Pybrain Feedforward neural network training error completely stuck - python

Hey guys I need a bit of help with my pybrain code. Everything loads fine, but after it trains the first time the training error doesn't go down. In fact, it just stays stuck there at exactly 13.3484055174. I've been checking my code many times and comparing it with other examples, but I consistently get the same problem. I've also already tried changing the number of hidden units, learningrate, momentum, weightdecay to no avail. I've checked the parameters and it starts off from [-1 to 1] then blows up into ~240-250. I was wondering if anyone can see why it's not working. I'm sure it's a really simple 1-liner that I'm missing.
I'm working on the kaggle 0-9 digit classification dataset. I've already gotten the randomforest to work but I really want to make this neural network work too. Any help would get greatly appreciated.
#learn digit classification with a nerual network
import pybrain
from pybrain.datasets import *
from pybrain.tools.shortcuts import buildNetwork
from pybrain.supervised.trainers import BackpropTrainer
from pybrain.structure.modules import SoftmaxLayer
from pybrain.utilities import percentError
import numpy
print "Importing training and test data"
data = numpy.genfromtxt('trainR.csv', delimiter = ',')
data = data[1:]
traindata = data[:(len(data)/2)]
testdata = data[(len(data)/2)+1:]
print "Importing actual data"
actualdata = numpy.genfromtxt('trainR.csv', delimiter = ',')
print "Adding samples to dataset and setting up neural network"
ds = ClassificationDataSet(784, 10, nb_classes = 10)
for x in traindata:
ds.addSample(tuple(x[1:]),tuple(x[0:1]))
ds._convertToOneOfMany( bounds=[0,1] )
net = buildNetwork(784, 100, 10, bias=True, outclass=SoftmaxLayer)
print "Training the neural network"
trainer = BackpropTrainer(net, dataset=ds, momentum = 0.1,
verbose = True, weightdecay = 0.01)
for i in range(3):
# train the network for 1 epoch
trainer.trainEpochs( 1 )
# evaluate the result on the training and test data
trnresult = percentError( trainer.testOnClassData(), [x[0] for x in traindata] )
# print the result
print "epoch: " + str(trainer.totalepochs) + " train error: " + str(trnresult)
print ""
print "Predicting with the neural network"
answerlist = []
for row in testdata:
answer = numpy.argmax(net.activate(row[1:]))
answerlist.append(answer)
tstresult = percentError(answerlist, [x[0] for x in testdata])
print "Test error: " + str(tstresult)

try changing
ds = ClassificationDataSet(784, 10, nb_classes = 10)
to
ds = ClassificationDataSet(784, 1, nb_classes = 10)
i think ClassificationDataSet second argument is the dimensions of the targets rather than the number of classes this is given by nb_classes. It depends on how your data is organized. Best thing is to enter each target as an integer for each class and then use _convertToOneOfMany()
It would be useful if you provided your first sample

Related

How to test a deepxde (DeepOnet) model on new input functions?

The post is directed to user's who have used the library deepxde. May you kindly help me in finding the solution to my problem.
I tried the DeepOnet operator learning example according to the dataset generated from grf from this tutorial website link . Now I want to apply the trained model on a known pair of function like cos(x) and sin(x) ; I'll generate my input data-field data as x = np.arange(0,4*np.pi,0.1) ; u(y) = y = np.cos(x) now I want to plot the anti-derivate of my u(y) and compare it with y = np.cos(x).
What additional code shall I implement in order to do so?
The following code runs well on my colab after installing the deepxde library with pip. Now I just want to extend this and check whether the trained model works okay on my custom fucntions or not? for example cosx , sinx etc. Thanks for the help!
import deepxde as dde
import matplotlib.pyplot as plt
import numpy as np
# Load dataset
d = np.load("antiderivative_aligned_train.npz", allow_pickle=True)
X_train = (d["X"][0].astype(np.float32), d["X"][1].astype(np.float32))
y_train = d["y"].astype(np.float32)
d = np.load("antiderivative_aligned_test.npz", allow_pickle=True)
X_test = (d["X"][0].astype(np.float32), d["X"][1].astype(np.float32))
y_test = d["y"].astype(np.float32)
data = dde.data.TripleCartesianProd(
X_train=X_train, y_train=y_train, X_test=X_test, y_test=y_test
)
# Choose a network
m = 100
dim_x = 1
net = dde.nn.DeepONetCartesianProd(
[m, 40, 40],
[dim_x, 40, 40],
"relu",
"Glorot normal",
)
# Define a Model
model = dde.Model(data, net)
# Compile and Train
model.compile("adam", lr=0.001, metrics=["mean l2 relative error"])
losshistory, train_state = model.train(iterations=10000)
# Plot the loss trajectory
dde.utils.plot_loss_history(losshistory)
plt.show()

