I'm trying to train an autoencoder but have problems in reshaping my X_train to fit it to my model model().
from tensorflow import keras
from keras.layers import *
from keras.models import Model
from keras.models import Sequential
from keras.optimizers import Adam
from keras.optimizers import RMSprop
from keras.utils import plot_model
X_train = np.array(X_train, dtype=np.float)
X_test =np.array(X_train, dtype=np.float)
X_train = X_train.reshape(len(X_train), 100,1)
X_test = X_test.reshape(len(X_test), 100,1)
#inputs = Input(shape=(230, 1,100))
epoch = 100
batch = 128
def model():
m = Sequential()
# ##m.add(Reshape((,)))
m.add(Flatten())
m.add(Dense(512, activation='relu'))
m.add(Dense(128, activation = 'relu'))
m.add(Dense(2, activation = 'linear'))
m.add(Dense(128, activation = 'relu'))
m.add(Dense(512, activation = 'relu'))
m.add(Dense(784, activation = 'sigmoid'))
m.compile(loss='mean_squared_error', optimizer = 'rmsprop', metrics = ['accuracy'])
# Fit data to model m
m.fit(X_train, X_train, batch_size = batch, epochs = epoch)
m.summary()
#score = m.evaluate(X_test, Y_test, verbose = 0)
#print('Test loss:' score[0])
#print('Test accuracy:', score[1])
#m.summary()
mod = model()
The of dimension of my data is the following:
X_train = (523, 100,1)
X_test = (523, 100,1)
To fix your issue, change the following:
X_train = X_train.reshape((-1, 100))
X_test = X_test.reshape((-1, 100))
Delete the Flatten layer and use 100 neurons for the last layer as stated in the comments.
Related
I built a simple categorical time series model to predict the next number of a random sequence, but the accuracy hardly moved even I trained it for 10000 epochs. The validation loss started to take off after a few hundred epochs. Could anyone make suggestions for improvement? Here's the model:
import os
import sys
import pandas as pd
import numpy as np
from sklearn.preprocessing import OneHotEncoder
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, LSTM
DEVICE = 'CPU'
if DEVICE == 'CPU':
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
else:
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
print(tf.test.gpu_device_name())
TOTAL_CATALOG=4
POSSIBLE_OUTCOME_COL=4
LOOK_BACK_WINDOW=1
TRAINING_DATA_RATIO=0.8
TRAINING_EPOCHS=10000
sys.path.insert(0, '/DataScience/MyModules')
from m6data import getDrawData, series_to_supervised, Split_data, get_all_categories
def get_all_categories_local(last_combination):
all_category = np.arange(1, last_combination+1)
return all_category.reshape(1,all_category.shape[0])
All_categories=get_all_categories_local(TOTAL_CATALOG)
data_sequence = [1,1,2,4,2,3,1,2,3,3,4,1,2,3,4,2,2,3,1,3]
raw_df = pd.DataFrame(data_sequence, columns=['NE'])
values = raw_df.values
# 05-Apr-2022: One-Hot Encoding
oh_encoder = OneHotEncoder(categories=All_categories, sparse=False)
encoded_input = oh_encoder.fit_transform(values)
FEATURES = encoded_input.shape[1]
POSSIBLE_OUTCOME_COL = FEATURES
draw_reframe = series_to_supervised(encoded_input, LOOK_BACK_WINDOW,1)
train, test = Split_data(draw_reframe, TRAINING_DATA_RATIO)
# Total input = all possible One-Hot Encoding outcome * number of look-back samples.
ALL_INPUT = POSSIBLE_OUTCOME_COL * LOOK_BACK_WINDOW
# split into input and outputs
train_X, train_y = train.iloc[:,:ALL_INPUT], train.iloc[:,ALL_INPUT:]
test_X, test_y = test.iloc[:,:ALL_INPUT], test.iloc[:,ALL_INPUT:]
train_X = train_X.values.reshape((train_X.shape[0], LOOK_BACK_WINDOW , FEATURES))
test_X = test_X.values.reshape((test_X.shape[0], LOOK_BACK_WINDOW, FEATURES))
print(train_X.shape, train_y.shape)
print(test_X.shape, test_y.shape)
def create_model():
model = Sequential()
model.add(LSTM(10,
return_sequences=False,
input_shape=(train_X.shape[1], train_X.shape[2]),
activation='relu'
)
)
#model.add(LSTM(20))
model.add(Dense(units=train_y.shape[1], activation='softmax'))
model.compile(optimizer = tf.keras.optimizers.Adam(learning_rate=0.00005),
loss = 'categorical_crossentropy',
metrics=['accuracy'])
return model
model=create_model()
history = model.fit(
train_X, train_y,
epochs=TRAINING_EPOCHS,
batch_size=8,
validation_data=(test_X, test_y),
verbose=1,
)
Here are the plots of accuracies and losses (red=training, blue=validation).
