I a dataset with 10000 rows and 4 features (positions of two cars and their velocity) as x_train and also y_train is my labels which is 0 or 1. I want with LSTM classifying my dataset but the accuracy do not go more than 50 percent. For LSTM I tested both input_shape (10000, 4, 1) and (10000, 1, 4) but accuracy remains around 50 percentage. Do you know what should I do to improve the accuracy? and which of (10000, 4, 1) and (10000, 1, 4) are correct format ?
x_train, x_test, y_train, y_test = train_test_split(x, label, test_size=0.25, random_state=42)
x_train = x_train.reshape(-1, 4, 1)
x_test = x_test.reshape(-1, 4, 1)
y_train = y_train.reshape(-1, 1, 1)
y_test = y_test.reshape(-1, 1, 1)
model = Sequential()
model.add(LSTM(256, input_shape=(x_train.shape[1:]), activation='tanh', return_sequences=True))
model.add(Dropout(0.2))
model.add(BatchNormalization())
model.add(LSTM(256, activation='tanh'))
model.add(Dropout(0.2))
model.add(BatchNormalization())
model.add(Dense(128, activation='tanh'))
model.add(BatchNormalization())
model.add(Dense(2, activation='softmax'))
model.compile( loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'] )
history = model.fit(x_train, y_train, validation_split=0.33, epochs=20, batch_size=128,shuffle=True )
Related
I'm using Tensorflow to train a word2vec skip gram model. The computation graph is in the code below:
# training data
self.dataset = tf.data.experimental.make_csv_dataset(file_name, batch_size=self.batch_size, column_names=['input', 'output'], header=False, num_epochs=self.epochs)
self.datum = self.dataset.make_one_shot_iterator().get_next()
self.inputs, self.labels = self.datum['input'], self.datum['output']
# embedding layer
self.embedding_g = tf.Variable(tf.random_uniform((self.n_vocab, self.n_embedding), -1, 1))
self.embed = tf.nn.embedding_lookup(self.embedding_g, self.inputs)
# softmax layer
self.softmax_w_g = tf.Variable(tf.truncated_normal((self.n_context, self.n_embedding)))
self.softmax_b_g = tf.Variable(tf.zeros(self.n_context))
# Calculate the loss using negative sampling
self.labels = tf.reshape(self.labels, [-1, 1])
self.loss = tf.nn.sampled_softmax_loss(
weights=self.softmax_w_g,
biases=self.softmax_b_g,
labels=self.labels,
inputs=self.embed,
num_sampled=self.n_sampled,
num_classes=self.n_context)
self.cost = tf.reduce_mean(self.loss)
self.optimizer = tf.train.AdamOptimizer().minimize(self.cost)
But after 25 epochs, loss values begin to increase. Is there any reason for this?
I want to test a customized objective function for lightgbm in multi-class classification.
I have specified the parameter "num_class=3".
However, an error: "
Number of classes must be 1 for non-multiclass training" is thrown
I am using python 3.6 and lightgbm version 0.2
# iris data
from sklearn import datasets
import lightgbm as lgb
import numpy as np
iris = datasets.load_iris()
X = iris['data']
y = iris['target']
# construct train-test
num_train = int(X.shape[0] / 3 * 2)
idx = np.random.permutation(X.shape[0])
x_train = X[idx[:num_train]]
x_test = X[idx[num_train:]]
y_train = y[idx[:num_train]]
y_test = y[idx[num_train:]]
# softmax function
def softmax(x):
'''
input x: an np.array of n_sample * n_class
return : an np.array of n_sample * n_class (probabilities)
'''
x = np.where(x>100, 100, x)
x = np.exp(x)
return x / np.reshape(np.sum(x, 1), [x.shape[0], 1])
# objective function
def objective(y_true, y_pred):
'''
input:
y_true: np.array of size (n_sample,)
y_pred: np.array of size (n_sample, n_class)
'''
y_pred = softmax(y_pred)
temp = np.zeros_like(y_pred)
temp[range(y_pred.shape[0]), y_true] = 1
gradient = y_pred - temp
hessian = y_pred * (1 - y_pred)
return [gradient, hessian]
# lightgbm model
model = lgb.LGBMClassifier(n_estimators=10000,
num_classes = 3,
objective = objective,
nthread=4)
model.fit(x_train, y_train,
eval_metric = 'multi_logloss',
eval_set = [(x_test, y_test), (x_train, y_train)],
eval_names = ['valid', 'train'],
early_stopping_rounds = 200, verbose = 100)
Let me answer my own question.
The arguments in the objective function should be:
y_true of size [n_sample, ]
y_pred of size [n_sample * n_class, ] instead of [n_sample, n_class]
To be more specific, y_pred should be like
y_pred = [first_class, first_class,..., second_class, second_class,..., third_class, third_class,...]