Python LSTM Bitcoin prediction flatlines

I'm currently trying to build a "simple" LSTM model that takes historical Bitcoin data, learns from that and then tries to predict the future X steps in advance.
I've build it on the idea that A + B + C = D so B + C + D should be E. (I think that's a very simple idea behind an LSTM model. I might be wrong however i'm pretty new to it.)
I managed to build the basics in python (I'm fairly new to python) but something seems off by the prediction. For some reason many of the predictions i test / make end up flatlining. I have a theory on why but we have no idea if it's correct and even less idea on how to solve it.
My theory is that within a sequence the model learns to put more importance / weight on the last digit in the sequence because with Bitcoin prices the future price (in 1 minute) is probably pretty close to the price now. That's try the predicted values keeps getting closer to the real value eventually being equal and thus flatlining in a graph. (I don't know if that makes sense but thats what i tought anyway.)
I've also added a screenshot of my graph from a few days ago. Almost all predictions however end similar to this graph. This is just a more extreme example as demonstration.
Here is my code, can someone please explain why it flatlines and what i did wrong?
import numpy as np
from matplotlib import pyplot
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers import Dropout
import yfinance as yf
from sklearn.preprocessing import MinMaxScaler
from math import sqrt
from sklearn.metrics import mean_squared_error
# Create output sets X + Y from given input-set
# with inputset : a 1-dimensional list of floats
# with N : the number of lookback values to use for X
# with Gap : the number of point skipped between X and Y
# Y: is equal to input, (although the first N are missing)
# X: for each y of Y a corresponding set of size N is created
# composed of the N values preceeding y.
def create_lookback(inputset, n=1, gap=0):
print("create_lookback with n=%d gap=%d" % (n,gap))
print(" - length of inputset = %d" % len(inputset))
dataX, dataY = [], []
for i in range(len(inputset) - (n+gap)):
a = inputset[i:(i + n), 0]
dataX.append(a)
dataY.append(inputset[i + n+gap, 0])
print(" - length of dataY = %d" % len(dataY))
data_x = np.array(dataX)
xret = data_x.reshape(data_x.shape[0], 1, data_x.shape[1])
return xret, np.array(dataY)
# Train model based on given training-set + Test-set
def create_model(trainX,trainY,testX,testY):
model = Sequential()
model.add(LSTM(units = 100, input_shape=(trainX.shape[1], trainX.shape[2], )))
model.add(Dropout(0.2))
#model.add(LSTM(30, return_sequences=True))
#model.add(Dropout(0.1))
model.add(Dense(1))
model.compile(loss='mae', optimizer='adam')
history = model.fit(trainX, trainY, epochs=100, batch_size=5, validation_data=(testX, testY), verbose=1, shuffle=False)
return model
# Evaluate given X / Y set.
# - Calculate RMSE
# - Generate visual line-plot to screen
def show_result(scaler,yhat,setY,txt):
print("Show %s result" % txt)
yhat_inverse = scaler.inverse_transform(yhat.reshape(-1, 1))
testY_inverse = scaler.inverse_transform(setY.reshape(-1, 1))
if len(testY_inverse) == len(yhat_inverse):
rmse = sqrt(mean_squared_error(testY_inverse, yhat_inverse))
print(' RMSE %s : %.3f' % (txt,rmse))
pyplot.plot(yhat_inverse, label='predict '+txt)
pyplot.plot(testY_inverse, label='actual '+txt, alpha=0.5)
pyplot.legend()
pyplot.show()
# Extrapoleer is dutch for Extrapolate
def extrapoleer(i,model,tup,toekomst):
if(i == 0):
return
setX = np.array([[tup]])
y = model.predict(setX)
y_float = y[0][0]
tup_new = np.append(tup[1:], y_float)
toekomst.append(y_float)
extrapoleer(i-1, model, tup_new,toekomst)
# --- end of defined functions
# -- start of main flow
data_grid_1 = yf.download('BTC-USD', start="2021-04-14",end="2021-04-15", interval="1m");
data_grid_2 = yf.download('BTC-USD', period="12h", interval="1m");
dataset_1 = data_grid_1.iloc[:, 1:2].values
dataset_2 = data_grid_2.iloc[:, 1:2].values
scaler = MinMaxScaler(feature_range = (0, 1))
scaled = scaler.fit_transform(dataset_1)
# 70% of dataset_1 is used to train ; 30% to test
train_size = int(len(scaled) * 0.7)
test_size = len(scaled) - train_size
train, test = scaled[0:train_size,:], scaled[train_size:len(scaled),:]
print("train: %d test: %d" % (len(train), len(test)))
scaled_2 = scaler.fit_transform(dataset_2)
look_back_n = 3
look_back_gap = 0
trainX, trainY = create_lookback(train, look_back_n, look_back_gap)
testX, testY = create_lookback(test, look_back_n, look_back_gap)
testX_2, testY_2 = create_lookback(scaled_2, look_back_n, look_back_gap)
model = create_model(trainX,trainY,testX,testY)
yhat_1 = model.predict(testX)
yhat_2 = model.predict(testX_2)
show_result(scaler,yhat_1,testY,"test")
show_result(scaler,yhat_2,testY_2,"test2")
last_n = testY_2[-look_back_n:]
#toekomst = Future in dutch
toekomst = []
#aantal = Amount in Dutch, this indicates the amount if steps you want to future predict
aantal = 30
extrapoleer(aantal, model, last_n, toekomst)
print("Resultaat van %d voorspelde punten in de toekomst: " % aantal)
print(toekomst)
yhat_2_plus = np.append(yhat_2,toekomst)
show_result(scaler,yhat_2_plus,testY_2,"test2-plus")