Accuracies
Losses
Thank you in advance for any suggestions.
Update (13-Jun-2022)
I changed my model to the following
def create_model():
model = Sequential()
model.add(LSTM(50,
return_sequences=True,
input_shape=(train_X.shape[1], train_X.shape[2]),
activation='relu'
)
)
model.add(LSTM(units=1000, kernel_regularizer=regularizers.l1(0.05), return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=1000, kernel_regularizer=regularizers.l1(0.05), return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=1000, kernel_regularizer=regularizers.l1(0.05), return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=1000, kernel_regularizer=regularizers.l1(0.05), activation='relu'))
model.add(Dropout(0.3))
model.add(BatchNormalization())
model.add(Dense(1000))
model.add(Dense(units=train_y.shape[1], activation='softmax'))
model.compile(optimizer = tf.keras.optimizers.SGD(learning_rate=1e-2, nesterov=True),
#tf.keras.optimizers.Adam(learning_rate=0.001),
loss = 'categorical_crossentropy',
metrics=['accuracy'])
return model
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.2,
patience=20,min_lr=1e-10)
early_stop = EarlyStopping(monitor='loss', patience=100)
history = model.fit(
train_X, train_y,
epochs=TRAINING_EPOCHS,
batch_size=16,
validation_split=0.1,
validation_data=(test_X, test_y),
verbose=1,
shuffle=False,
callbacks=([reduce_lr], [early_stop])
Accuracy was bouncing around and Val_accuracy was zero all the way. The loss and val_loss were almost the same and dropping together.
Can anyone advise what I can do in this scenario?
I am trying to Save the entire model after each epoch using ModelCheckpoint callback.
After training if i am trying to load the saved model and evaluate, the model weights are not loaded. Why is this load_model not working for loading the model weights?
import tensorflow as tf
print(tf.__version__)
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten, Conv2D, MaxPooling2D
from tensorflow.keras.callbacks import ModelCheckpoint
from tensorflow.keras.models import load_model
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()
x_train = x_train / 255.0
x_test = x_test / 255.0
# Use smaller subset -- speeds things up
x_train = x_train[:10000]
y_train = y_train[:10000]
x_test = x_test[:1000]
y_test = y_test[:1000]
def get_test_accuracy(model, x_test, y_test):
test_loss, test_acc = model.evaluate(x=x_test, y=y_test, verbose=0)
print('accuracy: {acc:0.3f}'.format(acc=test_acc))
def get_new_model():
model = Sequential([
Conv2D(filters=16, input_shape=(32, 32, 3), kernel_size=(3, 3),
activation='relu', name='conv_1'),
Conv2D(filters=8, kernel_size=(3, 3), activation='relu', name='conv_2'),
MaxPooling2D(pool_size=(4, 4), name='pool_1'),
Flatten(name='flatten'),
Dense(units=32, activation='relu', name='dense_1'),
Dense(units=10, activation='softmax', name='dense_2')
])
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
return model
# Create Tensorflow checkpoint object
checkpoint_path = "model_checkpoints"
checkpoint = ModelCheckpoint(filepath=checkpoint_path,
save_weights_only=False,
save_freq="epoch",
verbose=1)
# Create and fit model with checkpoint
model = get_new_model()
model.fit(x_train,
y_train,
epochs=3,
callbacks=[checkpoint])
# Get the model's test accuracy
get_test_accuracy(model,x_test,y_test)
# Reload model from scratch
model = load_model(checkpoint_path)
get_test_accuracy(model,x_test,y_test)
The accuracy after loading the saved model load_model is not same as the accuracy for trained model.
