LSTM Model and FGSM Attack Implementation in TensorFlow: Shape Mismatch Errors #20092
Description
I'm working on a project to implement an FGSM (Fast Gradient Sign Method) attack on an LSTM model for stock price prediction using TensorFlow and Keras. Despite my efforts, I'm encountering persistent issues with tensor shape mismatches, and I'm hoping to get some advice from this community.
I’ve created an LSTM model to predict stock prices and tried generating adversarial examples using the FGSM method. The training seems to proceed without issues, but when I attempt to generate adversarial examples and evaluate the model with this data, I encounter the following error:
Exception encountered when calling Sequential.call().
Cannot take the length of shape with unknown rank.
Arguments received by Sequential.call():
• inputs=tf.Tensor(shape=, dtype=float32)
• training=False
• mask=None
ValueError: Cannot take the length of shape with unknown rank.
During handling of the above exception, another exception occurred:
test_predictions = model.predict(adversarial_test_data)
ValueError: Exception encountered when calling Sequential.call().
Here’s a summary of the relevant sections of my code:
import numpy as np
import pandas as pd
import os
import tensorflow as tf
from keras.models import load_model
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense, LSTM, Dropout, Input
def fgsm(input_data, model, loss, epsilon=0.01):
"""
Generate adversarial examples using FGSM.
:param input_data: Input data to be perturbed
:param model: Trained model
:param epsilon: Perturbation size
"""
input_data = tf.convert_to_tensor(input_data, dtype=tf.float32)
loss = tf.convert_to_tensor(loss, dtype=tf.float32)
with tf.GradientTape() as tape:
tape.watch(input_data)
prediction = model(input_data)
loss = tf.keras.losses.MeanSquaredError()(loss, prediction)
gradient = tape.gradient(loss, input_data)
adversarial_example = input_data + epsilon * tf.sign(gradient)
return adversarial_example.numpy()
## Read each stock datasets as dataframe ##
rootpath = os.path.dirname(__file__)
print (rootpath)
folderpath = os.path.join(rootpath, './Stocks')
for file_name in os.listdir(folderpath):
if file_name.endswith('.csv'):
df = pd.read_csv(os.path.join(folderpath,file_name),delimiter=',',usecols=['Date','Open','High','Low','Close','Adj Close','Volume'])
basename, ext = os.path.splitext(file_name)
df['Date'] = pd.to_datetime(df['Date']) ## Convert 'Date' column to datetime format
print ('file:', file_name)
data = df.filter(['Close'])
# Convert the dataframe to a numpy array
dataset = data.values
# Get the number of rows to train the model on
training_data_len = int(np.ceil(len(dataset)* 0.8))
scaler = MinMaxScaler(feature_range=(0,1))
scale_data = scaler.fit_transform(dataset)
## Create the scaled training data set ##
train_data = scale_data[0:int(training_data_len), :]
## Split the data into train data and test data sets ##
x_train = []
y_train = []
for i in range(50, len(train_data)):
x_train.append(train_data[i-50:i, 0])
y_train.append(train_data[i,0])
if i < 50:
print(x_train)
print(y_train)
print()
## Convert the x_data and y_data to numpy arrays ##
x_train, y_train = np.array(x_train), np.array(y_train)
## Reshape the data
x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))
y_train = np.reshape(y_train, (y_train.shape[0], 1))
## Build the LSTM model ##
model = Sequential()
#model.add(LSTM(128, return_sequences=True, input_shape=(x_train.shape[1],1)))
model.add(Input(shape=(x_train.shape[1], 1)))
model.add(LSTM(128, return_sequences=True))
model.add(LSTM(64, return_sequences=False))
model.add(Dropout(0.2))
model.add(Dense(25))
model.add(Dense(1))
## Compile the model ##
model.compile(optimizer='adam', loss='mean_squared_error')
## Train the model ##
model.fit(x_train, y_train, batch_size=32, epochs=1,validation_split=0.2)
## Create the testing dataset ##
test_data = scale_data[training_data_len - 50: , :]
## Create the datasets x_test
x_test = []
y_test = dataset[training_data_len: , :]
for i in range (50, len(test_data)):
x_test.append(test_data[i-50:i, 0])
x_test = np.array(x_test)
y_test = np.array(y_test)
## Reshape the data ##
x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1],1))
y_test = np.reshape(y_test, (y_test.shape[0], 1))
## Generate adversarial examples for the training data ##
adversarial_train_data = fgsm(x_train, model, y_train, epsilon=0.01)
#Generate adversarial examples for the test data
adversarial_test_data = fgsm(x_test, model, y_test, epsilon=0.01)
# Ensure that the adversarial data has the correct shape
adversarial_train_data = np.reshape(adversarial_train_data, (adversarial_train_data.shape[0], adversarial_train_data.shape[1], 1))
adversarial_test_data = np.reshape(adversarial_test_data, (adversarial_test_data.shape[0], adversarial_test_data.shape[1], 1))
## Save adversarial examples to CSV files
adversarial_train_data = pd.DataFrame(adversarial_train_data.reshape(adversarial_train_data.shape[0], -1))
adversarial_train_data.to_csv('adversarial_train_data.csv', index=False)
## Evaluate the model with adversarial training data
train_predictions = model.predict(adversarial_train_data)
train_rmse = np.sqrt(np.mean((train_predictions - y_train) ** 2))
print (f'Training RMSE with adversarial examples: {train_rmse}')
## Evaluate the model with adversarial test data
test_predictions = model.predict(adversarial_test_data)
test_rmse = np.sqrt(np.mean((test_predictions - y_test) ** 2))
print (f'Test RMSE with adversarial examples: {test_rmse}')
How to properly handle tensor shapes in TensorFlow/Keras to avoid shape mismatch errors.
Any insights into why the Sequential.call() method might be encountering an unknown rank shape error.
Any help or pointers would be greatly appreciated. Thank you in advance!