machine-learning - keras fit 与 keras 评估

Question

应该有人能真正澄清这一点..

以下是 Keras 文档中的一些初始信息:Keras 中的 fit 函数只是训练给定数量的 epoch 模型。evaluate 函数返回测试模式下模型的损失值和指标值。

因此，这两个函数都会返回一个损失。为了举个例子，如果我有 1 个训练示例，则每个训练步骤后从拟合函数得到的损失应该与从评估函数得到的损失(在同一训练步骤之后)相同。 (这里的假设是我在同一训练集(仅包含 1 个示例)上运行 fit 和 evaluate 函数。)

我将我的网络定义如下:

def identity_loss(y_true, y_pred):
    return K.mean(y_pred - 0 * y_true)

model = ResNet50(weights='imagenet')
model.layers.pop()
x = model.get_layer('flatten_1').output # layer 'flatten_1' is the last layer of the model
model_out = Dense(128, activation='relu',  name='model_out')(x)
model_out = Lambda(lambda  x: K.l2_normalize(x,axis=-1))(model_out)

new_model = Model(inputs=model.input, outputs=model_out)

anchor_input = Input(shape=(224, 224, 3), name='anchor_input')
pos_input = Input(shape=(224, 224, 3), name='pos_input')
neg_input = Input(shape=(224, 224, 3), name='neg_input')

encoding_anchor   = new_model(anchor_input)
encoding_pos      = new_model(pos_input)
encoding_neg      = new_model(neg_input)

loss = Lambda(triplet_loss)([encoding_anchor, encoding_pos, encoding_neg])
siamese_network = Model(inputs  = [anchor_input, pos_input, neg_input], 
                        outputs = loss) 
siamese_network.compile(loss=identity_loss, optimizer=Adam(lr=.00003))

随后，我使用拟合函数训练我的训练集(仅包含 1 个示例)10 个时期。为了检查拟合函数和评估函数之间的差异，我还在每个时期的拟合函数之后运行评估函数，输出如下所示:

nr_epoch:  0 

Epoch 1/1
1/1 [==============================] - 4s 4s/step - loss: 2.0035
1/1 [==============================] - 3s 3s/step
eval_score for train set:  2.0027356147766113

nr_epoch:  1 

Epoch 1/1
1/1 [==============================] - 1s 1s/step - loss: 1.9816
1/1 [==============================] - 1s 1s/step
eval_score for train set:  2.001833915710449

nr_epoch:  2 

Epoch 1/1
1/1 [==============================] - 1s 1s/step - loss: 1.9601
1/1 [==============================] - 1s 1s/step
eval_score for train set:  2.00126576423645

nr_epoch:  3 

Epoch 1/1
1/1 [==============================] - 1s 1s/step - loss: 1.9388
1/1 [==============================] - 1s 1s/step
eval_score for train set:  2.0009117126464844

nr_epoch:  4 

Epoch 1/1
1/1 [==============================] - 1s 1s/step - loss: 1.9176
1/1 [==============================] - 1s 1s/step
eval_score for train set:  2.000725746154785

nr_epoch:  5 

Epoch 1/1
1/1 [==============================] - 1s 1s/step - loss: 1.8964
1/1 [==============================] - 1s 1s/step
eval_score for train set:  2.0006520748138428

nr_epoch:  6 

Epoch 1/1
1/1 [==============================] - 1s 1s/step - loss: 1.8759
1/1 [==============================] - 1s 1s/step
eval_score for train set:  2.0006656646728516

nr_epoch:  7 

Epoch 1/1
1/1 [==============================] - 1s 1s/step - loss: 1.8555
1/1 [==============================] - 1s 1s/step
eval_score for train set:  2.0007567405700684

nr_epoch:  8 

Epoch 1/1
1/1 [==============================] - 1s 1s/step - loss: 1.8355
1/1 [==============================] - 1s 1s/step
eval_score for train set:  2.0009000301361084

nr_epoch:  9 

Epoch 1/1
1/1 [==============================] - 2s 2s/step - loss: 1.8159
1/1 [==============================] - 2s 2s/step
eval_score for train set:  2.001085042953491

如图所示，fit 函数报告的损失(在每个纪元结束时)正在减少。来自评估函数的损失并没有减少。

所以困境是:如果我在 1 个训练示例上运行我的模型，我是否应该从同一时期的拟合和评估函数中看到相同的损失(在每个时期之后)？如果我继续训练，训练损失正在减少，但来自评估函数的损失在某种程度上保持在同一水平并且不会减少

最后，这是我如何调用拟合和评估函数:

z = np.zeros(len(anchor_path))

siamese_network.fit(x=[anchor_imgs, pos_imgs, neg_imgs], 
                    y=z, 
                    batch_size=batch_size, 
                    epochs=1, 
                    verbose=1, 
                    callbacks=None, 
                    validation_split=0.0, 
                    validation_data=None, 
                    shuffle=True, 
                    class_weight=None, 
                    sample_weight=None, 
                    initial_epoch=0, 
                    steps_per_epoch=None, 
                    validation_steps=None)

eval_score = siamese_network.evaluate(x=[anchor_imgs, pos_imgs, neg_imgs], 
                                      y=z,
                                      batch_size = batch_size, 
                                      verbose = 1)
print('eval_score for train set: ', eval_score)

那么，为什么执行fit函数时损失会减少，而evaluate函数却不会减少呢？我哪里出错了？

Answer 1

ResNet 使用批量归一化，在训练和测试期间表现不一样。您认为应该从 model.fit 和 model.evaluate 获得相同训练损失的假设是不正确的。