Lab 3 RNN implementation.ipynb

Kernel: Python 3 (ipykernel)

Implement the MNIST fashion dataset using a Recurrent Neural Network (RNN) in R,

you can follow these steps:

• Load the MNIST fashion dataset: The MNIST fashion dataset can be easily accessed through Keras in R.

• Preprocess the data: Preprocess the data by normalizing it and reshaping it if needed.

• Build the RNN model: Construct a recurrent neural network model using packages like TensorFlow or Keras.

• Compile the model: Compile the model with appropriate loss function, optimizer, and metrics.

• Train the model: Fit the model on the training data.

• Evaluate the model: Evaluate the performance of the model on the test data

import tensorflow as tf
from tensorflow.keras.datasets import fashion_mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM, Dense, Embedding
from tensorflow.keras.utils import to_categorical

# Load MNIST fashion dataset
(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()

# Preprocess the data
x_train = x_train / 255.0
x_test = x_test / 255.0
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)

# Define RNN model
model = Sequential([
    Embedding(input_dim=784, output_dim=128),
    LSTM(units=128),
    Dense(units=10, activation='softmax')
])

# Compile the model
model.compile(
    loss='categorical_crossentropy',
    optimizer='adam',
    metrics=['accuracy']
)

# Train the model
history = model.fit(
    x_train, y_train,
    epochs=10,
    batch_size=128,
    validation_split=0.2
)

# Evaluate the model
test_loss, test_accuracy = model.evaluate(x_test, y_test)
print(f'Test Loss: {test_loss}, Test Accuracy: {test_accuracy}')

Epoch 1/10
WARNING:tensorflow:Model was constructed with shape (None, None) for input KerasTensor(type_spec=TensorSpec(shape=(None, None), dtype=tf.float32, name='embedding_input'), name='embedding_input', description="created by layer 'embedding_input'"), but it was called on an input with incompatible shape (128, 28, 28).

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Input In [2], in <cell line: 31>()
     24 model.compile(
     25     loss='categorical_crossentropy',
     26     optimizer='adam',
     27     metrics=['accuracy']
     28 )
     30 # Train the model
---> 31 history = model.fit(
     32     x_train, y_train,
     33     epochs=10,
     34     batch_size=128,
     35     validation_split=0.2
     36 )
     38 # Evaluate the model
     39 test_loss, test_accuracy = model.evaluate(x_test, y_test)
File ~\Anaconda3\lib\site-packages\keras\utils\traceback_utils.py:67, in filter_traceback.<locals>.error_handler(*args, **kwargs)
     65 except Exception as e:  # pylint: disable=broad-except
     66   filtered_tb = _process_traceback_frames(e.__traceback__)
---> 67   raise e.with_traceback(filtered_tb) from None
     68 finally:
     69   del filtered_tb
File C:NaN, in outer_factory.<locals>.inner_factory.<locals>.tf__train_function(iterator)
     13 try:
     14     do_return = True
---> 15     retval_ = ag__.converted_call(ag__.ld(step_function), (ag__.ld(self), ag__.ld(iterator)), None, fscope)
     16 except:
     17     do_return = False
ValueError: in user code:

    File "C:\Users\suyashi144893\Anaconda3\lib\site-packages\keras\engine\training.py", line 1051, in train_function  *
        return step_function(self, iterator)
    File "C:\Users\suyashi144893\Anaconda3\lib\site-packages\keras\engine\training.py", line 1040, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "C:\Users\suyashi144893\Anaconda3\lib\site-packages\keras\engine\training.py", line 1030, in run_step  **
        outputs = model.train_step(data)
    File "C:\Users\suyashi144893\Anaconda3\lib\site-packages\keras\engine\training.py", line 889, in train_step
        y_pred = self(x, training=True)
    File "C:\Users\suyashi144893\Anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
        raise e.with_traceback(filtered_tb) from None
    File "C:\Users\suyashi144893\Anaconda3\lib\site-packages\keras\engine\input_spec.py", line 214, in assert_input_compatibility
        raise ValueError(f'Input {input_index} of layer "{layer_name}" '

    ValueError: Exception encountered when calling layer "sequential" (type Sequential).
    
    Input 0 of layer "lstm" is incompatible with the layer: expected ndim=3, found ndim=4. Full shape received: (128, 28, 28, 128)
    
    Call arguments received by layer "sequential" (type Sequential):
      • inputs=tf.Tensor(shape=(128, 28, 28), dtype=float32)
      • training=True
      • mask=None