I wanted to fit simple LSTM model to perform binary classification on multivariate time series data. Since my data is severely imbalanced, I have integrated class_weight argument from sklearn in my model. However, I have got pretty high loss value, and it was not decreasing with each epoch. My f1 score was 0.018 which is extremely low as well. I appreciate your suggestions!
Sample data:
sequence_length = 10
def generate_data(X, y, sequence_length = 10, step = 1):
X_local = []
y_local = []
for start in range(0, len(data) - sequence_length, step):
end = start + sequence_length
X_local.append(X[start:end])
y_local.append(y[end-1])
return np.array(X_local), np.array(y_local)
X_sequence, y = generate_data(data.loc[:, "V1":"V4"].values, data.Class)
model = keras.Sequential()
model.add(LSTM(100, input_shape = (10, 4)))
model.add(Dropout(0.5))
model.add(Dense(1, activation="sigmoid"))
model.compile(loss="binary_crossentropy"
, metrics=[keras.metrics.binary_accuracy]
, optimizer="adam")
model.summary()
training_size = int(len(X_sequence) * 0.7)
X_train, y_train = X_sequence[:training_size], y[:training_size]
X_test, y_test = X_sequence[training_size:], y[training_size:]
from sklearn.utils import class_weight
class_weights = dict(zip(np.unique(y_train), class_weight.compute_class_weight('balanced', np.unique(y_train),
y_train)))
model.fit(X_train, y_train, batch_size=64, epochs=50,class_weight=class_weights)
model.evaluate(X_test, y_test)
y_test_prob = model.predict(X_test, verbose=1)
y_test_pred = np.where(y_test_prob > 0.5, 1, 0)
from sklearn.metrics import f1_score
f1_score(y_test, y_test_pred)
Related
I need to run gridsearch CV on a Keras model but keep running into the following error:
TypeError: Only integers, slices (:), ellipsis (...), tf.newaxis (None) and scalar tf.int32/tf.int64 tensors are valid indices, got array([20000, 20001, 20002, ..., 59997, 59998, 59999])
on line grid_result = grid.fit(x_train, y_train)
The code to run the Gridsearch CV is as follows:
batch_size = 128
epochs = 20
model_CV = KerasClassifier(build_fn=create_model,epochs=epochs,batch_size=batch_size, verbose=0)
define the grid search parameters
init_mode = ['uniform', 'normal', 'he_normal','he_uniform']
param_grid = dict(init_mode=init_mode)
grid = GridSearchCV(estimator=model_CV,param_grid=param_grid, cv=3)
grid_result = grid.fit(x_train, y_train)
create_model used above
def create_model(init_mode='uniform'):
model = Sequential()
model.add(Dense(64, kernel_initializer=init_mode,
activation=tf.nn.relu, input_dim=784))
model.add(Dropout(rate=0.5))
model.add(Dense(64, kernel_initializer=init_mode,
activation=tf.nn.relu))
model.add(Dense(10, kernel_initializer=init_mode, activation=tf.nn.softmax))
compile model
model.compile(loss='categorical_crossentropy',
optimizer=RMSprop(),
metrics=['accuracy'])
return model
Data Source
mnist = keras.datasets.mnist
(x_train, y_train),(x_test, y_test) = mnist.load_data()
Data Preprocessing
flatten = tf.keras.layers.Flatten(input_shape=[28,28])
x_train = flatten(x_train)
x_train = x_train / 255
from tensorflow.keras.utils import to_categorical
y_train = to_categorical(y_train, num_classes = num_classes)
I tried changing y_train by flattening it or not running to_categorical on y_train but I still run into the same issue.
Is the problem with x_train or y_train and how can I fix it? Thank you for any help provided.
There is an imbalance two class classification problem with 12750 samples for class 0 and 2550 samples for class 1. I've gotten class weights using class_weight.compute_class_weight and fed them to model.fit. I've tested many loss and optimizer functions. The accuracy on test data is reasonable but loss and accuracy curves aren't normal, which are shown as below. I was wonder if some one give me a suggestion that how can I smooth the curves and fix this problem.