Word-embedding does not provide expected relations between words

I am trying to train a word embedding to a list of repeated sentences where only the subject changes. I expected that the generated vectors corresponding the subjects provide a strong correlation after training as it is expected from a word embedding. However, the angle between the vectors of subjects is not always larger than the angle between subjects and a random word.
Man is going to write a very long novel that no one can read.
Woman is going to write a very long novel that no one can read.
Boy is going to write a very long novel that no one can read.
The code is based on pytorch tutorial:
import torch
from torch import nn
import torch.nn.functional as F
import numpy as np
class EmbedTrainer(nn.Module):
def __init__(self, d_vocab, d_embed, d_context):
super(EmbedTrainer, self).__init__()
self.embed = nn.Embedding(d_vocab, d_embed)
self.fc_1 = nn.Linear(d_embed * d_context, 128)
self.fc_2 = nn.Linear(128, d_vocab)
def forward(self, x):
x = self.embed(x).view((1, -1)) # flatten after embedding
x = self.fc_2(F.relu(self.fc_1(x)))
x = F.log_softmax(x, dim=1)
return x
text = " ".join(["{} is going to write a very long novel that no one can read.".format(x) for x in ["Man", "Woman", "Boy"]])
text_split = text.split()
trigrams = [([text_split[i], text_split[i+1]], text_split[i+2]) for i in range(len(text_split)-2)]
dic = list(set(text.split()))
tok_to_ids = {w:i for i, w in enumerate(dic)}
tokens_text = text.split(" ")
d_vocab, d_embed, d_context = len(dic), 10, 2
""" Train """
loss_func = nn.NLLLoss()
model = EmbedTrainer(d_vocab, d_embed, d_context)
print(model)
optimizer = torch.optim.SGD(model.parameters(), lr=0.001)
losses = []
epochs = 10
for epoch in range(epochs):
total_loss = 0
for input, target in trigrams:
tok_ids = torch.tensor([tok_to_ids[tok] for tok in input], dtype=torch.long)
target_id = torch.tensor([tok_to_ids[target]], dtype=torch.long)
model.zero_grad()
log_prob = model(tok_ids)
#if total_loss == 0: print("train ", log_prob, target_id)
loss = loss_func(log_prob, target_id)
total_loss += loss.item()
loss.backward()
optimizer.step()
print(total_loss)
losses.append(total_loss)
embed_map = {}
for word in ["Man", "Woman", "Boy", "novel"]:
embed_map[word] = model.embed.weight[tok_to_ids[word]]
print(word, embed_map[word])
def angle(a, b):
from numpy.linalg import norm
a, b = a.detach().numpy(), b.detach().numpy()
return np.dot(a, b) / norm(a) / norm(b)
print("man.woman", angle(embed_map["Man"], embed_map["Woman"]))
print("man.novel", angle(embed_map["Man"], embed_map["novel"]))
I expected that the generated vectors corresponding the subjects provide a strong correlation after training as it is expected from a word embedding
I don't really think you'll achieve that kind of result with only 3 sentences and like 40 iterations in 10 epochs (plus most of the data in your 40 iterations is repeated).
maybe try downloading a couple of free datasets out there, or try your own data with a proven model like a genism model.
I'll give you the code for training a gensim model, so you can test your dataset on another model and see if the problem comes from your data or from your model.
I've tested similar gensim models on datasets with millions of sentences and it worked like a charm, for smaller datasets you might want to change the parameters.
from gensim.models import Word2Vec
from multiprocessing import cpu_count
corpus_path = 'eachLineASentence.txt'
vecSize = 300
winSize = 5
numWorkers = cpu_count()-1
epochs = 20
minCount = 5
skipGram = False
modelName = f'mymodel.model'
model = Word2Vec(corpus_file=corpus_path,
size=vecSize,
window=winSize,
min_count=minCount,
workers=numWorkers,
iter=epochs,
sg=skipGram)
model.save(modelName)
P.S. I don't think it's a good idea to use the keyword input as a variable in your code.
It's most probably the training size. Training a 128d embedding is definitely overkill. Rule of thumb from the the google developers blog:
Why is the embedding vector size 3 in our example? Well, the following "formula" provides a general rule of thumb about the number of embedding dimensions:
embedding_dimensions = number_of_categories**0.25
That is, the embedding vector dimension should be the 4th root of the number of categories. Since our vocabulary size in this example is 81, the recommended number of dimensions is 3:
3 = 81**0.25

