I'm trying to put a collection of images through a neural network, but I can't figure out how to get a large collection of images to go into a tensorflow model, as trying to convert the collection into a numpy array causes a memory error.
I should note that I am very new to tensorflow.
import numpy as np
from skimage.io import imread_collection
from tensorflow import keras
from tensorflow.keras import layers
def gen(arr):return(i.reshape(400*600*3) for i in arr) # Only used in Attempt2.
labelFile=open("lables_text_file.txt","r")
labels=labelFile.read()
labelFile.close()
labels=getTrain(labels)#Converts to a tuple containing the lables in order.
data = imread_collection("path_to_images/*.jpg", conserve_memory=True)
train=data[:-len(data)//4]
trainLabels=labels[:-len(data)//4]
test=data[-len(data)//4:]
testLabels=labels[-len(data)//4:]
#train = train.reshape(-1, 400*600*3) # Attempt1
#test = test.reshape(-1, 400*600*3) # Attempt1
#train = gen(train) # Attempt2
#test = gen(test) # Attempt2
trainLabels = keras.utils.to_categorical(trainLabels, 23)
testLabels = keras.utils.to_categorical(testLabels, 23)
model=keras.Sequential([keras.Input(shape=(400*600*3,)),
layers.Dense(600, name='hidden1', activation='relu'),
layers.Dense(400, name='hidden2', activation='relu'),
layers.Dense(46, name='hidden3', activation='relu'),
layers.Dense(23, activation="softmax")])
optimizer = keras.optimizers.Adam(learning_rate=0.0015)
model.compile(loss=keras.losses.CategoricalCrossentropy(), optimizer=optimizer, metrics=[keras.metrics.CategoricalAccuracy()])
model.fit(train,trainLabels,batch_size=128,epochs=8,validation_data=(test,testLabels), shuffle=True)
When I run the code as is, this is the result:
ValueError: Failed to find data adapter that can handle input: <class 'skimage.io.collection.ImageCollection'>, <class 'numpy.ndarray'>
When I try to use Attempt1, this is the result:
AttributeError: 'ImageCollection' object has no attribute 'reshape'
When I try to use Attempt2, this is the result:
ValueError: `y` argument is not supported when using python generator as input.
How can I put the data into `model.fit, such that it will successfully train the neural network?
I think I may have solved the problems.
Working code:
import numpy as np
from skimage.io import imread_collection
from tensorflow import keras
from tensorflow.keras import layers
def gen(arr,labels):return((arr[i].reshape(-1,400*600*3),labels[i].reshape(-1,23)) for i in range(len(arr)))
labelFile=open("lables_text_file.txt","r")
labels=labelFile.read()
labelFile.close()
labels=getTrain(labels)#Converts to a tuple containing the lables in order.
data = imread_collection("path_to_images/*.jpg", conserve_memory=True)
train=data[:-len(data)//4]
trainLabels=labels[:-len(data)//4]
test=data[-len(data)//4:]
testLabels=labels[-len(data)//4:]
#train = train.reshape(-1, 400*600*3) # Attempt1
#test = test.reshape(-1, 400*600*3) # Attempt1
trainLabels = keras.utils.to_categorical(trainLabels, 23)
testLabels = keras.utils.to_categorical(testLabels, 23)
train = gen(train,trainLabels) # Attempt2
test = gen(test,testLabels) # Attempt2
model=keras.Sequential([keras.Input(shape=(400*600*3,)),
layers.Dense(600, name='hidden1', activation='relu'),
layers.Dense(400, name='hidden2', activation='relu'),
layers.Dense(46, name='hidden3', activation='relu'),
layers.Dense(23, activation="softmax")])
optimizer = keras.optimizers.Adam(learning_rate=0.0015)
model.compile(loss=keras.losses.CategoricalCrossentropy(), optimizer=optimizer, metrics=[keras.metrics.CategoricalAccuracy()])
model.fit(train,None,batch_size=128,epochs=8,validation_data=(test,testLabels), shuffle=True)
The solution was to pass in a generator that returns two-tuples containing the input and label (instead of passing the labels in directly), but there were other problems that I may include in this answer if I get the time.
