Sequence-to-sequence classification with variable sequence lengths in Keras - python

I would like to train an LSTM or GRU network in TensorFlow/Keras to continuously recognize whether a user is walking or not based on input from motion sensors (accelerometer and gyroscope). I have 50 input sequences with lengths varying from 581 to 5629 time steps and 6 features and 50 corresponding output sequences of boolean values. My problem is that I don't know how to feed the training data to the fit() method.
I know approximately what I need to do: I'd like to train with 5 batches of 10 sequences each, and for each batch I have to pad all but the longest sequence so all 10 sequences have the same lengths and apply masking. I just don't know how to build the data structures. I know that I can make one big 3D tensor of size (50,5629,6) and that works, but it's painfully slow, so I'd really like to make the sequence length of each batch as small as possible.
Here's the problem in code:
import tensorflow as tf
import numpy as np
# Load data from file
x_list, y_list = loadSequences("train.csv")
# x_list is now a list of arrays (n,6) of float64, where n is the timesteps
# and 6 is the number of features, sorted by increasing sequence lengths.
# y_list is a list of arrays (n,1) of Boolean.
x_train = # WHAT DO I WRITE HERE?
y_train = # AND HERE?
model = tf.keras.models.Sequential([
tf.keras.layers.Masking(),
tf.keras.layers.LSTM(32, return_sequences=True),
tf.keras.layers.Dense(2, activation=tf.nn.softmax)
])
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.fit(x_train, y_train, batch_size=10, epochs=100)

You can do some thing like this
use generator function take a look at this link fit_generator look for fit_generator method.
def data_generater(batch_size):
print("reading data")
training_file = 'data_location', 'r')
# assuming data is in json format so feels free to change accordingly
training_set = json.loads(training_file.read())
training_file.close()
batch_i = 0 # Counter inside the current batch vector
batch_x = [] # The current batch's x data
batch_y = [] # The current batch's y data
while True:
for obj in training_set:
batch_x.append(your input sequences one by one)
if obj['val'] == True:
batch_y.append([1])
elif obj['val'] == False:
batch_y.append([0])
batch_i += 1
if batch_i == batch_size:
# Ready to yield the batch
# pad input to max length in the batch
batch_x = pad_txt_data(batch_x)
yield batch_x, np.array(batch_y)
batch_x = []
batch_y = []
batch_i = 0
def pad_txt_data(arr):
# expecting arr to be in the shape of (10, m, 6)
paded_arr = []
prefered_len = len(max(arr, key=len))
# Now pad all your sequences to preferred length in the batch(arr)
return np.array(paded_arr)
and in the model
model = keras.Sequential()
model.add(keras.layers.Masking(mask_value=0., input_shape=(None,6)))
model.add(keras.layers.LSTM(32))
model.add(keras.layers.Dense(1, activation="softmax"))
model.compile(optimizer="Adam", loss='categorical_crossentropy', metrics=['categorical_accuracy'])
model.fit_generator(data_generater(10), steps_per_epoch=5, epochs=10)
Batch_size, steps_per_epoch, epoch can be different.
Generally
steps_per_epoch = (number of sequences/batch_size)
Note: Form reading your description your task appears to be Binary classification problem not like an Sequence to sequence problem. A good example for sequence to sequence is a language translation. Just google around you will find what i mean.
And if you really want to see the difference in training times I suggest using a GPU if available and CuDNNLSTM.

In case it helps someone, here's how I ended up implementing a solution:
import tensorflow as tf
import numpy as np
# Load data from file
x_list, y_list = loadSequences("train.csv")
# x_list is now a list of arrays (m,n) of float64, where m is the timesteps
# and n is the number of features.
# y_list is a list of arrays (m,1) of Boolean.
assert len(x_list) == len(y_list)
num_sequences = len(x_list)
num_features = len(x_list[0][0])
batch_size = 10
batches_per_epoch = 5
assert batch_size * batches_per_epoch == num_sequences
def train_generator():
# Sort by length so the number of timesteps in each batch is minimized
x_list.sort(key=len)
y_list.sort(key=len)
# Generate batches
while True:
for b in range(batches_per_epoch):
longest_index = (b + 1) * batch_size - 1
timesteps = len(x_list[longest_index])
x_train = np.zeros((batch_size, timesteps, num_features))
y_train = np.zeros((batch_size, timesteps, 1))
for i in range(batch_size):
li = b * batch_size + i
x_train[i, 0:len(x_list[li]), :] = x_list[li]
y_train[i, 0:len(y_list[li]), 0] = y_list[li]
yield x_train, y_train
model = tf.keras.models.Sequential([
tf.keras.layers.Masking(mask_value=0., input_shape=(None,num_features)),
tf.keras.layers.LSTM(32, return_sequences=True),
tf.keras.layers.Dense(2, activation=tf.nn.softmax)
])
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.fit_generator(train_generator(), steps_per_epoch=batches_per_epoch, epochs=100)

