我正在尝试使用 fit_generator 和 Talos（用于超参数调整）。早些时候，当我使用 fit 方法时，我得到了 MemoryError，所以当我在这里搜索时，人们说我应该尝试使用 fit_generator。早些时候我给了太多参数，所以即使使用 fit_generator 我得到 MemoryError 现在我已经减少了参数的数量，现在我得到了不同的错误。请在下面找到代码和错误。
代码：：：：：：
def yield_arrays_train(array_x_train_feat1=xtrain_np_img1,array_x_train_feat2=xtrain_np_img2,array_y_train=y_train_numpy,batch_size=6):
while 1:
for i in range(14886):
X_feat1_train = (array_x_train_feat1[i:i+batch_size,:,:].astype(np.float16))
X_feat2_train = (array_x_train_feat2[i:i+batch_size,:,:].astype(np.float16))
Y_train = (array_y_train[i:i+batch_size].astype(np.float16))
yield ([(np.array(X_feat1_train)),(np.array(X_feat2_train))],(np.array(Y_train)))
def yield_arrays_val(array_x_test_feat1,array_x_test_feat2,array_y_test,batch_size):
while 1:
for i in range(60):
X_feat1_test = (array_x_test_feat1[i:i+batch_size,:,:].astype(np.float16))
X_feat2_test = (array_x_test_feat2[i:i+batch_size,:,:].astype(np.float16))
Y_test = (array_y_test[i:i+batch_size].astype(np.float16))
yield ([(np.array(X_feat1_test)),(np.array(X_feat2_test))],(np.array(Y_test)))
def siamese (array_x_train_feat1=xtrain_np_img1,array_x_train_feat2=xtrain_np_img2,array_y_train=y_train_numpy,array_x_test_feat1=xtest_np_img1,array_x_test_feat2=xtest_np_img2,array_y_test=y_test_numpy):
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=8,kernel_size=6, 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=6,kernel_size=4, padding='same', activation='relu'))
encoder.add(BatchNormalization())
encoder.add(Dropout(.1))
encoder.add(MaxPool1D())
encoder.add(Conv1D(filters=4,kernel_size=4, padding='same', activation='relu'))
encoder.add(BatchNormalization())
encoder.add(Dropout(.1))
encoder.add(MaxPool1D())
encoder.add(Flatten())
encoder.add(Dense(10,activation='relu'))
encoder.add(Dropout(.1))
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=.1, beta_1=0.1, beta_2=0.999,decay=.1, amsgrad=False)
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_data=([(x_val[:,:,:,0]).astype(np.float32),(x_val[:,:,:,1]).astype(np.float32)], y_val) ,batch_size=params['batch_size'],epochs=params['epochs'],callbacks=callback_early_stop_reduceLROnPlateau)
history=model.fit_generator(generator=yield_arrays_train(array_x_train_feat1,array_x_train_feat2,array_y_train,6),validation_data=yield_arrays_val(array_x_test_feat1,array_x_test_feat2,array_y_test,6),steps_per_epoch=2481,epochs=5, validation_steps=1000,verbose=1,callbacks=callback_early_stop_reduceLROnPlateau,use_multiprocessing=False,workers=0)
return history,model
siamese (xtrain_np_img1,xtrain_np_img2,y_train_numpy,xtest_np_img1,xtest_np_img2,y_test_numpy)
输出：：：：：：：：
WARNING:tensorflow:From C:\Users\DELL\AppData\Roaming\Python\Python37\site-packages\keras\backend\tensorflow_backend.py:4070: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead.
Model: "model_1"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) (None, 24, 939) 0
__________________________________________________________________________________________________
input_2 (InputLayer) (None, 24, 939) 0
__________________________________________________________________________________________________
sequential_1 (Sequential) (None, 10) 45580 input_1[0][0]
input_2[0][0]
__________________________________________________________________________________________________
lambda_1 (Lambda) (None, 1) 0 sequential_1[1][0]
sequential_1[2][0]
==================================================================================================
Total params: 45,580
Trainable params: 45,544
Non-trainable params: 36
__________________________________________________________________________________________________
WARNING:tensorflow:From C:\Users\DELL\anaconda3\envs\MyEnv\lib\site-packages\tensorflow\python\ops\math_grad.py:1250: add_dispatch_support.<locals>.wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
WARNING:tensorflow:From C:\Users\DELL\AppData\Roaming\Python\Python37\site-packages\keras\backend\tensorflow_backend.py:422: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.