Related
I'm trying to follow the tutorial given here.
This tutorial trains a Keras model using a genetic algorithm, with the PyGAD package. I'm interested in the binary classification case. My input matrix is of dimension 10000x20. Hence, I've created the following model using Keras:
input_layer = tensorflow.keras.layers.Input(20)
dense_layer1 = tensorflow.keras.layers.Dense(500, activation="relu")(input_layer)
dense_layer2 = tensorflow.keras.layers.Dense(500, activation="relu")(dense_layer1)
output_layer = tensorflow.keras.layers.Dense(1, activation="softmax")(dense_layer2)
model = tensorflow.keras.Model(inputs=input_layer, outputs=output_layer)
keras_ga = pygad.kerasga.KerasGA(model=model,
num_solutions=10)
However, when I go to run the algorithm, using ga_instance.run(), I get the error:
ValueError: Shapes (10000,) and (10000, 1) are incompatible
I can't figure out why I'm getting this error? I want my Keras model to have 2 hidden layers, each with 500 hidden nodes and 1 output node.
I think the problem is related to how each output is represented in the array. if you have a single output for 10000 instances, then this is an example of preparing the data that works with PyGAD. Its shape is (1000, 1).
numpy.random.uniform(0, 1, (1000, 1))
Here is a code that works but for a simple network architecture because, based on the fitness function you used, the fitness sometimes is NaN.
As I do not have the same data you used, I generated the input/output data randomly.
import tensorflow.keras
import pygad.kerasga
import numpy
import pygad
def fitness_func(solution, sol_idx):
global data_inputs, data_outputs, keras_ga, model
model_weights_matrix = pygad.kerasga.model_weights_as_matrix(model=model,
weights_vector=solution)
model.set_weights(weights=model_weights_matrix)
predictions = model.predict(data_inputs)
cce = tensorflow.keras.losses.CategoricalCrossentropy()
solution_fitness = 1.0 / (cce(data_outputs, predictions).numpy() + 0.00000001)
# print("solution_fitness", cce(data_outputs, predictions).numpy(), solution_fitness)
return solution_fitness
def callback_generation(ga_instance):
print("Generation = {generation}".format(generation=ga_instance.generations_completed))
print("Fitness = {fitness}".format(fitness=ga_instance.best_solution(ga_instance.last_generation_fitness)[1]))
data_inputs = numpy.random.uniform(0, 1, (1000, 20))
data_outputs = numpy.random.uniform(0, 1, (1000, 1))
# create model
from tensorflow.keras.layers import Dense, Dropout
l1_rate=1e-6
l2_rate = 1e-6
input_layer = tensorflow.keras.layers.InputLayer(20)
dense_layer1 = tensorflow.keras.layers.Dense(10, activation="relu",kernel_regularizer=tensorflow.keras.regularizers.l1_l2(l1=l1_rate, l2=l2_rate))
output_layer = tensorflow.keras.layers.Dense(1, activation="sigmoid")
model = tensorflow.keras.Sequential()
model.add(input_layer)
model.add(dense_layer1)
model.add(Dropout(0.2))
model.add(output_layer)
keras_ga = pygad.kerasga.KerasGA(model=model,
num_solutions=10)
# Run pygad
num_generations = 30
num_parents_mating = 5
initial_population = keras_ga.population_weights
ga_instance = pygad.GA(num_generations=num_generations,
num_parents_mating=num_parents_mating,
initial_population=initial_population,
fitness_func=fitness_func,
on_generation=callback_generation)
ga_instance.run()
Thanks for using PyGAD!
I am building a model based on this code for noise suppression. My problem with the vanilla implementation is that it loads all data at once, which is not the best idea when the training data gets really large; my input file, denoted in the linked code as training.h5, is over 30 GB.
I decided to instead go with tf.data interface that should allow me to work with large data sets; my problem here is that I don't know how to properly shape TFRecordDataset so that it meets what's required by the Model API.
If you check model.fit(x_train, [y_train, vad_train], it essentially requires the following:
x_train, shape [nb_sequences, window, 42]
y_train, shape [nb_sequences, window, 22]
vad_train, shape [nb_sequences, window, 1]
window one typically fixes (in the code: 2000), so the only variable nb_sequences that stems from how large is your data set. However, with tf.data, we don't supply x and y, but only x (see Model API docs).