Moreover, gradient and hessian should be grouped in the same way.
def objective(y_true, y_pred):
'''
input:
y_true: np.array of size [n_sample,]
y_pred: np.array of size [n_sample * n_class, ]
return:
gradient and hessian should have exactly the same form of y_pred
'''
y_pred = np.reshape(y_pred, [num_train, 3], order = 'F')
y_pred = softmax(y_pred)
temp = np.zeros_like(y_pred)
temp[range(y_pred.shape[0]), y_true] = 1
gradient = y_pred - temp
hessian = y_pred * (1 - y_pred)
return [gradient.ravel(order = 'F'), hessian.ravel(order = 'F')]
I am new to opencv and python.
I am trying to create sudoku solver in opencv and want to use this image as my dataset for recognizing the digits in sudoku.
I want the entire image to be used as dataset.
sudoku digits dataset
Dimensions: 468x108
This image has 39 numbers in a row and 9 such rows [ 1 .. 9 ]
image = cv2.imread( 'images/digits_sudoku4.png')
image = cv2.resize( image, None, fx=2, fy=2,)
gray = cv2.cvtColor( image, cv2.COLOR_BGR2GRAY)
cells = [np.hsplit(row, 39) for row in np.vsplit(gray, 12)]
# Convert the List data type to Numpy Array
x = np.array(cells)
print ("The shape of our cells array: " + str(x.shape))
train = x.astype(np.float32) # Size = (3500,400)
# Create labels for train and test data
k = [ 1, 2, 3, 4, 5, 6, 7, 8, 9]
train_labels = np.repeat( k, 468)[:, np.newaxis]
# Initiate kNN, train the data, then test it with test data for k=3
knn = cv2.KNearest()
knn.train(train, train_labels)
#ret, result, neighbors, distance = knn.find_nearest(test, k=3)
# Now we check the accuracy of classification
# For that, compare the result with test_labels and check which are wrong
'''
matches = result == test_labels
correct = np.count_nonzero(matches)
accuracy = correct * (100.0 / result.size)
print("Accuracy is = %.2f" % accuracy + "%")
'''
cv2.imshow( 'Sudoku', gray)
cv2.waitKey(0)
cv2.destroyAllWindows()
I am facing this error on line knn.train(train, train_labels)...
cv2.error: /build/opencv-SviWsf/opencv-2.4.9.1+dfsg/modules/ml/src/inner_functions.cpp:857: error: (-5) train data must be floating-point matrix in function cvCheckTrainData
Please help me out.
Thankyou.
Updated question:
I did this, but I am getting the same result for both precision and recall is it because I am using average ='binary'?
But when I use average='macro' I get this error message:
Test a custom review
messageC:\Python27\lib\site-packages\sklearn\metrics\classification.py:976:
DeprecationWarning: From version 0.18, binary input will not be
handled specially when using averaged precision/recall/F-score. Please
use average='binary' to report only the positive class performance.
'positive class performance.', DeprecationWarning)
Here is my updated code:
path = 'opinions.tsv'
data = pd.read_table(path,header=None,skiprows=1,names=['Sentiment','Review'])
X = data.Review
y = data.Sentiment
#Using CountVectorizer to convert text into tokens/features
vect = CountVectorizer(stop_words='english', ngram_range = (1,1), max_df = .80, min_df = 4)
X_train, X_test, y_train, y_test = train_test_split(X,y,random_state=1, test_size= 0.2)
#Using training data to transform text into counts of features for each message
vect.fit(X_train)
X_train_dtm = vect.transform(X_train)
X_test_dtm = vect.transform(X_test)
#Accuracy using KNN Model
KNN = KNeighborsClassifier(n_neighbors = 3)
KNN.fit(X_train_dtm, y_train)
y_pred = KNN.predict(X_test_dtm)
print('\nK Nearest Neighbors (NN = 3)')
#Naive Bayes Analysis
tokens_words = vect.get_feature_names()
print '\nAnalysis'
print'Accuracy Score: %f %%'% (metrics.accuracy_score(y_test,y_pred)*100)
print "Precision Score: %f%%" % precision_score(y_test,y_pred, average='binary')
print "Recall Score: %f%%" % recall_score(y_test,y_pred, average='binary')
By using the code above I get same value for precision and recall.
Thank you for answering my question, much appreciated.
To calculate precision and recall metrics, you should import the according methods from sklearn.metrics.
As stated in the documentation, their parameters are 1-d arrays of true and predicted labels:
from sklearn.metrics import precision_score
from sklearn.metrics import recall_score
y_true = [0, 1, 2, 0, 1, 2]
y_pred = [0, 2, 1, 0, 0, 1]
print('Calculating the metrics...')
recision_score(y_true, y_pred, average='macro')
>>> 0.22
recall_score(y_true, y_pred, average='macro')
>>> 0.33
I am struggling with different metrics while evaluating neural networks.
My investigations showed that Keras (version 1.2.2) calculates different values for specific metrics (using function evaluate) compared to sklearn.classification report.
Specifically, the values for the metric 'precision' (i.e. 'precision' of Keras != 'precision' of sklearn) or 'recall' (i.e. 'recall' of Keras != 'recall' of sklearn) differ.
