Hi I have been working on an LSTM network in python using Keras. I created a 1D array for my training and test set. When I try to fit the model I get the following error:
ValueError: Error when checking input: expected lstm_31_input to have 3 dimensions, but got array with shape (599, 1)
I have tried resizing the dimension and the add(Flatten) layer. None of this work. My code is below:
#Setup
import pandas as pd
import numpy as np
from numpy import array, zeros, newaxis
from numpy import argmax
from keras.layers.core import Dense, Activation, Dropout
from keras.preprocessing import sequence
from keras.models import Sequential
from keras.layers import Dense, Embedding, Flatten
from keras.layers import LSTM
#Used to ignore warning about some of the tensor command being depracated
#Code from:
#https://stackoverflow.com/questions/43819820/how-to-disable-keras-warnings
#import warnings
#with warnings.catch_warnings():
# warnings.simplefilter("ignore")
"""
#Allow use of modules from the Common_Functions Folder
import sys
sys.path.append('../_Common_Functions')
import Hello_World as helloWorld
"""
#Creates dataset of random numbers
#import numpy as np
from random import random
def generateDatset(n):
val = np.array([])
typ = np.array([])
for i in range (1, n):
val = np.append(val, round(random()*10, 2))
if val[i-1] < 3 or val[i-1] > 7:
typ = np.append(typ, 'm')
else:
typ = np.append(typ, 'f')
return val, typ
# Encode the output labels
def lable_encoding(gender_series):
labels = np.empty((0, 2))
for i in gender_series:
if i == 'm':
labels = np.append(labels, [[1,0]], axis=0)
else:
labels = np.append(labels, [[0,1]], axis=0)
return labels
#Gets dataset in proper format for this program
val, typ = generateDatset(1000)
df = pd.DataFrame( {"first_name": val[:], "gender": typ[:]} )
# Split dataset in 60% train, 20% test and 20% validation
train, validate, test = np.split(df.sample(frac=1), [int(.6*len(df)), int(.8*len(df))])
# Convert both the input names as well as the output lables into the discussed machine readable vector format
train_x = np.asarray(train.first_name)
#train_x = np.reshape(train_x, train_x.shape + (1,))
#train_x = np.reshape(train_x, (train_x.shape[0], 1, train_x.shape[1]))
train_y = lable_encoding(train.gender)
#train_y = np.reshape(train_y, train_y.shape + (1,))
#train_y = np.reshape(train_y, (train_y.shape[0], 1, train_y.shape[1]))
validate_x = np.asarray(validate.first_name)
#validate_x = np.reshape(validate_x, validate_x.shape + (1,))
validate_y = lable_encoding(validate.gender)
#validate_y = np.reshape(validate_y, validate_y.shape + (1,))
test_x = np.asarray(test.first_name)
#test_x = np.reshape(test_x, test_x.shape + (1,))
test_y = lable_encoding(test.gender)
#test_x = np.reshape(test_x, test_x.shape + (1,))
"""
The number of hidden nodes can be determined by the following equation:
Nh = (Ns/ (alpha * Ni + No ) )
Where Ni --> number of input neurons
No --> number of output neurons
Ns --> number of samples
alph --> scaling factor
Alternatively the following equation can be used:
Nh = (2/3)*(Ni + No)
As a not this equation is simpler but may not provide the best performance
"""
#Set a value for the scaling factor.
#This typically ranges between 2 and 10
alpha = 8
hidden_nodes = int(np.size(train_x) / (alpha * ((len(df.columns)-1)+ 4)))
input_length = train_x.shape # Length of the character vector
output_labels = 2 # Number of output labels
from keras import optimizers
# Build the model
print('Building model...')
model = Sequential()
#print(train_x.shape)
#
df = np.expand_dims(df, axis=2)
model.add(LSTM(hidden_nodes, return_sequences=True, input_shape=(599, 1)))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(units=output_labels))
model.add(Activation('softmax'))
sgd = optimizers.SGD(lr=0.5, clipnorm=10.)
model.compile(loss='categorical_crossentropy', optimizer= sgd, metrics=['acc'])
#
batch_size=1000
#x = train_x[..., newaxis, newaxis]
#x.shape
#y = train_y[..., newaxis, newaxis]
#y.shape
model.fit(train_x, train_y, batch_size=batch_size, epochs=10)
#http://45.76.113.195/?questions/46616674/expected-ndim-3-found-ndim-2-how-to-feed-sparse-matrix-to-lstm-layer-in-keras
input_shape=(599, 1) specifies the shape of one sample.
In here your train batch size is 599 and shape of one sample is 1. Since the first layer is a LSTM layer it needs 3 dimensional input(batch_size,number_of_time_stamps_of_a_sample,diamentionality_of_one_time_stamp).But we don't mention the batch size in input_shape.So input shape of a LSTM layer should be
input_shape=(number_of_time_stamps_of_a_sample,diamentionality_of_one_time_stamp)
So u should
1)Replace input_shape=(599, 1) with input_shape=(1, 1)
2)Add the following line before training train_x=train_x.reshape(599,1,1)
To be more clear please refer to this video uploaded by me ;-)