Epoch 1/5
2481/2481 [==============================] - 30s 12ms/step - loss: 0.0024 - accuracy: 0.9992 - val_loss: 0.8333 - val_accuracy: 0.1667
Epoch 2/5
2481/2481 [==============================] - 28s 11ms/step - loss: 6.9194e-05 - accuracy: 0.9999 - val_loss: 0.8333 - val_accuracy: 0.1667
Epoch 3/5
2481/2481 [==============================] - 28s 11ms/step - loss: nan - accuracy: 0.9993 - val_loss: nan - val_accuracy: 0.8333
Epoch 4/5
2481/2481 [==============================] - 28s 11ms/step - loss: nan - accuracy: 1.0000 - val_loss: nan - val_accuracy: 0.8333
Epoch 5/5
2481/2481 [==============================] - 28s 11ms/step - loss: nan - accuracy: 1.0000 - val_loss: nan - val_accuracy: 0.8333oss: nan - acc
Epoch 00005: early stopping
(<keras.callbacks.callbacks.History at 0x26cf45c6ec8>,
<keras.engine.training.Model at 0x26cf3e364c8>)
因此，当我使用硬编码的单组参数时，上面的代码在没有 Talos 的情况下工作
如果我使用
p = {
'filter1':[4,6,8],
'kernel_size1':[2,4,6],
'filter3' : [2,4,6,],
'kernel_size3' : [4,6,8],
'decay' :[.1,0.01,.001],
'droprate1' :[.1,.2,.3],
'filter2':[4,6,8],
'kernel_size2':[8,12],
'droprate4' : [.1,.2],
'droprate2' :[.1,.2],
'unit1': [10,36,64],
'droprate3': [.1,.2],
'lr' :[.1,0.01,.001]
}
def siamese (array_x_train_feat1=xtrain_np_img1,array_x_train_feat2=xtrain_np_img2,array_y_train=y_train_numpy,array_x_test_feat1=xtest_np_img1,array_x_test_feat2=xtest_np_img2,array_y_test=y_test_numpy,params=p):
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=(params['filter1']),kernel_size=(params['kernel_size1']), padding='same', activation='relu',input_shape=input_shape,kernel_initializer=W_init, bias_initializer=b_init))
encoder.add(BatchNormalization())
encoder.add(Dropout((params['droprate1'])))
encoder.add(MaxPool1D())
encoder.add(Conv1D(filters=(params['filter2']),kernel_size=(params['kernel_size2']), padding='same', activation='relu'))
encoder.add(BatchNormalization())
encoder.add(Dropout((params['droprate2'])))
encoder.add(MaxPool1D())
encoder.add(Conv1D(filters=(params['filter3']),kernel_size=(params['kernel_size3']), padding='same', activation='relu'))
encoder.add(BatchNormalization())
encoder.add(Dropout((params['droprate3'])))
encoder.add(MaxPool1D())
encoder.add(Flatten())
encoder.add(Dense((params['unit1']),activation='relu'))
encoder.add(Dropout((params['droprate4'])))
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=params['lr'], beta_1=0.1, beta_2=0.999,decay=.1, amsgrad=False)
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_generator(generator=yield_arrays_train(array_x_train_feat1,array_x_train_feat2,array_y_train,6),validation_data=yield_arrays_val(array_x_test_feat1,array_x_test_feat2,array_y_test,6),steps_per_epoch=2481,epochs=5, validation_steps=1000,verbose=1,callbacks=callback_early_stop_reduceLROnPlateau,use_multiprocessing=False,workers=0)
return history,model
t=ta.Scan(x=[xtrain_np_img1.astype(np.float16),xtrain_np_img2.astype(np.float16)],y=y_train_numpy,x_val=[xtest_np_img1,xtest_np_img2],y_val=y_test_numpy,model=siamese,params=p,experiment_name='exp_1')
错误
----> 3 t=ta.Scan(x=[xtrain_np_img1.astype(np.float16),xtrain_np_img2.astype(np.float16)],y=y_train_numpy,x_val=[xtest_np_img1,xtest_np_img2],y_val=y_test_numpy,model=siamese,params=p,experiment_name='exp_1')
~\anaconda3\envs\MyEnv\lib\site-packages\talos\scan\Scan.py in __init__(self, x, y, params, model, experiment_name, x_val, y_val, val_split, random_method, seed, performance_target, fraction_limit, round_limit, time_limit, boolean_limit, reduction_method, reduction_interval, reduction_window, reduction_threshold, reduction_metric, minimize_loss, disable_progress_bar, print_params, clear_session, save_weights)