Saving tfrecord to file
In an effort to make the code reproducible, I created the input file with the following code:
writer = tf.io.TFRecordWriter(path='example.tfrecord')
for record in data:
feature = {}
feature['X'] = tf.train.Feature(float_list=tf.train.FloatList(value=record[:42]))
feature['y'] = tf.train.Feature(float_list=tf.train.FloatList(value=record[42:64]))
feature['vad'] = tf.train.Feature(float_list=tf.train.FloatList(value=[record[64]]))
example = tf.train.Example(features=tf.train.Features(feature=feature))
serialized = example.SerializeToString()
writer.write(serialized)
writer.close()
data is our training data with shape [10000, 65]. My example.tfrecord is available here. It's 3 MB, in reality it would be 30 GB+.
You might notice that in the linked code, numpy array has shape [x, 87], while mine is [x, 65]. That's OK - the remainder is not used anywhere.
Loading the dataset with tf.data.TFRecordDataset
I would like to use tf.data to load "on demand" the data with some prefetching, there's no need to keep it all in memory. My attempt:
import datetime
import numpy as np
import h5py
import tensorflow as tf
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import GRU
from tensorflow.keras import regularizers
from tensorflow.keras.constraints import Constraint
from tensorflow.keras.callbacks import ModelCheckpoint
from tensorflow.keras import backend as K
from tensorflow.keras.layers import concatenate
def load_dataset(path):
def _parse_function(example_proto):
keys_to_features = {
'X': tf.io.FixedLenFeature([42], tf.float32),
'y': tf.io.FixedLenFeature([22], tf.float32),
'vad': tf.io.FixedLenFeature([1], tf.float32)
}
features = tf.io.parse_single_example(example_proto, keys_to_features)
return (features['X'], (features['y'], features['vad']))
dataset = tf.data.TFRecordDataset(path).map(_parse_function)
return dataset
def my_crossentropy(y_true, y_pred):
return K.mean(2 * K.abs(y_true - 0.5) * K.binary_crossentropy(y_pred, y_true), axis=-1)
def mymask(y_true):
return K.minimum(y_true + 1., 1.)
def msse(y_true, y_pred):
return K.mean(mymask(y_true) * K.square(K.sqrt(y_pred) - K.sqrt(y_true)), axis=-1)
def mycost(y_true, y_pred):
return K.mean(mymask(y_true) * (10 * K.square(K.square(K.sqrt(y_pred) - K.sqrt(y_true))) + K.square(
K.sqrt(y_pred) - K.sqrt(y_true)) + 0.01 * K.binary_crossentropy(y_pred, y_true)), axis=-1)
def my_accuracy(y_true, y_pred):
return K.mean(2 * K.abs(y_true - 0.5) * K.equal(y_true, K.round(y_pred)), axis=-1)
class WeightClip(Constraint):
'''Clips the weights incident to each hidden unit to be inside a range
'''
def __init__(self, c=2.0):
self.c = c
def __call__(self, p):
return K.clip(p, -self.c, self.c)
def get_config(self):
return {'name': self.__class__.__name__,
'c': self.c}
def build_model():
reg = 0.000001
constraint = WeightClip(0.499)
main_input = Input(shape=(None, 42), name='main_input')
tmp = Dense(24, activation='tanh', name='input_dense', kernel_constraint=constraint, bias_constraint=constraint)(
main_input)
vad_gru = GRU(24, activation='tanh', recurrent_activation='sigmoid', return_sequences=True, name='vad_gru',
kernel_regularizer=regularizers.l2(reg), recurrent_regularizer=regularizers.l2(reg),
kernel_constraint=constraint, recurrent_constraint=constraint, bias_constraint=constraint)(tmp)
vad_output = Dense(1, activation='sigmoid', name='vad_output', kernel_constraint=constraint,
bias_constraint=constraint)(vad_gru)
noise_input = concatenate([tmp, vad_gru, main_input])
noise_gru = GRU(48, activation='relu', recurrent_activation='sigmoid', return_sequences=True, name='noise_gru',
kernel_regularizer=regularizers.l2(reg), recurrent_regularizer=regularizers.l2(reg),
kernel_constraint=constraint, recurrent_constraint=constraint, bias_constraint=constraint)(noise_input)
denoise_input = concatenate([vad_gru, noise_gru, main_input])
denoise_gru = GRU(96, activation='tanh', recurrent_activation='sigmoid', return_sequences=True, name='denoise_gru',
