当我使用 keras model.fit 这样我不使用“validation_data”并且只有 x_train 和 y_train 时，即使我使用“validation_split”，我也不会收到任何错误。下面是工作代码
def siamese(x_train,y_train):
W_init = tf.keras.initializers.he_normal(seed=100)
b_init = tf.keras.initializers.he_normal(seed=50)
input_shape = (24,939)
left_input = Input(input_shape)
right_input = Input(input_shape)
encoder = Sequential()
encoder.add(Conv1D(filters=6,kernel_size=4, padding='same', activation='relu',input_shape=input_shape,kernel_initializer=W_init, bias_initializer=b_init))
encoder.add(BatchNormalization())
encoder.add(Dropout(.1))
encoder.add(MaxPool1D())
encoder.add(Conv1D(filters=4,kernel_size=3, padding='same', activation='relu'))
encoder.add(BatchNormalization())
encoder.add(Dropout(.1))
encoder.add(MaxPool1D())
encoder.add(Conv1D(filters=3,kernel_size=2, padding='same', activation='relu'))
encoder.add(BatchNormalization())
encoder.add(Dropout(.1))
encoder.add(MaxPool1D())
encoder.add(Flatten())
encoder.add(Dense(64,activation='relu'))
encoder.add(Dropout(.3))
encoded_l = encoder(left_input)
encoded_r = encoder(right_input)
distance = Lambda(euclidean_distance, output_shape=eucl_dist_output_shape)([encoded_l, encoded_r])
adam = optimizers.Adam(lr=.001)
earlyStopping = EarlyStopping(monitor='loss',min_delta=0,patience=3,verbose=1,restore_best_weights=False)
callback_early_stop_reduceLROnPlateau=[earlyStopping]
model = Model([left_input, right_input], distance)
model.compile(loss=contrastive_loss, optimizer=adam,metrics=[accuracy])
model.summary()
history = model.fit([(x_train[:,:,:,0]).astype(np.float32),(x_train[:,:,:,1]).astype(np.float32)],y_train,validation_split = .15,batch_size=64,epochs=4,callbacks=callback_early_stop_reduceLROnPlateau)
return model,history
model1,history1=siamese(xtrain_np_img1_img2,y_train_numpy)
输出：：：：
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_5 (InputLayer) (None, 24, 939) 0
__________________________________________________________________________________________________
input_6 (InputLayer) (None, 24, 939) 0
__________________________________________________________________________________________________
sequential_3 (Sequential) (None, 64) 23337 input_5[0][0]
input_6[0][0]
__________________________________________________________________________________________________
lambda_3 (Lambda) (None, 1) 0 sequential_3[1][0]
sequential_3[2][0]
==================================================================================================
Total params: 23,337
Trainable params: 23,311
Non-trainable params: 26
__________________________________________________________________________________________________
Train on 12653 samples, validate on 2233 samples
Epoch 1/4
12653/12653 [==============================] - 8s 668us/step - loss: 5.2016 - accuracy: 0.4152 - val_loss: 0.1739 - val_accuracy: 0.7323
Epoch 2/4
12653/12653 [==============================] - 7s 533us/step - loss: nan - accuracy: 0.4359 - val_loss: nan - val_accuracy: 1.0000
Epoch 3/4
12653/12653 [==============================] - 7s 539us/step - loss: nan - accuracy: 0.4117 - val_loss: nan - val_accuracy: 1.0000
Epoch 4/4
12653/12653 [==============================] - 7s 532us/step - loss: nan - accuracy: 0.4117 - val_loss: nan - val_accuracy: 1.0000
Epoch 00004: early stopping
现在我想介绍“validation_data”而不是使用“validation_split”
所以我先试了
def siamese(x_train,y_train,x_val,y_val):
W_init = tf.keras.initializers.he_normal(seed=100)
b_init = tf.keras.initializers.he_normal(seed=50)
input_shape = (24,939)
left_input = Input(input_shape)
right_input = Input(input_shape)
encoder = Sequential()
encoder.add(Conv1D(filters=6,kernel_size=4, padding='same', activation='relu',input_shape=input_shape,kernel_initializer=W_init, bias_initializer=b_init))
encoder.add(BatchNormalization())
encoder.add(Dropout(.1))
encoder.add(MaxPool1D())
encoder.add(Conv1D(filters=4,kernel_size=3, padding='same', activation='relu'))
encoder.add(BatchNormalization())
encoder.add(Dropout(.1))
encoder.add(MaxPool1D())
encoder.add(Conv1D(filters=3,kernel_size=2, padding='same', activation='relu'))
encoder.add(BatchNormalization())
encoder.add(Dropout(.1))