194 # start runtime
195 from .scan_run import scan_run
--> 196 scan_run(self)
~\anaconda3\envs\MyEnv\lib\site-packages\talos\scan\scan_run.py in scan_run(self)
24 # otherwise proceed with next permutation
25 from .scan_round import scan_round
---> 26 self = scan_round(self)
27 self.pbar.update(1)
28
~\anaconda3\envs\MyEnv\lib\site-packages\talos\scan\scan_round.py in scan_round(self)
17 # fit the model
18 from ..model.ingest_model import ingest_model
---> 19 self.model_history, self.round_model = ingest_model(self)
20 self.round_history.append(self.model_history.history)
21
~\anaconda3\envs\MyEnv\lib\site-packages\talos\model\ingest_model.py in ingest_model(self)
8 self.x_val,
9 self.y_val,
---> 10 self.round_params)
<ipython-input-27-fe409e1ff506> in siamese(array_x_train_feat1, array_x_train_feat2, array_y_train, array_x_test_feat1, array_x_test_feat2, array_y_test, params)
11
12 encoder = Sequential()
---> 13 encoder.add(Conv1D(filters=(params['filter1']),kernel_size=(params['kernel_size1']), padding='same', activation='relu',input_shape=input_shape,kernel_initializer=W_init, bias_initializer=b_init))
14 encoder.add(BatchNormalization())
15 encoder.add(Dropout((params['droprate1'])))
~\AppData\Roaming\Python\Python37\site-packages\keras\legacy\interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' + object_name + '` call to the ' +
90 'Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
~\AppData\Roaming\Python\Python37\site-packages\keras\layers\convolutional.py in __init__(self, filters, kernel_size, strides, padding, data_format, dilation_rate, activation, use_bias, kernel_initializer, bias_initializer, kernel_regularizer, bias_regularizer, activity_regularizer, kernel_constraint, bias_constraint, **kwargs)
351 kernel_constraint=kernel_constraint,
352 bias_constraint=bias_constraint,
--> 353 **kwargs)
354
355 def get_config(self):
~\AppData\Roaming\Python\Python37\site-packages\keras\layers\convolutional.py in __init__(self, rank, filters, kernel_size, strides, padding, data_format, dilation_rate, activation, use_bias, kernel_initializer, bias_initializer, kernel_regularizer, bias_regularizer, activity_regularizer, kernel_constraint, bias_constraint, **kwargs)
107 self.filters = filters
108 self.kernel_size = conv_utils.normalize_tuple(kernel_size, rank,
--> 109 'kernel_size')
110 self.strides = conv_utils.normalize_tuple(strides, rank, 'strides')
111 self.padding = conv_utils.normalize_padding(padding)
~\AppData\Roaming\Python\Python37\site-packages\keras\utils\conv_utils.py in normalize_tuple(value, n, name)
37 if len(value_tuple) != n:
38 raise ValueError('The `' + name + '` argument must be a tuple of ' +
---> 39 str(n) + ' integers. Received: ' + str(value))
40 for single_value in value_tuple:
41 try:
ValueError: The `kernel_size` argument must be a tuple of 1 integers. Received: [2, 4, 6]
如果我只给出一组超参数来检查我会得到不同的错误还是相同的错误
p = {
'filter1':[6],
'kernel_size1':[4],
'filter3' : [4],
'kernel_size3' : [6],
'decay' :[.1],
'droprate1' :[.1],
'filter2':[4],
'kernel_size2':[8],
'droprate4' : [.1],
'droprate2' :[.1],
'unit1': [10],
'droprate3': [.1],
'lr' :[.1]
}
def siamese (array_x_train_feat1=xtrain_np_img1,array_x_train_feat2=xtrain_np_img2,array_y_train=y_train_numpy,array_x_test_feat1=xtest_np_img1,array_x_test_feat2=xtest_np_img2,array_y_test=y_test_numpy,params=p):
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=(params['filter1']),kernel_size=(params['kernel_size1']), padding='same', activation='relu',input_shape=input_shape,kernel_initializer=W_init, bias_initializer=b_init))
encoder.add(BatchNormalization())