kernel_regularizer=regularizers.l2(reg), recurrent_regularizer=regularizers.l2(reg),
kernel_constraint=constraint, recurrent_constraint=constraint, bias_constraint=constraint)(
denoise_input)
denoise_output = Dense(22, activation='sigmoid', name='denoise_output', kernel_constraint=constraint,
bias_constraint=constraint)(denoise_gru)
model = Model(inputs=main_input, outputs=[denoise_output, vad_output])
model.compile(loss=[mycost, my_crossentropy],
metrics=[msse],
optimizer='adam', loss_weights=[10, 0.5])
return model
model = build_model()
dataset = load_dataset('example.tfrecord')
My dataset has now the following shape:
<MapDataset shapes: ((42,), ((22,), (1,))), types: (tf.float32, (tf.float32, tf.float32))>
which I thought is what Model API expects (spoiler: it doesn't).
model.fit(dataset.batch(10))
gives following error:
ValueError: Error when checking input: expected main_input to have 3 dimensions, but got array with shape (None, 42)
Makes sense, I don't have the window here. At the same time it seems like it's not getting correct shape expected by Model(inputs=main_input, outputs=[denoise_output, vad_output]).
How to modify load_dataset so that it matches what's expected by the Model API for the tf.data?
Given that your model has 1 input and 2 outputs, your tf.data.Dataset should have two entries:
1) Input array of shape (window, 42)
2) Tuple of two arrays each of shape (window, 22) and (window, 1)
EDIT: Updated answer - you already return two element tuple
I just noticed that your dataset has these two entries (similar to those described above) and the only thing that differs is the shape.
The only operations you need to perfom is to batch your data twice:
First - to restore the window parameter.
Second - to pass a batch to a model.
window_size = 1
batch_size = 10
dataset = load_dataset('example.tfrecord')
model.fit(dataset.batch(window_size).batch(batch_size)
And that should work.
Below is an old answer, where I wrongfully assumed your dataset shape:
Old Answer, where I assumed you are returning three element tuple:
Assuming that you are starting from three element tuple of shapes (42,), (22,) and (1,), this can be achieved in the same batching operations, enriched with a custom_reshape function to return two-element tuple:
window_size = 1
batch_size = 10
dataset = load_dataset('example.tfrecord')
dataset = dataset.batch(window_size).batch(batch_size)
# Change output format
def custom_reshape(x, y, vad):
return x, (y, vad)
dataset = dataset.map(custom_reshape)
In short, given this dataset shape, you could just call:
model.fit(dataset.batch(window_size).batch(10).map(custom_reshape)
and it should work too.
Best of luck. And sorry again for the fuss.
Currently I can train a LSTM network using one csv file based on this tutorial: https://machinelearningmastery.com/how-to-develop-lstm-models-for-time-series-forecasting/
This code generate sliding windows where the last n_steps of the features are saved to predict the actual target (similar to this: Keras LSTM - feed sequence data with Tensorflow dataset API from the generator):
#%% Import
import pandas as pd
import tensorflow as tf
from tensorflow.python.keras.models import Sequential, model_from_json
from tensorflow.python.keras.layers import LSTM
from tensorflow.python.keras.layers import Dense
# for path
import pathlib
import os
#%% Define functions
# Function to split multivariate input data into samples according to the number of timesteps (n_steps) used for the prediction ("sliding window")
def split_sequences(sequences, n_steps):
X, y = list(), list()
for i in range(len(sequences)):
# find end of this pattern
end_ix = i + n_steps
# check if beyond maximum index of input data
if end_ix > len(sequences):
break
# gather input and output parts of the data in corresponding format (depending on n_steps)
seq_x, seq_y = sequences[i:end_ix, :-1], sequences[end_ix-1, -1]
X.append(seq_x)
y.append(seq_y)
#Append: Adds its argument as a single element to the end of a list. The length of the list increases by one.