I'm trying to save the following file but not sure how. I've tried placing with tf.Session as sess just prior to training my model history = model.fit_generator... but was receiving ValueError: No variables to save. Then I tried placing with tf.Session... above my model initialisation at model = Sequential(). I'm new to Tensorflow so I'm just trying to learn the ropes.
Any guidance would be great, thanks!
import numpy as np
import keras
from keras import backend as K
from keras.models import Sequential
from keras.layers import Activation, Dropout, Input
from keras.layers.core import Dense, Flatten
from keras.optimizers import Adam, Adadelta, SGD
from keras.metrics import categorical_crossentropy
from keras.preprocessing.image import ImageDataGenerator
from keras.layers.normalization import BatchNormalization
from keras.layers.convolutional import *
from sklearn.metrics import confusion_matrix
from keras.models import Model
from keras.utils import np_utils
import itertools
import matplotlib.pyplot as plt
import livelossplot
#%matplotlib inline
#plot_losses = livelossplot.PlotLossesKeras()
PATH = './Food-5K/'
train_path = '%straining/' %PATH
valid_path = '%svalidation/' %PATH
test_path = '%sevaluation/' %PATH
classes = ('food', 'non-food')
print (train_path)
batch_size = 16
epochs = 20
nb_train_samples = 3001
nb_validation_samples = 1000
train_batches = ImageDataGenerator(rescale=1./255, shear_range=0.2, zoom_range=0.2, horizontal_flip=True).flow_from_directory(train_path, target_size=(224,224),
batch_size=32, class_mode='binary')
valid_batches = ImageDataGenerator(rescale = 1./255 ).flow_from_directory(valid_path, target_size=(224,224),
batch_size=batch_size, class_mode='binary')
test_batches = ImageDataGenerator(rescale = 1./255).flow_from_directory(test_path, target_size=(224,224),
batch_size=batch_size, class_mode='binary')
print(type(train_batches[0]))
x_train, y_train = train_batches[0]
x_test, y_test = valid_batches[0]
print('x_train.shape: ' + str(x_train.shape))
print('y_train.shape: ' + str(y_train.shape))
print('y_train.shape: ' + str(y_train.reshape(y_train.shape + (1,)).shape))
print('x_test.shape: ' + str(x_test.shape))
print('y_test.shape: ' + str(y_test.shape))
print('y_test.shape: ' + str(y_test.reshape(y_test.shape + (1,)).shape))
X_train_flatten = x_train.reshape(x_train.shape[0], -1).T
X_test_flatten = x_test.reshape(x_test.shape[0], -1).T
y_train_flatten = y_train.T
y_test_flatten = y_test.T
print('X_train_flatten.shape: ' + str(X_train_flatten.T.shape))
print('y_train_flatten.shape: ' + str(y_train_flatten.shape))
#print('y_train_flatten.shape: ' + str(np.squeeze(y_train_flatten, axis=(2,)).shape))
print('X_test_flatten.shape: ' + str(X_test_flatten.T.shape))
print('y_test_flatten.shape: ' + str(y_test_flatten.shape))
#print('y_test_flatten.shape: ' + str(np.squeeze(y_test_flatten, axis=(2,)).shape))
train_set_x = X_train_flatten/255.
test_set_x = X_test_flatten/255.
print('len(train_set_x): ' + str(train_set_x.shape))
print('len(test_set_x): ' + str(test_set_x.shape))
print(y_train.shape)
# plots images with labels within jupyter notebook
def plots(ims, figsize=(80,60), rows=1, interp=False, titles=None):
if type(ims[0]) is np.ndarray:
#print(ims[0])
#ims = np.array(ims).astype(np.uint8)
#print(ims)
if (ims.shape[-1] != 3):
ims = ims.transpose((1,2,3,1))
f = plt.figure(figsize=figsize)
cols = len(ims)//rows if len(ims) % 2 == 0 else len(ims)//rows + 1
for i in range(len(ims)):
sp = f.add_subplot(rows, cols, i+1)
sp.axis('Off')
if titles is not None:
sp.set_title(titles[i], fontsize=15)
plt.imshow(ims[i], interpolation=None if interp else 'none')
imgs, labels = next(train_batches)
plots(imgs, titles=labels)
# Deep Multilayer Perceptron model
model = Sequential()
# Set the initial random weights > kernel_initializer
model.add(Flatten(input_shape=(224, 224, 3)))
model.add(Dense(200, input_dim=150528, kernel_initializer='normal'))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(100, input_dim=200, kernel_initializer='normal'))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(10, input_dim=100, kernel_initializer='normal'))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1, input_dim=10, kernel_initializer='normal'))
model.add(Activation('sigmoid'))