How can I tune my neural network to avoid overfitting the mnist data set?

!!!!!!!!!TL;DR at the bottom!!!!!!!!
In an attempt to learn the in's and out's of ML, I have been implementing a neural network optimizer in c++ and wrapped it with swig as a python module. Of course, the first problem I tackled was XOR via the following snip of code: 2 input layers, 2 hidden layers, 1 output layer.
from MikeLearn import NeuralNetwork
from MikeLearn import ClassificationOptimizer
import time
#=======================================================
# Training Set
#=======================================================
X = [[0,1],[1,0],[1,1],[0,0]]
Y = [[1],[1],[0],[0]]
nIn = len(X[0])
nOut = len(Y[0])
#=======================================================
# Model
#=======================================================
verbosity = 0
#Initualize neural network
# NeuralNetwork([nInputs, nHidden1, nHidden2,..,nOutputs],['Activation1','Activation2'...]
N = NeuralNetwork([nIn,2,nOut],['sigmoid','sigmoid'])
N.setLoggerVerbosity(verbosity)
#Initialize the classification optimizer
#ClassificationOptimizer(NeuralNetwork,Xtrain,Ytrain)
Opt = ClassificationOptimizer(N,X,Y)
Opt.setLoggerVerbosity(verbosity)
start_time = time.time();
#fit data
#fit(nEpoch,LearningRate)
E = Opt.fit(10000,0.1)
print("--- %s seconds ---" % (time.time() - start_time))
#Make a prediction
print(Opt.predict(X))
This snippet of code yields the following output (Correct answer would be [1,1,0,0])
--- 0.10273098945617676 seconds ---
((0.9398755431175232,), (0.9397522211074829,), (0.0612373948097229,), (0.04882470518350601,))
>>>
Looks great!
Now for the issue. The following snippet of code tries to learn from the mnist dataset, but suffers very obviously from overfitting. ~750 input (28X28 pixels), 50 hidden, 10 output
from MikeLearn import NeuralNetwork
from MikeLearn import ClassificationOptimizer
import matplotlib.pyplot as plt
import numpy as np
import pickle
import time
#=======================================================
# Data Set
#=======================================================
#load the data dictionary
modeldata = pickle.load( open( "mnist_data.p", "rb" ) )
X = modeldata['X']
Y = modeldata['Y']
#normalize data
X = np.array(X)
X = X/255
X = X.tolist()
#training set
X1 = X[0:49999]
Y1 = Y[0:49999]
#validation set
X2 = X[50000:59999]
Y2 = Y[50000:59999]
#number of inputs/outputs
nIn = len(X[0]) #~750
nOut = len(Y[0]) #=10
#=======================================================
# Model
#=======================================================
verbosity = 1
#Initualize neural network
# NeuralNetwork([nInputs, nHidden1, nHidden2,..,nOutputs],['Activation1','Activation2'...]
N = NeuralNetwork([nIn,50,nOut],['sigmoid','sigmoid'])
N.setLoggerVerbosity(verbosity)
#Initialize optimizer
#ClassificationOptimizer(NeuralNetwork,Xtrain,Ytrain)
Opt = ClassificationOptimizer(N,X1,Y1)
Opt.setLoggerVerbosity(verbosity)
start_time = time.time();
#fit data
#fit(nEpoch,LearningRate)
E = Opt.fit(10,0.1)
print("--- %s seconds ---" % (time.time() - start_time))
#================================
#Final Accuracy on training set
#================================
XL = Opt.predict(X1)
correct = 0
for i,x in enumerate(XL):
if XL[i].index(max(XL[i])) == Y[i].index(max(Y1[i])):
correct = correct + 1
print("Training set Correct = " + str(correct))
Accuracy = correct/len(XL)*100;
print("Accuracy = " + str(Accuracy) + '%')
#================================
#Final Accuracy on validation set
#================================
XL = Opt.predict(X2)
correct = 0
for i,x in enumerate(XL):
if XL[i].index(max(XL[i])) == Y[i].index(max(Y2[i])):
correct = correct + 1
print("Testing set Correct = " + str(correct))
Accuracy = correct/len(XL)*100;
print("Accuracy = " + str(Accuracy)+'%')
That snippet of code yields the following output which shows the training accuracy and validation accuracy.
-------------------------
Epoch
9
-------------------------
E=
0.00696964
E=
0.350509
E=
3.49568e-05
E=
4.09073e-06
E=
1.38491e-06
E=
0.229873
E=
3.60186e-05
E=
0.000115187
E=
2.29978e-06
E=
2.69165e-06
--- 27.400235176086426 seconds ---
Training set Correct = 48435
Accuracy = 96.87193743874877%
Testing set Correct = 982
Accuracy = 9.820982098209821%
The training set accuracy is great, but then the testing set is no better than a random guess. Any idea what could be causing this?
TL;DR
Solved XOR with a model 2 inputs, 2 hidden, 1 output and sigmoid activation functions. Good results.
Tried to solve the Mnist data set with a model of 750 inputs (28X28 pixels), 50 hidden, 10 output and sigmoid activation functions. Severe overfitting issue. 95% accuracy on the training set, 10% accuracy on validation set.
Any Idea what is causing this?
The cause of overfitting is a combination of the data and model (network in this case). During the training is was 'lazy' and found aspects of the data that worked well in training data but not generalize well.
It is difficult/impossible to point out exactly where in the trained network the nodes/weights are located that are responsible for overfitting.
But we can avoid overfitting with several tricks:
Regularisation
Drop-out (easier to implement)
Change Network Architecture (less layers/less nodes/more dimension-reduction)
https://machinelearningmastery.com/dropout-for-regularizing-deep-neural-networks/
To get an idea of regularization, try the playground from tensorflow:
https://playground.tensorflow.org/
A visualisation of dropout
https://yusugomori.com/projects/deep-learning/dropout-relu
Besides try out regularisation techniques, also experiments with different NN architectures.