Thank you
import tensorflow as tf
import keras
import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Flatten
from keras.layers import Conv2D, MaxPooling2D, UpSampling2D,Dropout, Conv1D
from sklearn.utils import class_weight
import scipy.io
from sklearn.model_selection import train_test_split
from sklearn.utils import shuffle
import sklearn.metrics as metrics
from sklearn.utils import class_weight
#General Variables
batch_size = 32
epochs = 100
num_classes = 2
#Load Data
# X_p300 = scipy.io.loadmat('D:/P300_challenge/BCI data- code 2005/code2005/p300Cas.mat',variable_names='p300Cas').get('p300Cas')
# X_np300 = scipy.io.loadmat('D:/P300_challenge/BCI data- code 2005/code2005/np300Cas.mat',variable_names='np300Cas').get('np300Cas')
X_p300 = scipy.io.loadmat('/content/drive/MyDrive/p300/p300Cas.mat',variable_names='p300Cas').get('p300Cas')
X_np300 = scipy.io.loadmat('/content/drive/MyDrive/p300/np300Cas.mat',variable_names='np300Cas').get('np300Cas')
X_np300=X_np300[:,:]
X_p300=X_p300[:,:]
X=np.concatenate((X_p300,X_np300))
X = np.expand_dims(X,2)
Y=np.zeros((15300,))
Y[0:2550]=1
#Shuffle data as it is now in order by row colunm index
print('Shuffling...')
X, Y = shuffle(X, Y)
#Split data between 80% Training and 20% Testing
print('Splitting...')
x_train, x_test, y_train, y_test = train_test_split(
X, Y, train_size=.8, test_size=.2, shuffle=True)
# determine the weight of each class
class_weights = class_weight.compute_class_weight('balanced',
np.unique(y_train),
y_train)
class_weights = {i:class_weights[i] for i in range(2)}
y_train = tf.keras.utils.to_categorical(y_train, num_classes)
y_test = tf.keras.utils.to_categorical(y_test, num_classes)
model = Sequential()
model.add(Conv1D(256,kernel_size=3,activation='relu', input_shape =(1680, 1)))
# model.add(Dropout(.5))
model.add(Flatten())
model.add(Dense(200, activation='relu'))
model.add(Dense(50, activation='relu'))
model.add(Dense(2, activation='softmax'))
model.compile(loss='mse',
optimizer='sgd',
metrics= ['acc'])
## use it when you want to apply weight of the classes
history = model.fit(x_train, y_train,class_weight=class_weights, validation_split = 0.3, epochs = epochs, verbose = 1)
#model.fit(x_train, y_train,batch_size=32,validation_split = 0.1, epochs = epochs, verbose = 1)
import matplotlib.pyplot as plt
history_dict = history.history
history_dict.keys()
loss_values = history_dict['loss']
val_loss_values = history_dict['val_loss']
acc = history_dict.get('acc')
epochs = range(1, len(acc) + 1)
plt.plot(epochs, loss_values, 'r--', label = 'Training loss')
plt.plot(epochs, val_loss_values, 'b', label = 'Validation_loss')
plt.title('Training and Validation Loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.show()
acc_values = history_dict['acc']
val_acc_values = history_dict['val_acc']
plt.plot(epochs, acc, 'r--', label = 'Training acc')
plt.plot(epochs, val_acc_values, 'b', label = 'Validation acc')
plt.title('Training and Validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('accuracy')
plt.legend()
plt.show()
model.summary()
test_loss, test_acc = model.evaluate(x_test, y_test)
print('test_acc:', test_acc)
i followed the guide found here(regression):
https://stackabuse.com/tensorflow-2-0-solving-classification-and-regression-problems/
using this dataset:
https://drive.google.com/file/d/1mVmGNx6cbfvRHC_DvF12ZL3wGLSHD9f_/view
and ended up with this code:
data = pd.read_csv(r'path')
X = data.iloc[:, 0:4].values
y = data.iloc[:, 4].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
input_layer = Input(shape=(X.shape[1],))
dense_layer_1 = Dense(100, activation='relu')(input_layer)
dense_layer_2 = Dense(50, activation='relu')(dense_layer_1)
dense_layer_3 = Dense(25, activation='relu')(dense_layer_2)
output = Dense(1)(dense_layer_3)
model = Model(inputs=input_layer, outputs=output)
model.compile(loss="mean_squared_error" , optimizer="adam", metrics=["mean_squared_error"])
history = model.fit(X_train, y_train, batch_size=2, epochs=100, verbose=1, validation_split=0.2)
from sklearn.metrics import mean_squared_error
from math import sqrt
pred_train = model.predict(X_train)
print(np.sqrt(mean_squared_error(y_train,pred_train)))
pred = model.predict(X_test)
print(np.sqrt(mean_squared_error(y_test,pred)))
Everything works and the model gets trained, but how do i actually use it? I want to input 4 intergers and in return get the prediction. So for example take the array [9, 4554, 1950, 0.634] and then get the predicted value. No matter what i do the model won't accept the data i am using.
