Reshape the input for BatchDataset trained model

user_16521838 0
Viewed 161

I trained my tensorflow model on images after convert it to BatchDataset

  IMG_size = 224
  INPUT_SHAPE = [None, IMG_size, IMG_size, 3] # 4D input

  model.fit(x=train_data,
            epochs=EPOCHES,
            validation_data=test_data,
            validation_freq=1, # check validation metrics every epoch
            callbacks=[tensorboard, early_stopping])


     model.compile(
      loss=tf.keras.losses.CategoricalCrossentropy(), 
      optimizer=tf.keras.optimizers.Adam(), 
      metrics=["accuracy"] 
    )


  model.build(INPUT_SHAPE)

the train_data type is: tensorflow.python.data.ops.dataset_ops.BatchDataset.

I want to run my model on a single numpy array or tensor constant, but it will be 3D input matrix not 4D as the input TensorShape([224, 224, 3]); how can i reshape it?

keras tensorflow deep-learning machine-learning image-processing
2 Answers

You can expand the dimensions of your image matrix by using this code:

newImage = tf.expand_dims(Original_Image, axis = 0)

then pass it to the predict function, it will work fine.

user_144356800

target sizes make all input into the same shape.

It is helpful with input shape or you can use the image function to expand the dimension. img_array = tf.expand_dims(image, 0) # Create a batch

Talking about your input INPUT_SHAPE = [None, IMG_size, IMG_size, 3] # 4D input you can arrange those input images by image training dataset and feeds into the model.

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
Variables
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
BATCH_SIZE = 16
IMG_SIZE = (160, 160)
PATH = 'F:\\datasets\\downloads\\sample\\cats_dogs\\training'
training_directory = os.path.join(PATH, 'train')
validation_directory = os.path.join(PATH, 'validation')

train_dataset = tf.keras.utils.image_dataset_from_directory(training_directory,
            shuffle=True,
            batch_size=BATCH_SIZE,
            image_size=IMG_SIZE,
            seed=42)
validation_dataset = tf.keras.utils.image_dataset_from_directory(validation_directory,
            shuffle=True,
            batch_size=BATCH_SIZE,
            image_size=IMG_SIZE,
            seed=42)
    
class_names = train_dataset.class_names
print( "class_names: " + str( class_names ) )

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
DataSet
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
AUTOTUNE = tf.data.experimental.AUTOTUNE
train_dataset = train_dataset.prefetch(buffer_size=AUTOTUNE)

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
Model ( examine input layer )
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
inputs = tf.keras.Input(shape=(160, 160, 3))
model = tf.keras.Model(inputs, outputs)

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
Training
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
history = model.fit(train_dataset, epochs=initial_epochs, validation_data=validation_dataset)

... Sample

user_78485790
Related