Related

Tensorflow Data cardinality is ambigous with multiple inputs

I have a model with two inputs for text classification with additional input 'subject' of text. One of my inputs is for text - it gets vectorized by a vectorization layer. The other is 'subject' as int. These are concatenated later. In my code below, x_train_text is simply a list of texts. x_train_subject is a list of integers. These two and y_train_int has same sizes. However, even though the sizes are the same(4499), I get the following error:
ValueError: Data cardinality is ambiguous:
x sizes: 2
y sizes: 4499
Make sure all arrays contain the same number of samples.
CODE:
MAX_TOKENS_NUM = 5000 # Maximum vocab size.
MAX_SEQUENCE_LEN = 40 # Sequence length to pad the outputs to.
EMBEDDING_DIMS = 100
text_input = tf.keras.Input(shape=(1,), dtype=tf.string)
subject_input = tf.keras.Input(shape=(1,), dtype=tf.int32)
text_layer = vectorize_layer(text_input)
text_layer = tf.keras.layers.Embedding(MAX_TOKENS_NUM + 1, EMBEDDING_DIMS)(text_layer)
text_layer = tf.keras.layers.GlobalAveragePooling1D()(text_layer)
subject_layer = tf.keras.layers.CategoryEncoding(
num_tokens=len(subjects), output_mode='one_hot', sparse=False
)(subject_input)
concatenated = tf.keras.layers.Concatenate(axis=1)([text_layer, subject_layer])
output = tf.keras.layers.Dense(len(labels))(concatenated)
model = tf.keras.models.Model(inputs=[text_input, subject_input], outputs=output)
model.summary()
model.compile(loss=losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer='adam',
metrics=tf.metrics.SparseCategoricalAccuracy())
FIT FUNCTION :
epochs = 100
history = model.fit(
[x_train_text,x_train_subject],
y=y_train_int,
epochs=epochs)
What could be the solution?
When I changed the fit function to receive inputs as Pandas.DataFrame.values as below it works.
FIT FUNCTION :
epochs = 100
history = model.fit(
[pd.DataFrame(x_train_text).values,pd.DataFrame(x_train_subject).values],
y=pd.DataFrame(y_train_int).values,
epochs=epochs)

What this error means: `y` argument is not supported when using python generator as input