# Rho > is a hyper-parameter which attenuates the influence of past gradient.
model.compile(optimizer=Adam(), loss='binary_crossentropy', metrics=['accuracy'])
model.summary()
# Train
history = model.fit_generator(train_batches, steps_per_epoch=32, #steps_per_epoch=nb_train_samples,
#callbacks=[plot_losses],
validation_steps = 16,
validation_data=train_batches, epochs=epochs, verbose=1)
# Evaluate
x_test, y_test = valid_batches[0]
evaluation = model.evaluate(x_test, y_test, batch_size=batch_size, verbose=1)
print('Summary: Loss over the test dataset: %.2f, Accuracy: %.2f' % (evaluation[0], evaluation[1]))
print(history.history.keys())
# summarize history for accuracy
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
# summarize history for loss
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
From Keras documentation:
from keras.models import load_model
model.save('my_model.h5') # creates a HDF5 file 'my_model.h5'
del model # deletes the existing model
# returns a compiled model
# identical to the previous one
model = load_model('my_model.h5')
I am using ANN for Multiclass Classification(12 classes) in Python. However i am getting errors. Here is the code snippet:
import keras
from keras.models import Sequential
from keras.layers import Dense
# Initialising the ANN
# Initialising the ANN
classifier = Sequential()
# Adding the input layer and the first hidden layer
classifier.add(Dense(units = 8, kernel_initializer = 'uniform', activation = 'relu', input_dim = 4))
# Adding the second hidden layer
classifier.add(Dense(units = 8, kernel_initializer = 'uniform', activation = 'relu'))
# Adding the output layer
classifier.add(Dense(units = 13, kernel_initializer = 'uniform', activation = 'softmax'))
# Compiling the ANN
classifier.compile(optimizer = 'adam', loss = 'sparse_categorical_crossentropy', metrics = ['accuracy'])
# Fitting the ANN to the Training set
classifier.fit(X_train, y_train, batch_size =200 , epochs = 100)
# Predicting the Test set results
y_pred = classifier.predict(X_test)
# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
The program runs all the way until running the neural code and also finds the y_pred. After that i get this error i.e the confusion matrix is not formed.
The error:
ValueError: Classification metrics can't handle a mix of multiclass and continuous-multioutput targets
from sklearn.metrics import confusion_matrix
y_pred = classifier.predict(X_test)
predictions = np.argmax(y_pred, axis=-1)
cm = confusion_matrix(y_test, y_pred)
I hope it will resolve your problem
from sklearn.metrics import confusion_matrix
from sklearn.preprocessing import LabelEncoder
y_pred = classifier.predict(X_test)
predictions = np.argmax(y_pred, axis=-1)
label_encoder = LabelEncoder().fit(y_test)
label_y = label_encoder.transform(y_test)
cm = confusion_matrix(label_y, predictions)
I am just a novice in area of deep learning.
I made my first basic attempt with Keras Conv1D. Not sure what I did and whether I did it right. My input data is simply total sales by every week (total of 313 weeks), for stores across US and with a time step of 1.