Thanks for the help!
Main Problem which you are facing as per my understanding is dimension Because you insert [9,...,0.634] which of shape (4,) it mean 1D while X_test,X_train require to be 2D as per documentationo you have to convert 1D to 2D.
How You Convert
import numpy as np
X_test=[9,...,0.634]
X_test=np.array(X_test)
X_test=X_test.reshape(1,4)
model.predict(X_test)
s
I use CIFAR10 dataset to learn how to code using Keras and PyTorch.
The environment is Python 3.6.7, Torch 1.0.0, Keras 2.2.4, Tensorflow 1.14.0.
I use the same batch size, number of epochs, learning rate and optimizer.
I use DenseNet121 as the model.
After training, Keras get 69% accuracy in test data.
PyTorch just get 54% in test data.
I know the results are different, but why is the result so bad in PyTorch?
Here is the Keras code:
import os, keras
from keras.datasets import cifar10
from keras.applications.densenet import DenseNet121
batch_size = 32
num_classes = 10
epochs = 20
# The data, split between train and test sets:
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# Convert class vectors to binary class matrices.
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
# model
model = DenseNet121(include_top=True, weights=None, input_shape=(32,32,3), classes=10)
# initiate RMSprop optimizer
opt = keras.optimizers.SGD(lr=0.001, momentum=0.9)
model.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy'])
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
validation_data=(x_test, y_test),
shuffle=True)
# Score trained model.
scores = model.evaluate(x_test, y_test, verbose=1)
print('Test loss:', scores[0])
print('Test accuracy:', scores[1])
Here is the Pytorch code:
import torch
import torchvision
import torchvision.transforms as transforms
from torch import flatten
import torch.optim as optim
from torchvision import transforms, models
from torch.nn import Linear, Softmax, Module, Sequential, CrossEntropyLoss
import numpy as np
from tqdm import tqdm
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
transform = transforms.Compose([transforms.ToTensor()])
trainset = torchvision.datasets.CIFAR10(root='./DataSet', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=32, shuffle=True, num_workers=0)
testset = torchvision.datasets.CIFAR10(root='./DataSet', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=False, num_workers=0)
import torch.nn as nn
import torch.nn.functional as F
class Net(Module):
def __init__(self):
super(Net, self).__init__()
self.funFeatExtra = Sequential(*[i for i in list(models.densenet121().children())[:-1]])
self.funFlatten = flatten
self.funOutputLayer = Linear(1024, 10)
self.funSoftmax = Softmax(dim=1)
def forward(self, x):
x = self.funFeatExtra(x)
x = self.funFlatten(x, 1)
x = self.funOutputLayer(x)
x = self.funSoftmax(x)
return x
net = Net()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
for epoch in range(20): # loop over the dataset multiple times
running_loss = 0.0
for i, data in tqdm(enumerate(trainloader, 0)):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = data
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = net.cuda()(inputs.cuda())
loss = criterion(outputs, labels.cuda())
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
# if i % 2000 == 1999: # print every 2000 mini-batches
# print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 2000))
# running_loss = 0.0
print('Finished Training')
########################################################################
# The results seem pretty good.
#
# Let us look at how the network performs on the whole dataset.
correct = 0
total = 0
with torch.no_grad():
for data in tqdm(testloader):
images, labels = data
outputs = net.cpu()(images.cpu())
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: %d %%' % (100 * correct / total))
You are not supposed to softmax the model output before you pass it to CrossEntropyLoss. Per the documentation:
This criterion combines nn.LogSoftmax() and nn.NLLLoss() in one single class.
...
The input is expected to contain raw, unnormalized scores for each class.
You can softmax them separately (outside of forward()) when calculating accuracy.
I'm trying to work with lstm in tensorflow, but I got to the point I can't make a simple imdb sentiment model to converge.
I took a keras model and tried to duplicate the exact same model in tensorflow, in keras it trains and converge however in tensorflow it is just stuck at some point (0.69 loss).
I tried to make them as equal as possible, the only difference I can tell of is that in keras the padding is before the sequence, while in tensorflow I use 'post' padding due to the conventions in tensorflow.