I try to develop a network, and use python generator as data provider. Everything looks OK until the model starts to fit, then I receive this error:
ValueError: `y` argument is not supported when using dataset as input.
I proofed every line and, I think the problem is in the format of x_test and y_test feed to the network. After hours of googling, and changing the format several times, the error is still there.
Can you help me to fix it? You can find the whole code below:
import os
import numpy as np
import pandas as pd
import re # To match regular expression for extracting labels
import tensorflow as tf
print(tf.__version__)
def xfiles(filename):
if re.match('^\w{12}_x\.csv$', filename) is None:
return False
else:
return True
def data_generator():
folder = "i:/Stockpred/csvdbase/datasets/DS0002"
file_list = os.listdir(folder)
x_files = list(filter(xfiles, file_list))
x_files.sort()
np.random.seed(1729)
np.random.shuffle(x_files)
for file in x_files:
filespec = folder + '/' + file
xs = pd.read_csv(filespec, header=None)
yfile = file.replace('_x', '_y')
yfilespec = folder + '/' + yfile
ys = pd.read_csv(open(yfilespec, 'r'), header=None, usecols=[1])
xs = np.asarray(xs, dtype=np.float32)
ys = np.asarray(ys, dtype=np.float32)
for i in range(xs.shape[0]):
yield xs[i][1:169], ys[i][0]
dataset = tf.data.Dataset.from_generator(
data_generator,
(tf.float32, tf.float32),
(tf.TensorShape([168, ]), tf.TensorShape([])))
dataset = dataset.shuffle(buffer_size=16000, seed=1729)
# dataset = dataset.batch(4000, drop_remainder=True)
dataset = dataset.cache('R:/Temp/model')
def is_test(i, d):
return i % 4 == 0
def is_train(i, d):
return not is_test(i, d)
recover = lambda i, d: d
test_dataset = dataset.enumerate().filter(is_test).map(recover)
train_dataset = dataset.enumerate().filter(is_train).map(recover)
x_test = test_dataset.map(lambda x, y: x)
y_test = test_dataset.map(lambda x, y: y)
x_train = train_dataset.map(lambda x, y: x)
y_train = train_dataset.map(lambda x, y: y)
print(x_train.element_spec)
print(y_train.element_spec)
print(x_test.element_spec)
print(y_test.element_spec)
# define an object (initializing RNN)
model = tf.keras.models.Sequential()
# first LSTM layer
model.add(tf.keras.layers.LSTM(units=168, activation='relu', return_sequences=True, input_shape=(168, 1)))
# dropout layer
model.add(tf.keras.layers.Dropout(0.2))
# second LSTM layer
model.add(tf.keras.layers.LSTM(units=168, activation='relu', return_sequences=True))
# dropout layer
model.add(tf.keras.layers.Dropout(0.2))
# third LSTM layer
model.add(tf.keras.layers.LSTM(units=80, activation='relu', return_sequences=True))
# dropout layer
model.add(tf.keras.layers.Dropout(0.2))
# fourth LSTM layer
model.add(tf.keras.layers.LSTM(units=120, activation='relu'))
# dropout layer
model.add(tf.keras.layers.Dropout(0.2))
# output layer
model.add(tf.keras.layers.Dense(units=1))
model.summary()
# compile the model
model.compile(optimizer='adam', loss='mean_squared_error')
model.fit(x_train.as_numpy_iterator(), y_train.as_numpy_iterator(), batch_size=32, epochs=100)
predicted_stock_price = model.predict(x_test)
everything looks OK until the model starts to fit. and i reciev this error:
ValueError: `y` argument is not supported when using dataset as input.
Can you help to fix it?
As the docs say:
y - Target data. Like the input data x, it could be either Numpy array(s) or TensorFlow tensor(s). It should be consistent with x (you cannot have Numpy inputs and tensor targets, or inversely). If x is a dataset, generator, or keras.utils.Sequence instance, y should not be specified (since targets will be obtained from x).
So, I suppose you should have one generator serving tuples of sample and label.
If you are providing Dataset as input, then
type(train_dataset) should be tensorflow.python.data.ops.dataset_ops.BatchDataset
if so, simply feed this Dataset (which includes your X and y bundle) into the model,
model.fit(train_dataset, batch_size=32, epochs=100)
(Yes, this is a little different convention than how we did in sklearn - X and y separately.)
meanwhile, if you want tensorflow to explicitly use a separate dataset for validation, you must use the kwarg like:
model.fit(train_dataset, validation_data=val_dataset, batch_size=32, epochs=100)
where val_dataset is a separate dataset you had spared for validation during model training. (Not test).
use model.fit_generator, and use tuples (x,y) of input data and labels. So altogether:
model.fit_generator(train_dataset.as_numpy_iterator(),epochs=100)