For the following working example the differences seem to be random, but evaluating bigger networks shows that 'precision' of Keras equals (almost) 'recall' of sklearn whereas both 'recall' metrics differ clearly.
I appreciate your help!
from __future__ import print_function
import numpy as np
np.random.seed(1337) # for reproducibility
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils # numpy utils for to_categorical()
from keras import backend as K # abstract backend API (in order to generate compatible code for Theano and Tf)
from sklearn.metrics import classification_report
batch_size = 128
nb_classes = 10
nb_epoch = 30
# input image dimensions
img_rows, img_cols = 28, 28
# number of convolutional filters to use
nb_filters = 32
# size of pooling area for max pooling
pool_size = (2, 2)
# convolution kernel size
kernel_size = (3, 3)
# the data, shuffled and split between train and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data()
if K.image_dim_ordering() == 'th':
X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 1)
X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255 # range [0,1]
X_test /= 255 # range [0,1]
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 = np_utils.to_categorical(y_train, nb_classes) # necessary for use of categorical_crossentropy
Y_test = np_utils.to_categorical(y_test, nb_classes) # necessary for use of categorical_crossentropy
# create model
model = Sequential()
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],
border_mode='valid',
input_shape=input_shape))
model.add(Activation('relu'))
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
# configure model
model.compile(loss='categorical_crossentropy',
optimizer='adadelta',
metrics=['accuracy', 'precision', 'recall'])
# train model
model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch,
verbose=1, validation_data=(X_test, Y_test))
# evaluate model with keras
score = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])
print('Test precision:', score[2])
print('Test recall:', score[3])
# evaluate model with sklearn
predictions_last_epoch = model.predict(X_test, batch_size=batch_size, verbose=1)
target_names = ['class 0', 'class 1', 'class 2', 'class 3', 'class 4',
'class 5', 'class 6', 'class 7', 'class 8', 'class 9']
predicted_classes = np.argmax(predictions_last_epoch, axis=1)
print('\n')
print(classification_report(y_test, predicted_classes,
target_names=target_names, digits = 6))
E D I T
The output of the script given above:
Test score: 0.0271549037314
Test accuracy: 0.9916
Test precision: 0.992290322304
Test recall: 0.9908
9728/10000 [============================>.] - ETA: 0s
precision recall f1-score support
class 0 0.987867 0.996939 0.992382 980
class 1 0.993860 0.998238 0.996044 1135
class 2 0.990329 0.992248 0.991288 1032
class 3 0.991115 0.994059 0.992585 1010
class 4 0.994882 0.989817 0.992343 982
class 5 0.991041 0.992152 0.991597 892
class 6 0.993678 0.984342 0.988988 958
class 7 0.992180 0.987354 0.989761 1028
class 8 0.989754 0.991786 0.990769 974
class 9 0.991054 0.988107 0.989578 1009
avg / total 0.991607 0.991600 0.991597 10000
For another model:
val/test loss: 0.231304548573
val/test categorical_accuracy: **0.978500002956**
val/test precision: *0.995103668976*
val/test recall: 0.941900001907
val/test fbeta_score: 0.967675107574
val/test mean_squared_error: 0.0064611148566
10000/10000 [==============================] - 0s
precision recall f1-score support
class 0 0.989605 0.971429 0.980433 980
class 1 0.985153 0.993833 0.989474 1135
class 2 0.988154 0.969961 0.978973 1032
class 3 0.981373 0.991089 0.986207 1010
class 4 0.968907 0.983707 0.976251 982
class 5 0.997633 0.945067 0.970639 892
class 6 0.995690 0.964509 0.979852 958
class 7 0.987230 0.977626 0.982405 1028
class 8 0.945205 0.991786 0.967936 974
class 9 0.951429 0.990089 0.970374 1009
avg / total *0.978964* **0.978500** 0.978522 10000
Definition of desired metrics (for model.compile):
metrics=['categorical_accuracy', 'precision', 'recall', 'fbeta_score', 'mean_squared_error']
model.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=metrics)
Output of model.metrics_names:
['loss', 'categorical_accuracy', 'precision', 'recall', 'fbeta_score', 'mean_squared_error']
Yes, it is different due to the fact that the sklearn classification report gives you the weighted average based on the support.
Experiment with:
from sklearn.metrics import classification_report
y_true = [0, 1,2,1]
y_pred = [0, 0,2,0]
target_names = ['class 0', 'class 1', 'class 2']
print(classification_report(y_true, y_pred, target_names=target_names))
Gives you:
precision recall f1-score support
class 0 0.33 1.00 0.50 1
class 1 0.00 0.00 0.00 2
class 2 1.00 1.00 1.00 1
avg / total 0.33 0.50 0.38 **4**
However, (1+0+0.33)/3 = 0.44(3), but as it seems from the support column sklearn returns (1*1+0*2+0.33*1)/4=0.3325