CODEWITHSUNDEEP
pythontensorflowkerastensorflow-datasetsconv-neural-network
Dariyan Khan
Dariyan Khan

Reputation: 89

How to expand the dimension of each batch in a tensorflow dataset

I created a tf.data dataset, however, I keep on running into this error when trying to fit my Sequential CNN model with it.

 ValueError: Input 0 of layer sequential is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [32, 28, 28]

At the moment, my train dataset is of the form ('x_train','y_train'), where each batch in 'x_train' has shape [32,28,28], and each batch in 'y_train' has shape (32,). How do I change the dimension of each 'x_train' batch to [32,28,28,1], without changing the shape of each batch in 'y_train'?

Here is my entire code:

#imports
import tarfile
import numpy as np
import pandas as pd
import matplotlib
import tensorflow as tf

# Get Data



def get_images():

    """Get the fashion-mnist images.
    Returns
    -------
    (x_train, x_test) : tuple of uint8 arrays
        Grayscale image data with shape (num_samples, 28, 28)
    (y_train, y_test) : tuple of uint8 arrays
        Labels (integers in range 0-9) with shape (num_samples,)
    Examples
    --------
    >>> from reader import get_images
    >>> (x_train, y_train), (x_test, y_test) = get_images() 
    Notes
    -----
    The data is split into train and test sets as described in the original paper [1].
    References
    ----------
    1. Xiao H, Rasul K, Vollgraf R. Fashion-MNIST: a Novel Image Dataset for 
    Benchmarking Machine Learning Algorithms. CoRR [Internet]. 2017;abs/1708.07747.
    Available from: http://arxiv.org/abs/1708.07747
    """

    with tarfile.open('data.tar.gz', 'r') as f:
        f.extractall()

    df_train = pd.read_csv('fashion_mnist_train.csv')
    df_test = pd.read_csv('fashion_mnist_test.csv')

    x_train = df_train.drop('label', axis=1).to_numpy(np.uint8)
    y_train = df_train['label'].to_numpy(np.uint8)
    x_test = df_test.drop('label', axis=1).to_numpy(np.uint8)
    y_test = df_test['label'].to_numpy(np.uint8)

    return (x_train, y_train), (x_test, y_test)

(x_train,y_train),(x_test,y_test)=get_images()

clothing=['top','trouser','pullover','dress','coat','sandal','shirt','sneaker','bag','ankle boot']

BUFFER_SIZE=1000

BATCH_SIZE=32

#Reshape x_train and y_train, and scale them to the range [0,1]

new_x_train=[]
new_x_test=[]
for i,train in enumerate(x_train):
    #print(np.shape(train))
    arr=np.reshape(x_train[i],(28,28))
    arr=arr/255.0
    new_x_train.append(arr)
    
    
    
for i,test in enumerate(x_test):
    arr=np.reshape(x_test[i],(28,28))
    arr=arr/255.0
    new_x_test.append(arr)

train_dataset = tf.data.Dataset.from_tensor_slices((new_x_train,y_train)).shuffle(BUFFER_SIZE).batch(BATCH_SIZE,drop_remainder=True)

from keras.layers import LeakyReLU

CNN_model= tf.keras.Sequential()

#CNN_model.add(tf.keras.layers.Lambda(tf.py_function(expand_dims)))

CNN_model.add(tf.keras.layers.Conv2D(
    20, (5,5), strides=(1, 1), padding='valid',
    kernel_initializer='glorot_uniform'))

#CNN_model.add(tf.keras.layers(tf.keras.layers.Lambda(
 #   function)

              
CNN_model.add(LeakyReLU(alpha=0.05))
              
CNN_model.add(tf.keras.layers.MaxPool2D(
    pool_size=(2, 2), strides=None, padding='valid'))

CNN_model.add(tf.keras.layers.Conv2D(
    50, (3,3), strides=(1, 1), padding='valid',
    kernel_initializer='glorot_uniform'))

CNN_model.add(LeakyReLU(alpha=0.05))

CNN_model.add(tf.keras.layers.MaxPool2D(
    pool_size=(2, 2), strides=None, padding='valid'))  
              
CNN_model.add(tf.keras.layers.Conv2D(
    10, (1,1), strides=(1, 1), padding='valid',
    kernel_initializer='glorot_uniform'))

CNN_model.add(LeakyReLU(alpha=0.05))

CNN_model.add(tf.keras.layers.GlobalAveragePooling2D())

CNN_model.add(tf.keras.layers.Softmax(axis=-1))



CNN_model.compile(loss="sparse_categorical_crossentropy",
              optimizer="adam",
              metrics=["accuracy"])

CNN_history = CNN_model.fit(train_dataset, epochs=10)

Upvotes: 0

Views: 2875

Answers (2)

Cenk Bircanoglu
Cenk Bircanoglu

Reputation: 529

You can try to use this

arr=np.reshape(x_test[i],(1, 28,28))

instead of this

arr=np.reshape(x_test[i],(28,28))

If you are using channel last you can put 1 as the 3rd dim.

Upvotes: 1

Edwin Cheong
Edwin Cheong

Reputation: 989

Well you can do a simple expand dims:

import numpy as np
x_train = np.expand_dims(x_train, axis=-1)

But strange can i ask how did you load your data? Generator function?

Upvotes: 1

Related Questions