return array(X), array(y)
# Set source files
csv_train_path = os.path.join(dir_of_file, 'SimulationData', 'SimulationTrainData', 'SimulationTrainData001.csv')
# Load data
df_train = pd.read_csv(csv_train_path, header=0, parse_dates=[0], index_col=0)
#%% Select features and target
features_targets_considered = ['Fz1', 'Fz2', 'Fz3', 'Fz4', 'Fz5', 'Fz_res']
n_features = len(features_targets_considered)-1 # substract the target
features_targets_train = df_train[features_targets_considered]
# "Convert" to array
train_values = features_targets_train.values
# Set number of previous timesteps, which are considered to predict
n_steps = 100
# Convert into input (400x5) and output (1) values
X, y = split_sequences(train_values, n_steps)
X_test, y_test = split_sequences(test_values, n_steps)
#%% Define model
model = Sequential()
model.add(LSTM(200, activation='relu', return_sequences=True, input_shape=(n_steps, n_features)))
model.add(LSTM(200, activation='relu', return_sequences=True))
model.add(LSTM(200, activation='relu'))
model.add(Dense(1))
model.compile(optimizer='adam', loss='mse', metrics=['mae'])
#%% Fit model
history = model.fit(X, y, epochs=200, verbose=1)
I now want to expand this example to efficiently train the network with different csv files. In the data folder I have the files 'SimulationTrainData001.csv', 'SimulationTrainData002.csv', ..., 'SimulationTrainData300.csv' (about 14 GB).
To achieve this, I tried to adopt the code of this input pipeline example: https://www.tensorflow.org/guide/data#consuming_sets_of_files, which works to a certain extend. I can show the training files in the folder with this change:
# Set source folders
csv_train_path = os.path.join(dir_of_file, 'SimulationData', 'SimulationTrainData')
csv_train_path = pathlib.Path(csv_train_path)
#%% Show five example files from training folder
list_ds = tf.data.Dataset.list_files(str(csv_train_path/'*'))
for f in list_ds.take(5):
print(f.numpy())
One problem is, that in the example the files are pictures of flowers and not time series values and I do not know at which point I can use the split_sequences(sequences, n_steps) function to create the sliding windows to provide the necessary data format to train the LSTM network.
Also, as far as I know, it would be better for the training process, if the generated windows of the different files would be shuffled. I could use the split_sequences(sequences, n_steps) function on every csv file (to generate X_test , y_test) and join the result in one big variable or file and shuffle the windows, but I do not think this is an efficient way and it also had to be redone if n_steps will be changed.
If somebody could suggest a (established) method or example to preprocess my data, I would be very thankful.
You can use the TimeSeriesGenerator after consuming those sets of files.
Here is the reference link.
As per the documentation:
'''
This class takes in a sequence of data-points gathered at equal intervals, along with time-series parameters such as stride, length of history, etc., to produce batches for training/validation.