Any idea whats wrong with my tensorflow model?
from __future__ import print_function
import random
import numpy as np
from tensorflow.contrib.keras.python.keras.preprocessing import sequence
from tensorflow.contrib.keras.python.keras.models import Sequential
from tensorflow.contrib.keras.python.keras.layers import Dense, Dropout, Activation
from tensorflow.contrib.keras.python.keras.layers import Embedding
from tensorflow.contrib.keras.python.keras.layers import LSTM
from tensorflow.contrib.keras.python.keras.layers import Conv1D, MaxPooling1D
from tensorflow.contrib.keras.python.keras.datasets import imdb
import tensorflow as tf
# Embedding
max_features = 30000
maxlen = 2494
embedding_size = 128
# Convolution
kernel_size = 5
filters = 64
pool_size = 4
# LSTM
lstm_output_size = 70
# Training
batch_size = 30
epochs = 2
class TrainData:
def __init__(self, batch_sz=batch_size):
(x_train, y_train), (_, _) = imdb.load_data(num_words=max_features)
y_train = [[int(x == 1), int(x != 1)] for x in y_train]
self._batch_size = batch_sz
self._train_data = sequence.pad_sequences(x_train, padding='pre')
self._train_labels = y_train
def next_batch(self):
if len(self._train_data) < self._batch_size:
self.__init__()
batch_x, batch_y = self._train_data[:self._batch_size], self._train_labels[:self._batch_size]
self._train_data = self._train_data[self._batch_size:]
self._train_labels = self._train_labels[self._batch_size:]
return batch_x, batch_y
def batch_generator(self):
while True:
if len(self._train_data) < self._batch_size:
self.__init__()
batch_x, batch_y = self._train_data[:self._batch_size], self._train_labels[:self._batch_size]
self._train_data = self._train_data[self._batch_size:]
self._train_labels = self._train_labels[self._batch_size:]
yield batch_x, batch_y
def get_num_batches(self):
return int(len(self._train_data) / self._batch_size)
def length(sequence):
used = tf.sign(tf.abs(sequence))
length = tf.reduce_sum(used, reduction_indices=1)
length = tf.cast(length, tf.int32)
return length
def get_model(x, y):
embedding = tf.get_variable("embedding", [max_features, embedding_size], dtype=tf.float32)
embedded_x = tf.nn.embedding_lookup(embedding, x)
print(x)
print(embedded_x)
print(length(x))
cell_1 = tf.contrib.rnn.BasicLSTMCell(lstm_output_size)
output_1, state_1 = tf.nn.dynamic_rnn(cell_1, embedded_x, dtype=tf.float32, scope="rnn_layer1",
sequence_length=length(x))
# Select last output.
last_index = tf.shape(output_1)[1] - 1
# reshaping to [seq_length, batch_size, num_units]
output = tf.transpose(output_1, [1, 0, 2])
last = tf.gather(output, last_index)
# Softmax layer
with tf.name_scope('fc_layer'):
weight = tf.get_variable(name="weights", shape=[lstm_output_size, 2])
bias = tf.get_variable(shape=[2], name="bias")
logits = tf.matmul(last, weight) + bias
loss = tf.losses.softmax_cross_entropy(y, logits=logits)
optimizer = tf.train.AdamOptimizer()
optimize_step = optimizer.minimize(loss=loss)
return loss, optimize_step
def tf_model():
x_holder = tf.placeholder(tf.int32, shape=[None, maxlen])
y_holder = tf.placeholder(tf.int32, shape=[None, 2])
loss, opt_step = get_model(x_holder, y_holder)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
step = 0
for epoch in range(10):
cost_epochs = []
train_data = TrainData()
cost_batch = 0
for batch in range(train_data.get_num_batches()):
x_train, y_train = train_data.next_batch()
_, cost_batch = sess.run([opt_step, loss],
feed_dict={x_holder: x_train,
y_holder: y_train})
cost_epochs.append(cost_batch)
step += 1
# if step % 100 == 0:
print("Epoch: " + str(epoch))
print("\tcost: " + str(np.mean(cost_epochs)))
def keras_model():
# print('Loading data...')
(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=max_features)
y_test = [[int(x == 1), int(x != 1)] for x in y_test]
x_test = sequence.pad_sequences(x_test, maxlen=maxlen, padding='pre')
model = Sequential()
model.add(Embedding(max_features, embedding_size, input_length=maxlen))
model.add(LSTM(lstm_output_size))
model.add(Dense(2))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
print('Train...')
data = TrainData()
model.fit_generator(data.batch_generator(), steps_per_epoch=data.get_num_batches(),
epochs=epochs,
validation_data=(x_test, y_test))
if __name__ == '__main__':
# keras_model()
tf_model()
EDIT
When I limit the sequence length to 100 both models converge, so I assume there is something different in the the lstm layer.
Check the initial values of your operations. In my case the adadelta optimizer in keras had initial learning rate of 1.0 and in tf.keras it had 0.001 so in the mnist dataset it converged much slowly.