Hey folks, cross posting my question from here: keras - Floating point exception when creating a TensorFlow TimeDistributed layer - Stack Overflow
I have so far been unable to resolve this bug. I am running my code and getting floating point exception with no stack trace. I tried to debug and step through my code and it dies after going through the call function twice. Here is the full code:
import os
import sys
from typing import Counter
import tensorflow as tf
import numpy as np
from tensorflow.keras import models, layers, callbacks
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.datasets import mnist
from matplotlib import pyplot as plt
# Change this to the location of the database directories
DB_DIR = os.path.dirname(os.path.realpath(__file__))
# Import databases
sys.path.insert(1, DB_DIR)
from db_utils import get_imdb_dataset, get_speech_dataset, get_single_digit_dataset
def Secure_Voice_Channel(func):
"""Define Secure_Voice_Channel decorator."""
def execute_func(*args, **kwargs):
print('Established Secure Connection.')
returned_value = func(*args, **kwargs)
print("Ended Secure Connection.")
return returned_value
return execute_func
@Secure_Voice_Channel
class generic_vns_function(tf.keras.Model):
def __init__(self, input_shape, layers, layer_units):
super().__init__()
self.convolutions = []
# Dynamically create Convolutional layers and MaxPools
for layer in range(len(layers)):
self.convolutions.append(tf.keras.layers.Conv2D(layer, 3, padding="same", input_shape=input_shape, activation="relu"))
# Add MaxPooling layer
self.convolutions.append(tf.keras.layers.MaxPooling2D((2,2)))
# Flatten
self.flatten = tf.keras.layers.Flatten()
# Dense layer
self.dense1 = tf.keras.layers.Dense(1024, activation="relu")
def call(self, input):
x = input
for layer in self.convolutions:
x = layer(x)
x = self.flatten(x)
x = self.dense1(x)
return x
def train_model(model, epochs, batch_size, X_train, y_train, X_test, y_test):
"""Generic Deep Learning Model training function."""
cb = [callbacks.EarlyStopping(monitor='val_loss', patience=3)]
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=epochs,
batch_size=batch_size, verbose=1, callbacks=cb)
scores = model.evaluate(X_test, y_test, verbose=2)
print("Baseline Error: %.2f%%" % (100-scores[1]*100))
return model
def choose_dataset(dataset_type):
"""Select dataset based on string variable."""
if dataset_type == "nlp":
return get_imdb_dataset(dir=DB_DIR)
elif dataset_type == "computer_vision":
(X_train, y_train), (X_test, y_test) = mnist.load_data()
elif dataset_type == "speech_recognition":
# (X_train, y_train), (X_test, y_test), (_, _) = get_speech_dataset()
(X_train, y_train), (X_test, y_test), (_, _) = get_single_digit_dataset(0)
else:
raise ValueError("Couldn't find dataset.")
(X_train, X_test) = normalize_dataset(dataset_type, X_train, X_test)
(X_train, y_train), (X_test, y_test) = reshape_dataset(X_train, y_train, X_test, y_test)
return (X_train, y_train), (X_test, y_test)
def normalize_dataset(string, X_train, X_test):
"""Normalize speech recognition and computer vision datasets."""
if string == "computer vision":
X_train = X_train / 255
X_test = X_test / 255
else:
mean = np.mean(X_train)
std = np.std(X_train)
X_train = (X_train-std)/mean
X_test = (X_test-std)/mean
return (X_train, X_test)
def reshape_dataset(X_train, y_train, X_test, y_test):
"""Reshape Computer Vision and Speech datasets."""
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)
return (X_train, y_train), (X_test, y_test)
def create_LSTM(cnn_model, input_shape, num_classes):
input_layer = layers.Input(shape=input_shape)
distributed_cnn = tf.keras.layers.TimeDistributed(cnn_model)(input_layer)
x, state_a, state_b = layers.LSTM(distributed_cnn)
output = layers.Dense(num_classes, activation="softmax")(x)
model = models.Model(inputs=input_layer, outputs=output)
opt = Adam()
model.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy'])
return model
def main():
# Hyperparameters
layers = [64, 32]
layer_units = 1000
epochs = 10
batch_size = 200
lr = 0.001
filter = 64
kernal_size = 3
window = 3
dataset = "speech_recognition"
# Import Datasets
(X_train, y_train), (X_test, y_test) = choose_dataset(dataset)
num_classes = y_train.shape[1]
# Reshape both the train and test dataset
X_train = X_train.reshape(X_train.shape[0], window, int(X_train.shape[1]/window), X_train.shape[2], 1)
X_test = X_test.reshape(X_test.shape[0], window, int(X_test.shape[1]/window), X_test.shape[2], 1)
# Generate CNN model
cnn_model = generic_vns_function(X_train.shape[1:], layers, layer_units)
print("Created generic CNN model")
# Create the LSTM CNN with time distributed layer
model = create_LSTM(cnn_model, X_train.shape[1:], num_classes)
print("Created LST model")
trained_model = train_model(model, epochs, batch_size, X_train, y_train, X_test, y_test)
save_format="tf"
# # Save model to h5 file
trained_model.save(save_format, 'models/model_%s_a3.h5' % dataset)
return None
The error occurs after looping through the call function twice while creating the distributed_cnn = tf.keras.layers.TimeDistributed(cnn_model)(input_layer) . Any ideas as to why? This is baffling to me.