encoder.add(MaxPool1D())
encoder.add(Flatten())
encoder.add(Dense(64,activation='relu'))
encoder.add(Dropout(.3))
encoded_l = encoder(left_input)
encoded_r = encoder(right_input)
distance = Lambda(euclidean_distance, output_shape=eucl_dist_output_shape)([encoded_l, encoded_r])
adam = optimizers.Adam(lr=.001)
earlyStopping = EarlyStopping(monitor='loss',min_delta=0,patience=3,verbose=1,restore_best_weights=False)
callback_early_stop_reduceLROnPlateau=[earlyStopping]
model = Model([left_input, right_input], distance)
model.compile(loss=contrastive_loss, optimizer=adam,metrics=[accuracy])
model.summary()
history = model.fit([(x_train[:,:,:,0]).astype(np.float32),(x_train[:,:,:,1]).astype(np.float32)],y_train,tuple([(x_val[:,:,:,0]).astype(np.float32),(x_val[:,:,:,1]).astype(np.float32)]),y_val,batch_size=128,epochs=4,callbacks=callback_early_stop_reduceLROnPlateau)
return model,history
model1,history1=siamese(xtrain_np_img1_img2,y_train_numpy,xtest_np_img1_img2,y_test_numpy)
我得到的错误是 TypeError: fit() got multiple values for argument 'batch_size'
所以我尝试了另一种方法，因为我无法解决上述问题
def siamese(x_train,y_train,x_val,y_val,batch_size,epochs,callbacks):
W_init = tf.keras.initializers.he_normal(seed=100)
b_init = tf.keras.initializers.he_normal(seed=50)
input_shape = (24,939)
left_input = Input(input_shape)
right_input = Input(input_shape)
encoder = Sequential()
encoder.add(Conv1D(filters=6,kernel_size=4, padding='same', activation='relu',input_shape=input_shape,kernel_initializer=W_init, bias_initializer=b_init))
encoder.add(BatchNormalization())
encoder.add(Dropout(.1))
encoder.add(MaxPool1D())
encoder.add(Conv1D(filters=4,kernel_size=3, padding='same', activation='relu'))
encoder.add(BatchNormalization())
encoder.add(Dropout(.1))
encoder.add(MaxPool1D())
encoder.add(Conv1D(filters=3,kernel_size=2, padding='same', activation='relu'))
encoder.add(BatchNormalization())
encoder.add(Dropout(.1))
encoder.add(MaxPool1D())
encoder.add(Flatten())
encoder.add(Dense(64,activation='relu'))
encoder.add(Dropout(.3))
encoded_l = encoder(left_input)
encoded_r = encoder(right_input)
distance = Lambda(euclidean_distance, output_shape=eucl_dist_output_shape)([encoded_l, encoded_r])
adam = optimizers.Adam(lr=.001)
earlyStopping = EarlyStopping(monitor='loss',min_delta=0,patience=3,verbose=1,restore_best_weights=False)
callback_early_stop_reduceLROnPlateau=[earlyStopping]
model = Model([left_input, right_input], distance)
model.compile(loss=contrastive_loss, optimizer=adam,metrics=[accuracy])
model.summary()
history = model.fit([(x_train[:,:,:,0]).astype(np.float32),(x_train[:,:,:,1]).astype(np.float32)],y_train,tuple([(x_val[:,:,:,0]).astype(np.float32),(x_val[:,:,:,1]).astype(np.float32)]),y_val,batch_size,epochs,callbacks)
return model,history
model1,history1=siamese(xtrain_np_img1_img2,y_train_numpy,xtest_np_img1_img2,y_test_numpy,64,4,callback_early_stop_reduceLROnPlateau)
现在这个时间错误是
TypeError Traceback (most recent call last)
<ipython-input-17-fd746aea477d> in <module>
----> 1 model1,history1=siamese(xtrain_np_img1_img2,y_train_numpy,xtest_np_img1_img2,y_test_numpy,64,4,callback_early_stop_reduceLROnPlateau)
<ipython-input-15-cebaa8a123ad> in siamese(x_train, y_train, x_val, y_val, batch_size, epochs, callbacks)
36 model.summary()
---> 38 history = model.fit([(x_train[:,:,:,0]).astype(np.float32),(x_train[:,:,:,1]).astype(np.float32)],y_train,tuple([(x_val[:,:,:,0]).astype(np.float32),(x_val[:,:,:,1]).astype(np.float32)]),y_val,batch_size,epochs,callbacks)
39 return model,history
~\AppData\Roaming\Python\Python37\site-packages\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
1179 val_inputs = val_x + val_y + val_sample_weights
1180
-> 1181 elif validation_split and 0. < validation_split < 1.:
1182 if any(K.is_tensor(t) for t in x):
1183 raise ValueError(
TypeError: '<' not supported between instances of 'float' and 'list'
我很确定我在学习机器学习时犯了一些小错误。
我之所以尝试这个，是因为我想使用一个名为“talos”的工具，并且因为我正在使用需要多个输入的连体网络，并且为了让 talos 正常工作，我不能使用validation_split，而是使用validation_data https://autonomio。 github.io/talos/#/Examples_Multiple_Inputs
我想使用 talos 的原因是为了查询另一个线程，因为我的模型表现不佳，所以我想可能我应该先尝试超参数调整。