encoder.add(Dropout((params['droprate1'])))
encoder.add(MaxPool1D())
encoder.add(Conv1D(filters=(params['filter2']),kernel_size=(params['kernel_size2']), padding='same', activation='relu'))
encoder.add(BatchNormalization())
encoder.add(Dropout((params['droprate2'])))
encoder.add(MaxPool1D())
encoder.add(Conv1D(filters=(params['filter3']),kernel_size=(params['kernel_size3']), padding='same', activation='relu'))
encoder.add(BatchNormalization())
encoder.add(Dropout((params['droprate3'])))
encoder.add(MaxPool1D())
encoder.add(Flatten())
encoder.add(Dense((params['unit1']),activation='relu'))
encoder.add(Dropout((params['droprate4'])))
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=params['lr'], beta_1=0.1, beta_2=0.999,decay=.1, amsgrad=False)
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_generator(generator=yield_arrays_train(array_x_train_feat1,array_x_train_feat2,array_y_train,6),validation_data=yield_arrays_val(array_x_test_feat1,array_x_test_feat2,array_y_test,6),steps_per_epoch=2481,epochs=5, validation_steps=1000,verbose=1,callbacks=callback_early_stop_reduceLROnPlateau,use_multiprocessing=False,workers=0)
return history,model
t=ta.Scan(x=[xtrain_np_img1.astype(np.float16),xtrain_np_img2.astype(np.float16)],y=y_train_numpy,x_val=[xtest_np_img1,xtest_np_img2],y_val=y_test_numpy,model=siamese,params=p,experiment_name='exp_1')
错误：：：：：：：
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-31-4c923301ede6> in <module>
1 #t=ta.Scan(x=xtrain_np_img1_img2,y=y_train_numpy,x_val=xtest_np_img1_img2,y_val=y_test_numpy,model=siamese,params=p,experiment_name='exp_1')
2
----> 3 t=ta.Scan(x=[xtrain_np_img1.astype(np.float16),xtrain_np_img2.astype(np.float16)],y=y_train_numpy,x_val=[xtest_np_img1,xtest_np_img2],y_val=y_test_numpy,model=siamese,params=p,experiment_name='exp_1')
~\anaconda3\envs\MyEnv\lib\site-packages\talos\scan\Scan.py in __init__(self, x, y, params, model, experiment_name, x_val, y_val, val_split, random_method, seed, performance_target, fraction_limit, round_limit, time_limit, boolean_limit, reduction_method, reduction_interval, reduction_window, reduction_threshold, reduction_metric, minimize_loss, disable_progress_bar, print_params, clear_session, save_weights)
194 # start runtime
195 from .scan_run import scan_run
--> 196 scan_run(self)
~\anaconda3\envs\MyEnv\lib\site-packages\talos\scan\scan_run.py in scan_run(self)
24 # otherwise proceed with next permutation
25 from .scan_round import scan_round
---> 26 self = scan_round(self)
27 self.pbar.update(1)
28
~\anaconda3\envs\MyEnv\lib\site-packages\talos\scan\scan_round.py in scan_round(self)
17 # fit the model
18 from ..model.ingest_model import ingest_model
---> 19 self.model_history, self.round_model = ingest_model(self)
20 self.round_history.append(self.model_history.history)
21
~\anaconda3\envs\MyEnv\lib\site-packages\talos\model\ingest_model.py in ingest_model(self)
8 self.x_val,
9 self.y_val,
---> 10 self.round_params)
<ipython-input-30-fe409e1ff506> in siamese(array_x_train_feat1, array_x_train_feat2, array_y_train, array_x_test_feat1, array_x_test_feat2, array_y_test, params)
11
12 encoder = Sequential()
---> 13 encoder.add(Conv1D(filters=(params['filter1']),kernel_size=(params['kernel_size1']), padding='same', activation='relu',input_shape=input_shape,kernel_initializer=W_init, bias_initializer=b_init))
14 encoder.add(BatchNormalization())
15 encoder.add(Dropout((params['droprate1'])))
~\AppData\Roaming\Python\Python37\site-packages\keras\engine\sequential.py in add(self, layer)
164 # and create the node connecting the current layer
165 # to the input layer we just created.