Here is my code:
from pandas import read_csv
import matplotlib.pyplot as plt
import numpy
from keras.datasets import imdb
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Flatten
from keras.layers.convolutional import Conv1D
from keras.layers.convolutional import MaxPooling1D
from keras.layers.embeddings import Embedding
from keras.preprocessing import sequence
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
def create_dataset(dataset, look_back=1):
dataX, dataY = [], []
for i in range(len(dataset)-look_back):
a = dataset[i:(i+look_back), 0]
dataX.append(a)
dataY.append(dataset[i + look_back, 0])
return numpy.array(dataX), numpy.array(dataY)
seed = 7
numpy.random.seed(seed)
dataframe = read_csv('D:/MIS793/Dataset/Academic Dataset External 2/Python scripts/totalsale _byweek.csv', usecols=[1], engine='python')
plt.plot(dataframe)
plt.show()
dataset = dataframe.values
dataset = dataset.astype('float32')
# normalize the dataset
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
train_size = int(len(dataset) * 0.67)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]
# reshape into X=t and Y=t+1
look_back = 1
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)
trainX = trainX.reshape(trainX.shape[0], trainX.shape[1], 1).astype('float32')
testX = testX.reshape(testX.shape[0], testX.shape[1], 1).astype('float32')
model = Sequential()
model.add(Conv1D(filters=10, kernel_size=1, padding='same', strides=1, activation='relu',input_shape=(1,1)))
model.add(MaxPooling1D(pool_size=1))
model.add(Flatten())
model.add(Dense(250, activation='relu'))
model.add(Dense(1, activation='linear'))
model.compile(loss='mse', optimizer='adam', metrics=['mae'])
print(model.summary())
model.fit(trainX, trainY, validation_data=(testX, testY), epochs=10, batch_size=100)
scores = model.evaluate(testX, testY, verbose=0)
print("Accuracy: %.2f%%" % (scores[1]*100))
Not sure about few things here:
Reshaping of trainX and testX.
Value of kernel_size and input_shape
My idea here is it's just one vector of sales value. 10 filters, each of size 1 move from one value to another. Input shape is of the format time step, dimensions.
I only got accuracy of 10.91%! So my first question is whether I am feeding in the right parameters.
Thanks
ASC
With model.metrics_names you can get the labels of your scores variable.
In your case it will be ['loss', 'mean_absolute_error'].
So what you are printing is not the accuracy, but the mae, multiplied by 100.
I tried using accuracy instead of mae. However I got accuracy as 0%. Just wondering as this was about predicting numerical values, should I really use accuracy? Here is my latest code.
from pandas import read_csv
import matplotlib.pyplot as plt
import numpy
from keras.datasets import imdb
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Flatten
from keras.layers import Dropout
from keras.layers.convolutional import Conv1D
from keras.layers.convolutional import MaxPooling1D
from keras.layers.embeddings import Embedding
from keras.preprocessing import sequence
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
def create_dataset(dataset, look_back=1):
dataX, dataY = [], []
for i in range(len(dataset)-look_back):
a = dataset[i:(i+look_back), 0]
dataX.append(a)
dataY.append(dataset[i + look_back, 0])
return numpy.array(dataX), numpy.array(dataY)
# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
dataframe = read_csv('D:/MIS793/Dataset/Academic Dataset External 2/Python scripts/totalsale _byweek.csv', usecols=[1], engine='python')
plt.plot(dataframe)
plt.show()
dataset = dataframe.values
dataset = dataset.astype('float32')
# normalize the dataset
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
train_size = int(len(dataset) * 0.67)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]
# reshape into X=t and Y=t+1
look_back = 1
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)
trainX = trainX.reshape(trainX.shape[0], trainX.shape[1],1).astype('float32')
testX = testX.reshape(testX.shape[0], testX.shape[1],1).astype('float32')
model = Sequential()
model.add(Conv1D(filters=20, kernel_size=1, padding='same', strides=1, activation='relu',input_shape=(1,1)))
model.add(MaxPooling1D(pool_size=1))
model.add(Conv1D(filters=10, kernel_size=1, padding='same', strides=1, activation='relu'))
model.add(MaxPooling1D(pool_size=1))
model.add(Flatten())
model.add(Dense(4, activation='relu'))
model.add(Dense(1, activation='linear'))
model.compile(loss='mse', optimizer='adam', metrics=['accuracy'])
print(model.summary())
model.fit(trainX, trainY, validation_data=(testX, testY), epochs=10, batch_size=100)
scores = model.evaluate(testX, testY, verbose=0)
print("Accuracy: %.2f%%" % (scores[1]*100))
OR should I go with MAE?
If I go with MAE, my scores will look like below:
[0.12740663779013364, 0.31208728355111426]
First one is loss and second one is MAE. Isn't that a better metrics in this case?
The final line will be like this:
print("MAE: %.2f%%" % (scores[1]))
Thanks
Anindya