我有不同长度的序列，我想训练一个基于LSTM的神经网络，它将使用前面的Nth标记来预测每个N-1标记。
但是，培训的结果很奇怪；几个时期之后，准确性（在训练和验证中）下降到接近0，而损失也下降到接近0。
由于其无法解释的行为（描述为here），我决定更深入地研究并查看模型的每次迭代所预测的结果。
为此，我想加载每个模型并将其用于验证数据的预测，并将其与模型的原始拟合所生成的度量进行比较。
问题是，我收到以下错误消息：
File "/home/user/experiments/LSTM/1/use_model.py", line 65, in main
prediction = model.predict_generator(test_generator(val_list),steps = len(val_list))
File "/home/user/.local/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/home/user/.local/lib/python3.6/site-packages/keras/engine/training.py", line 1522, in predict_generator
verbose=verbose)
File "/home/user/.local/lib/python3.6/site-packages/keras/engine/training_generator.py", line 474, in predict_generator
return np.concatenate(all_outs[0])
ValueError: all the input array dimensions except for the concatenation axis must match exactly
这似乎是由于LSTM输入的大小不同而发生的。
但是，尽管predict_generator失败了，但fit_generator似乎没有问题。
为什么predict_generator失败了，而fit_generator成功了呢？
如何成功预测使用不同长度的序列？
我的代码如下：
import numpy as np
import glob
import keras
from keras.models import Sequential, load_model
from keras.layers import LSTM, Dense, TimeDistributed,Lambda, Dropout, Activation
from keras.metrics import top_k_categorical_accuracy
from keras.callbacks import ModelCheckpoint
###
import matplotlib
matplotlib.use('Agg') # prevents it from failing when there is no display
import matplotlib.pyplot as plt
import keras.backend as K
from keras.utils import plot_model
###
name='smash7'
model_designation=str(name)+'_'
train_val_split=0.2 # portion to be placed in validation
train_control_number=0
val_control_number=0
test_control_number=0
batch_size = 16
def my_3D_top_5(true, pred):
features_num=int(list(pred.shape)[-1])
true = K.reshape(true, (-1, features_num))
pred = K.reshape(pred, (-1, features_num))
return top_k_categorical_accuracy(true, pred, k=5)
def my_3D_top_10(true, pred):
features_num=int(list(pred.shape)[-1])
true = K.reshape(true, (-1, features_num))
pred = K.reshape(pred, (-1, features_num))
return top_k_categorical_accuracy(true, pred, k=10)
def main ():
input_files=glob.glob('*npy')
data_list,dim=loader(input_files)
train_list,val_list=data_spliter(data_list)
train_list=group_data(train_list,batch_size)
val_list=group_data(val_list,batch_size)
dependencies={'my_3D_top_5' : my_3D_top_5,'my_3D_top_10' : my_3D_top_10}
model=load_model('saved-model-try7_-24.hdf5',custom_objects=dependencies)
#For debugging - to check that train_generator and val_generator work####
model.fit_generator(train_generator(train_list), steps_per_epoch=len(train_list), epochs=1, verbose=1,validation_data=val_generator(val_list),validation_steps=len(val_list))
#########################################################################
prediction = model.predict_generator(test_generator(val_list),steps = len(val_list))
def group_data(data_list,size): # groups data and elongate it to match
output=[]
list_of_sizes=[]
for data in data_list:
list_of_sizes.append(list(data.shape)[1])
data_list = [x for _, x in sorted(zip(list_of_sizes,data_list), key=lambda pair: pair[0])]
while len(data_list)>size:
this=data_list[:size]
data_list=data_list[size:]
combined=(elongate_and_combine(this))
output.append(combined)
combined=(elongate_and_combine(data_list))
output.append(combined)
return (output)
def elongate_and_combine(data_list):
max_length= (list(data_list[-1].shape)[1])
last_element=list.pop(data_list)
output=last_element
stop_codon=last_element[0,(max_length-1),:]
stop_codon=stop_codon.reshape(1,1,stop_codon.size)
for data in data_list:
size_of_data=list(data.shape)[1]
while size_of_data<max_length:
data=np.append(data, stop_codon, axis=1)
size_of_data=list(data.shape)[1]
output=np.append(output, data, axis=0)
return (output)
def train_generator(data_list):
while True:
global train_control_number
train_control_number=cycle_throught(len(data_list),train_control_number)
#print (train_control_number)
this=data_list[train_control_number]
x_train = this [:,:-1,:] # all but the last 1
y_train = this [:,1:,:] # all but the first 1
yield (x_train, y_train)
def val_generator(data_list):
while True:
global val_control_number
val_control_number=cycle_throught(len(data_list),val_control_number)
#print (val_control_number)
this=data_list[val_control_number]
x_train = this [:,:-1,:] # all but the last 1
y_train = this [:,1:,:] # all but the first 1
yield (x_train, y_train)
def test_generator(data_list):
while True:
global test_control_number
test_control_number=cycle_throught(len(data_list),test_control_number)
#print (test_control_number)
this=data_list[test_control_number]
x_train = this [:,:-1,:] # all but the last 1
y_train = this [:,1:,:] # all but the first 1
yield (x_train, y_train)
def cycle_throught (total,current):
current+=1
if (current==total):
current=0
return (current)
def loader(input_files):
data_list=[]
for input_file in input_files:
a=np.load (input_file)
incoming_shape=list(a.shape)
requested_shape=[1]+incoming_shape
a=a.reshape(requested_shape)
#print (a.shape)
data_list.append(a)
return (data_list,incoming_shape[-1])
def data_spliter(input_list):
val_num=int(len(input_list)*train_val_split)
validation=input_list[:val_num]
train=input_list[val_num:]
return (train,validation)
main()