Tensorflow 2 LSTM model doesn't learn using a Sequence

I'm currently using a LSTM model to make timeserie predictions with Tensorflow 2.2.0
I've been using a large dataset and everything works nicely.
However, the dataset creation takes a lot of RAM and I wanted to use a tensorflow.keras.utils.Sequence to solve the issue, my problem is the following:
When using a Sequence, my model doesn't learn anymore (it predicts the average of the real signal over the whole dataset)
My dataset is created from two python lists x_train_flights and y_train_flights, each containing pandas DataFrames. For each (x_train_flight, y_train_flight) of this list:
x_train_flight of shape (-1, features) containing features signals
y_train_flight of shape (-1, 1) containing one signal being aligned in time with the ones from x_train_flights
The system looks like as follow (I am not allowed to share the real data, I've recreated the graph using pseudo-random signals instead):
Here, features=2 (the blue and orange lines), and look_back=5. That is to say, the 10 points (from x_train_flights) in the rectangle are used to predict the golden point (which is compared to the corresponding point in y_train_flights during the training phase). The gray points are previous predictions.
To create my dataset, I've been using these functions:
def lstm_shapify(sequence, look_back, features):
res = np.empty((look_back, len(sequence), features), dtype=np.float32)
for i in range(look_back):
res[i] = np.roll(sequence, -i * features)
return np.transpose(res, axes=(1, 0, 2))[:-look_back + 1]
def make_dataset(x_flights, y_flights, look_back, features):
x = np.empty((0, look_back, features), dtype=np.float32)
y = np.empty((0, 1), dtype=np.float32)
for i in range(len(x_flights)):
x_sample = x_flights[i].values
y_sample = y_flights[i].values[look_back - 1:]
x = np.concatenate([x, lstm_shapify(x_sample, look_back, features)])
y = np.concatenate([y, y_sample])
return x, y
And I fit my network with the following:
model.fit(
x_train,
y_train,
epochs=7,
batch_size=batch_size
)
So, I've created this custom Sequence:
class LSTMGenerator(Sequence):
def __init__(
self,
x_flights: List[DataFrame],
y_flights: List[DataFrame],
look_back: int,
batch_size: int,
features: int
):
self.x_flights = x_flights
self.y_flights = []
self.look_back = look_back
self.batch_size = batch_size
self.features = features
self.length = 0
for y_flight in y_flights:
y = y_flight.iloc[look_back - 1:].to_numpy()
self.y_flights.append(y)
self.length += len(y) // batch_size
def __getitem__(self, index):
flight_index = 0
while True:
n = len(self.y_flights[flight_index]) // self.batch_size
if index < n:
break
flight_index += 1
index = index - n
start_index = index * self.batch_size
x_batch = lstm_shapify(
self.x_flights[flight_index]
.iloc[start_index:start_index + self.batch_size + self.look_back - 1]
.to_numpy(),
self.look_back,
self.features
)
y_batch = self.y_flights[flight_index][start_index:start_index + self.batch_size]
return x_batch, y_batch
def __len__(self):
return self.length
Each tuple (x, y) it returns are two numpy arrays of shape (batch_size, look_back, features) and (batch_size, 1) respectively.
And now I'm trying to fit it with:
model.fit(
LSTMGenerator(x_train_flights, y_train_flights, look_back, batch_size, features),
epochs=epochs
)
Here is my model:
model = Sequential()
model.add(LSTM(
100,
input_shape=(look_back, features),
kernel_regularizer=regularizers.l2(1e-3),
bias_regularizer=regularizers.l2(1e-4)
))
model.add(Dropout(0.2))
model.add(BatchNormalization())
model.add(Dense(1, activation='tanh'))
model.compile(optimizer='adam', loss='mse')
Hope you can help me
EDIT: more details about the datasets
I solved it by taking a break and looking at the code once again (and I realized it was a silly mistake): the issue of my Sequence comes from the samples in each batch being consecutive samples in time, whereas my compute-everything-dataset's batches where nicely shuffled.
My Sequence was problematic because the batches were selected at a random index from a random dataset. Now I select each sample at a random index from a random dataset to create a single batch.
Here is a working example:
from tensorflow.keras import *
from tensorflow.keras.layers import *
from tensorflow.keras.utils import *
import numpy as np
import tensorflow as tf
np.random.seed(1234)
tf.random.set_seed(1234)
features = 3
lookback = 7
model = Sequential()
model.add(LSTM(500, input_shape = (lookback, features)))
model.add(Dense(1, activation='tanh'))
XS = np.random.randn(200, features)
YS = np.random.randn(200)
class LookbackSeq(Sequence):
def __init__(self, XS, YS, batch_size, lookback):
self.XS = XS
self.YS = YS
self.batch_size = batch_size
self.lookback = lookback
def __len__(self):
n_windows = self.XS.shape[0] - self.lookback
return int(np.ceil(n_windows / self.batch_size))
def __getitem__(self, i):
base = i * self.batch_size
n_windows = self.XS.shape[0] - self.lookback
batch_size = min(n_windows - base, self.batch_size)
X = np.zeros((batch_size, self.lookback, self.XS.shape[1]))
Y = np.zeros((batch_size, 1))
for i in range(batch_size):
for j in range(self.lookback):
X[i, j] = self.XS[base + i + j]
Y[i] = self.YS[base + i + self.lookback]
return X, Y
model.compile(optimizer='adam', loss='mse')
# ALL SAMPLES IN MEMORY
X, Y = [], []
for i in range(len(XS) - lookback):
X.append(XS[i:i+lookback])
Y.append(YS[i+lookback])
X, Y = np.array(X), np.array(Y)
model.fit(X, Y, epochs = 10, batch_size = 4, shuffle = False)
# GENERATED ON THE FLY
# gen = LookbackSeq(XS, YS, 4, lookback)
# model.fit(x = gen,
# steps_per_epoch = len(gen),
# shuffle = False,
# epochs = 10)
I'm assuming your input data has the shape X = (n_points, n_features) and Y = (n_points,). LookbackSeq does the batching and windowing (lookback) for you.
You can comment and uncomment the relevant lines to either train with samples generated on the fly or with them all stored in memory. You should get identical results.