How can I improve this Keras model that predicts whether a given number is odd or even

I am trying to create a tensorflow keras deep learning model to predict whether a number is odd vs even. However, I cannot figure out how to actually make it work. It's current accuracy ranges between 40-60%, making me assume its just guessing. How can I improve this model? I also have no idea what loss function to use. This is my first model so I am very much a noob. I have also tried changing the layer sizes and that doesn't seem to yield much either. I have also tried varying the size of my sample data (random numbers with a label list of whether they are odd or even). I used as little as 50 to as high as the full 10000. Any help is much appreciated!
Code:
import tensorflow as tf
from tensorflow import keras
import numpy as np
import matplotlib.pyplot as plt
#The next few lines just import and preprocess the data
dataFile = open('oddEvenData.txt','r')
dataLabels = open('oddEvenLabels.txt','r')
data = dataFile.read()
labels = dataLabels.read()
train_data = data.split(',')
train_labels = labels.split(',')
train_data.remove('')
train_labels.remove('')
train_data = [int(x) for x in train_data]
train_labels = [int(x) for x in train_labels]
dataFile.close()
dataLabels.close()
#Creates and pre process's test data set
test_data = [[123],[56],[273],[834],[778]]
test_labels = [[0],[1],[0],[1],[1]]
test_data = np.array(test_data)
test_labels = np.array(test_labels)
test_data = test_data/10000
#Builds framework
model = keras.Sequential([
keras.layers.Dense(32, activation = 'relu',input_shape = (1,)),
keras.layers.Dense(128,activation = 'relu'),
keras.layers.Dense(64,activation = 'relu'),
keras.layers.Dense(2,activation = 'softmax')
])
model.compile(optimizer = 'adam',loss = 'sparse_categorical_crossentropy',metrics = ['accuracy'])
model.fit(train_data,train_labels,epochs = 10)
test_loss,test_acc = model.evaluate(test_data,test_labels)
print('Tested Acc:'+str(test_acc))
testNum = [int(input('Input test num: '))]
prediction = model.predict(np.array(testNum))
print(prediction)

Categories

Resources