--> 166 layer(x)
167 set_inputs = True
168 else:
~\AppData\Roaming\Python\Python37\site-packages\keras\engine\base_layer.py in __call__(self, inputs, **kwargs)
461 'You can build it manually via: '
462 '`layer.build(batch_input_shape)`')
--> 463 self.build(unpack_singleton(input_shapes))
464 self.built = True
465
~\AppData\Roaming\Python\Python37\site-packages\keras\layers\convolutional.py in build(self, input_shape)
139 name='kernel',
140 regularizer=self.kernel_regularizer,
--> 141 constraint=self.kernel_constraint)
142 if self.use_bias:
143 self.bias = self.add_weight(shape=(self.filters,),
~\AppData\Roaming\Python\Python37\site-packages\keras\engine\base_layer.py in add_weight(self, name, shape, dtype, initializer, regularizer, trainable, constraint)
277 if dtype is None:
278 dtype = self.dtype
--> 279 weight = K.variable(initializer(shape, dtype=dtype),
280 dtype=dtype,
281 name=name,
~\anaconda3\envs\MyEnv\lib\site-packages\tensorflow\python\ops\init_ops.py in __call__(self, shape, dtype, partition_info)
513 if partition_info is not None:
514 scale_shape = partition_info.full_shape
--> 515 fan_in, fan_out = _compute_fans(scale_shape)
516 if self.mode == "fan_in":
517 scale /= max(1., fan_in)
~\anaconda3\envs\MyEnv\lib\site-packages\tensorflow\python\ops\init_ops.py in _compute_fans(shape)
1445 fan_in = shape[-2] * receptive_field_size
1446 fan_out = shape[-1] * receptive_field_size
-> 1447 return int(fan_in), int(fan_out)
1448
1449
TypeError: int() argument must be a string, a bytes-like object or a number, not 'list'
对我来说，所有这些似乎都是 python 错误，与 talos 无关（超参数优化工具）
我的问题是
- 我在代码中犯了什么错误？
- 我写代码的逻辑有什么错误吗？
我有另一个查询，但为此我将启动另一个线程来了解我正在解决的问题，即通过 MFCC+MFCC_del+MFCC_del_del 识别扬声器并使用连体网络会起作用吗？可以从此链接访问完整代码，但我没有将数据文件上传到谷歌驱动器，所以它不会工作，但可能会看到完整代码的主要部分
https://colab.research.google.com/drive/1Twssq_MiQ4RxMZ69A595SFIgs4JhG18u?usp=sharing ############################ 编辑：我只是检查一个链接https://www.kaggle.com/sohaibanwaar1203/talos-hyper-parameter-optimization 在这个代码是
params = {'lr': (0.1, 0.01,1 ),
'epochs': [10,5,15],
'dropout': (0, 0.40, 0.8),
'optimizer': ["Adam","Adagrad","sgd"],
'loss': ["binary_crossentropy","mean_squared_error","mean_absolute_error"],
'last_activation': ["softmax","sigmoid"],
'activation' :["relu","selu","linear"],
'clipnorm':(0.0,0.5,1),
'decay':(1e-6,1e-4,1e-2),
'momentum':(0.9,0.5,0.2),
'l1': (0.01,0.001,0.0001),
'l2': (0.01,0.001,0.0001),
'No_of_CONV_and_Maxpool_layers':[1,2],
'No_of_Dense_Layers': [2,3,4],
'No_of_Units_in_dense_layers':[64,32],
'Kernal_Size':[(3,3),(5,5)],
'Conv2d_filters':[60,40,80,120],
'pool_size':[(3,3),(5,5)],
'padding':["valid","same"]
}
lr = params['lr']
epochs=params['epochs']
dropout_rate=params['dropout']
optimizer=params['optimizer']
loss=params['loss']
last_activation=params['last_activation']
activation=params['activation']
clipnorm=params['clipnorm']
decay=params['decay']
momentum=params['momentum']
l1=params['l1']
l2=params['l2']
No_of_CONV_and_Maxpool_layers=params['No_of_CONV_and_Maxpool_layers']
No_of_Dense_Layers =params['No_of_Dense_Layers']
No_of_Units_in_dense_layers=params['No_of_Units_in_dense_layers']
Kernal_Size=params['Kernal_Size']
Conv2d_filters=params['Conv2d_filters']
pool_size_p=params['pool_size']
padding_p=params['padding']
输出
print (type((params['epochs'])))
<class 'list'>
所以我什至在这个博客中看到输出是列表，所以我不明白它为什么会出错。