Accuracy not growing across epochs on keras

I'm new to machine learning and deep learning and I'm trying to classify texts from 5 categories using neural networks. For that, I made a dictionary in order to translate the words to indexes, finally getting an array with lists of indexes. Moreover I change the labels to integers. I also did the padding and that stuff. The problem is that when I fit the model the accuracy keeps quite low (~0.20) and does not change across the epochs. I have tried to change a lot of params, like the size of the vocabulary, number of neurones, dropout probability, optimizer parameter, etc. The key parts of the code are below.
# Arrays with indexes (that works fine)
X_train = tokens_to_indexes(tokenized_tr_mrp, vocab, return_vocab=False)
X_test, vocab_dict = tokens_to_indexes(tokenized_te_mrp, vocab)
# Labels to integers
labels_dict = {}
labels_dict['Alzheimer'] = 0
labels_dict['Bladder Cancer'] = 1
labels_dict['Breast Cancer'] = 2
labels_dict['Cervical Cancer'] = 3
labels_dict['Negative'] = 4
y_train = np.array([labels_dict[i] for i in y_tr])
y_test = np.array([labels_dict[i] for i in y_te])
# One-hot encoding of labels
from keras.utils import to_categorical
encoded_train = to_categorical(y_train)
encoded_test = to_categorical(y_test)
# Padding
max_review_length = 235
X_train_pad = sequence.pad_sequences(X_train, maxlen=max_review_length)
X_test_pad = sequence.pad_sequences(X_test, maxlen=max_review_length)
# Model
# Vocab size
top_words = len(list(vocab_dict.keys()))
# Neurone type
rnn = LSTM
# dropout
set_dropout = True
p = 0.2
# embedding size
embedding_vector_length = 64
# regularization strength
L = 0.0005
# Number of neurones
N = 50
# Model
model = Sequential()
# Embedding layer
model.add(Embedding(top_words,
embedding_vector_length,
embeddings_regularizer=regularizers.l1(l=L),
input_length=max_review_length
#,embeddings_constraint=UnitNorm(axis=1)
))
# Dropout layer
if set_dropout:
model.add(Dropout(p))
# Recurrent layer
model.add(rnn(N))
# Output layer
model.add(Dense(5, activation='softmax'))
# Compilation
model.compile(loss='categorical_crossentropy',
optimizer=Adam(lr=0.001),
metrics=['Accuracy'])
# Split training set for validation
X_tr, X_va, y_tr_, y_va = train_test_split(X_train_pad, encoded_train,
test_size=0.3, random_state=2)
# Parameters
batch_size = 50
# N epochs
n_epocas = 20
best_val_acc = 0
best_val_loss = 1e20
best_i = 0
best_weights = []
acum_tr_acc = []
acum_tr_loss = []
acum_val_acc = []
acum_val_loss = []
# Training
for e in range(n_epocas):
h = model.fit(X_tr, y_tr_,
batch_size=batch_size,
validation_data=(X_va, y_va),
epochs=1, verbose=1)
acum_tr_acc = acum_tr_acc + h.history['accuracy']
acum_tr_loss = acum_tr_loss + h.history['loss']
val_acc = h.history['val_accuracy'][0]
val_loss = h.history['val_loss'][0]
acum_val_acc = acum_val_acc + [val_acc]
acum_val_loss = acum_val_loss + [val_loss]
# if val_acc > best_val_acc:
if val_loss < best_val_loss:
best_i = len(acum_val_acc)-1
best_val_acc = val_acc
best_val_loss = val_loss
best_weights = model.get_weights().copy()
if len(acum_tr_acc)>1 and (len(acum_tr_acc)+1) % 1 == 0:
if e>1:
clear_output()
The code you posted is really bad practice.
You can either train for n_epocas using your current method and add callbacks to get the best weights (ex ModelCheckpoint) or use tf.GradientTape but using model.fit() for one epoch at a time can lead to weird results, since your optimizer doesn't know which epoch it is at.
I suggest keeping your current code but training for n_epocas all in one go and report the results here (accuracy + loss).
Someone gave me the solution. I just had to change this line:
model.compile(loss='categorical_crossentropy',
optimizer=Adam(lr=0.001),
metrics=['Accuracy'])
For this:
model.compile(loss='categorical_crossentropy',
optimizer=Adam(lr=0.001),
metrics=['acc'])
I also changed the lines in the final loop relating to accuracy. The one-hot encoding was necessary as well.