'''
Provided examples for both univariate & multiple variate scenario
Univariate Example:
from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Dense, LSTM
import numpy as np
import tensorflow as tf
# define dataset
series = np.array([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
# reshape to [10, 1]
n_features = 1
series = series.reshape((len(series), n_features))
# define generator
n_input = 2
generator = TimeseriesGenerator(series, series, length=n_input, batch_size=8)
# create model
model = Sequential()
model.add(LSTM(100, activation='relu', input_shape=(n_input, n_features)))
model.add(Dense(1))
model.compile(optimizer='adam', loss='mse')
# fit model
model.fit_generator(generator, steps_per_epoch=1, epochs=500, verbose=1)
#sample prediction
inputs = np.array([9, 10]).reshape((1, n_input, n_features))
result = model.predict(inputs, verbose=0)
print(result)
Multi-variate Example
from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Dense, LSTM
import numpy as np
import tensorflow as tf
# define dataset
in_seq1 = np.array([10, 20, 30, 40, 50, 60, 70, 80, 90, 100])
in_seq2 = np.array([15, 25, 35, 45, 55, 65, 75, 85, 95, 105])
# reshape series
in_seq1 = in_seq1.reshape((len(in_seq1), 1))
in_seq2 = in_seq2.reshape((len(in_seq2), 1))
# horizontally stack columns
dataset = np.hstack((in_seq1, in_seq2))
# define generator
n_features = dataset.shape[1]
n_input = 2
generator = TimeseriesGenerator(dataset, dataset, length=n_input, batch_size=8)
# define model
model = Sequential()
model.add(LSTM(100, activation='relu', input_shape=(n_input, n_features)))
model.add(Dense(2))
model.compile(optimizer='adam', loss='mse')
# fit model
model.fit_generator(generator, steps_per_epoch=1, epochs=500, verbose=1)
# make a one step prediction out of sample
inputs = np.array([[90, 95], [100, 105]]).reshape((1, n_input, n_features))
result = model.predict(inputs, verbose=1)
print(result)
Note: All of these were simulated using Google Colaboratory
from keras.applications.resnet50 import ResNet50
from keras.preprocessing import image
from keras.applications.resnet50 import preprocess_input, decode_predictions
import numpy as np
model = ResNet50(weights='imagenet')
In this code, there is the "wrapper" (that's what it's referred to) ResNet50. What are the other types of weights I can use for this? I tried looking around but I don't even understand the source code; there is nothing conclusive there either
You can find it on the keras doc
Or github code
There is only two options, either None if you just want the architecture without the weights, or imagenet to load imagenet weights.
Edit : how to use our own weights :
# Take a DenseNET201
backbone = tf.keras.applications.DenseNet201(input_shape=input_shape, weights=None, include_top=False)
# Change the model a little bit, because why not
input_image = tf.keras.layers.Input(shape=input_shape)
x = backcone(input_image)
x = tf.keras.layers.Conv2D(classes, (3, 3), padding='same', name='final_conv')(input)
x = tf.keras.layers.Activation(activation, name=activation)(x)
model = tf.keras.Model(input, x)
#... some additional code
# training part
optimizer = tf.keras.optimizers.Adam(lr=FLAGS.learning_rate)
model.compile(loss=loss,
optimizer=optimizer,
metrics=['accuracy', f1_m, recall_m, precision_m])
callbacks = [tf.keras.callbacks.ModelCheckpoint(filepath=ckpt_name)]
model.fit(train_generator, validation_data=validation_generator, validation_freq=1, epochs=10, callbacks=callbacks)
# using the callback there will weights saved in cktp_name each epoch
# Inference part, just need to reinstance the model (lines after #Change part comment)
model.load_weights(ckpt_name)
results = model.predict(test_generator, verbose=1)
You don't need to change the model obviously, you could have used x = backbone(x) and then model = tf.keras.Model(input, x)
import os
import json
import datetime
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import statsmodels.formula.api as sm
import tflearn
import tensorflow as tf
data = pd.read_csv("line.csv")
data.columns = ['total', 'saved', 'lines' , 'inv']
target = list(data['saved'])
#function filter out the columns we wont be using to train the machine
def preprocess(data, columns_to_ignore):
data = data.drop(columns=columns_to_ignore)
return data
ignore = ['saved' , 'inv']
data = preprocess(data, ignore)
train = [list(l) for l in zip(data['total'], data['lines'])]
# Build neural network
net = tflearn.input_data(shape=[None, 2])
net = tflearn.fully_connected(net, 16)
net = tflearn.fully_connected(net, 16)
net = tflearn.fully_connected(net, 1, activation='softmax')
net = tflearn.regression(net)
# Training Neural Network
model = tflearn.DNN(net)
# Start Training using tensorflow gradient descent algorithim
model = model.fit(train, target, n_epoch=10, batch_size=10, show_metric=True)
I keep running into this error. I thought the shape should be: None , 2 since there are 2 features in the program. The csv file has 4 features. One of them gets filtered out. One is read as the target. What should I do to get rid of this error?
ValueError: Cannot feed value of shape (10,) for Tensor 'TargetsData/Y:0', which has shape '(?, 1)'
If I change the labels from 1-D to 2-D I don't see that error.
target = list(data['y'])
a = np.array(target)
target = np.reshape(a , (-1,1))