止的实现：

早期停止可以应用于训练过程的某些阶段，例如在每个阶段的末尾。具体地说，在我的例子中，我在每个阶段监视测试（验证）丢失，并且在测试丢失在20个阶段（self.require_improvement= 20）之后没有改善，训练被中断。

您可以将max epochs设置为10000或20000或任何您想要的值（self.max_epochs = 10000）。

  self.require_improvement= 20
  self.max_epochs = 10000

以下是我的训练功能，我使用提前停车：

定义序列（自）：

# training data
    train_input = self.Normalize(self.x_train)
    train_output = self.y_train.copy()            
#===============
    save_sess=self.sess # this used to compare the result of previous sess with actual one
# ===============
  #costs history :
    costs = []
    costs_inter=[]
# =================
  #for early stopping :
    best_cost=1000000 
    stop = False
    last_improvement=0
# ================
    n_samples = train_input.shape[0] # size of the training set
# ===============
   #train the mini_batches model using the early stopping criteria
    epoch = 0
    while epoch < self.max_epochs and stop == False:
        #train the model on the traning set by mini batches
        #suffle then split the training set to mini-batches of size self.batch_size
        seq =list(range(n_samples))
        random.shuffle(seq)
        mini_batches = [
            seq[k:k+self.batch_size]
            for k in range(0,n_samples, self.batch_size)
        ]

        avg_cost = 0. # The average cost of mini_batches
        step= 0

        for sample in mini_batches:

            batch_x = x_train.iloc[sample, :]
            batch_y =train_output.iloc[sample, :]
            batch_y = np.array(batch_y).flatten()

            feed_dict={self.X: batch_x,self.Y:batch_y, self.is_train:True}

            _, cost,acc=self.sess.run([self.train_step, self.loss_, self.accuracy_],feed_dict=feed_dict)
            avg_cost += cost *len(sample)/n_samples 
            print('epoch[{}] step [{}] train -- loss : {}, accuracy : {}'.format(epoch,step, avg_cost, acc))
            step += 100

        #cost history since the last best cost
        costs_inter.append(avg_cost)

        #early stopping based on the validation set/ max_steps_without_decrease of the loss value : require_improvement
        if avg_cost < best_cost:
            save_sess= self.sess # save session
            best_cost = avg_cost
            costs +=costs_inter # costs history of the validatio set
            last_improvement = 0
            costs_inter= []
        else:
            last_improvement +=1
        if last_improvement > self.require_improvement:
            print("No improvement found during the ( self.require_improvement) last iterations, stopping optimization.")
            # Break out from the loop.
            stop = True
            self.sess=save_sess # restore session with the best cost

        ## Run validation after every epoch : 
        print('---------------------------------------------------------')
        self.y_validation = np.array(self.y_validation).flatten()
        loss_valid, acc_valid = self.sess.run([self.loss_,self.accuracy_], 
                                              feed_dict={self.X: self.x_validation, self.Y: self.y_validation,self.is_train: True})
        print("Epoch: {0}, validation loss: {1:.2f}, validation accuracy: {2:.01%}".format(epoch + 1, loss_valid, acc_valid))
        print('---------------------------------------------------------')

        epoch +=1

我们可以在这里恢复重要代码：

def train(self):
  ...
      #costs history :
        costs = []
        costs_inter=[]
      #for early stopping :
        best_cost=1000000 
        stop = False
        last_improvement=0
       #train the mini_batches model using the early stopping criteria
        epoch = 0
        while epoch < self.max_epochs and stop == False:
            ...
            for sample in mini_batches:
            ...                   
            #cost history since the last best cost
            costs_inter.append(avg_cost)

            #early stopping based on the validation set/ max_steps_without_decrease of the loss value : require_improvement
            if avg_cost < best_cost:
                save_sess= self.sess # save session
                best_cost = avg_cost
                costs +=costs_inter # costs history of the validatio set
                last_improvement = 0
                costs_inter= []
            else:
                last_improvement +=1
            if last_improvement > self.require_improvement:
                print("No improvement found during the ( self.require_improvement) last iterations, stopping optimization.")
                # Break out from the loop.
                stop = True
                self.sess=save_sess # restore session with the best cost
            ...
            epoch +=1

希望它能帮助某人：）。

Answer 2

因为TensorFlow版本r1.10中的估计器API可以使用早期停止挂钩（参见github）。

例如tf.contrib.estimator.stop_if_no_decrease_hook（请参见docs）

Answer 3

ValidationMonitor标记为已弃用。不建议这样做。但你还是可以用的。 下面是如何创建一个示例：

    validation_monitor = monitors.ValidationMonitor(
        input_fn=functools.partial(input_fn, subset="evaluation"),
        eval_steps=128,
        every_n_steps=88,
        early_stopping_metric="accuracy",
        early_stopping_rounds = 1000
    )

你可以自己实现，这里是我的实现：

          if (loss_value < self.best_loss):
            self.stopping_step = 0
            self.best_loss = loss_value
          else:
            self.stopping_step += 1
          if self.stopping_step >= FLAGS.early_stopping_step:
            self.should_stop = True
            print("Early stopping is trigger at step: {} loss:{}".format(global_step,loss_value))
            run_context.request_stop()