Dataset.from_generator cannot replicate functionality of numpy arrays as input to 1D Convnet

I am feeding many time series of length 100 and 3 features into a 1D Convnet. I have too many of these to use numpy arrays, therefore I need to use Dataset.from_generator().
The problem is that when I train the model on the dataset, it gives the error:
expected conv1d_input to have 3 dimensions, but got array with shape (100, 3)
The code below demonstrates the problem. The generator produces each element as an expected (100,3) array. Why does the model not recognise the generator output as valid?
Many thanks for any help. Julian
import numpy as np
import tensorflow as tf
def create_timeseries_element():
# returns a random time series of 100 intervals, each with 3 features,
# and a random one-hot array of 5 entries
data = np.random.rand(100,3)
label = np.eye(5, dtype='int')[np.random.choice(5)]
return data, label
def data_generator():
d, l = create_timeseries_element()
yield (d, l)
model = tf.keras.models.Sequential([
tf.keras.layers.Conv1D(128, 9, activation='relu', input_shape=(100, 3)),
tf.keras.layers.Conv1D(128, 9, activation='relu'),
tf.keras.layers.MaxPooling1D(2),
tf.keras.layers.Conv1D(256, 5, activation='relu'),
tf.keras.layers.Conv1D(256, 5, activation='relu'),
tf.keras.layers.GlobalAveragePooling1D(),
tf.keras.layers.Dropout(0.5),
tf.keras.layers.Dense(5, activation='softmax')])
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
x_train = []
y_train = []
for _ in range(1000):
d, l = create_timeseries_element()
x_train.append(d)
y_train.append(l)
x_train = np.array(x_train)
y_train = np.array(y_train)
# train model with numpy arrays - this works
model.fit(x=x_train, y=y_train)
ds = tf.data.Dataset.from_generator(data_generator, output_types=(tf.float32, tf.int32),
output_shapes=(tf.TensorShape([100, 3]), tf.TensorShape([5])))
# train model with dataset - this fails
model.fit(ds)
Model expects a batch/list of samples. You can do that by simply setting batch property while creating your dataset as follows:
ds = tf.data.Dataset.from_generator(data_generator, output_types=(tf.float32, tf.int32),
output_shapes=(tf.TensorShape([100, 3]), tf.TensorShape([5])))
ds = ds.batch(16)
You can also do that another way when you prepare sample. In this way, You need to expand the sample dimension so that a sample acts as a batch (you can pass a list of samples too) and you have to do the following modifications in your output_shapes of dataset and create_timeseries_element function
def create_timeseries_element():
# returns a random time series of 100 intervals, each with 3 features,
# and a random one-hot array of 5 entries
# Expand dimensions to create a batch of single sample
data = np.expand_dims(np.random.rand(100, 3), axis=0)
label = np.expand_dims(np.eye(5, dtype='int')[np.random.choice(5)], axis=0)
return data, label
ds = tf.data.Dataset.from_generator(data_generator, output_types=(tf.float32, tf.int32), output_shapes=(tf.TensorShape([None, 100, 3]), tf.TensorShape([None, 5])))
The above changes will supply only a single batch (sample for first solution) for each epochs of your dataset. You can generate as much batches (samples for first solution) you want (e.g. 25) by passing a parameter to data_generator function while you define your dataset like follows:
def data_generator(count=1):
for _ in range(count):
d, l = create_timeseries_element()
yield (d, l)
ds = tf.data.Dataset.from_generator(data_generator, args=[25], output_types=(tf.float32, tf.int32), output_shapes=(tf.TensorShape([None, 100, 3]), tf.TensorShape([None, 5])))

Categories