Skip to content
masterclass Buddy
Start learning

TensorFlow · Class

layers.Conv2DTranspose

A 2D transposed convolution layer. It can turn a smaller feature map into a larger one while learning the connection pattern used for the transformation.

Last updated

Syntax

tf.keras.layers.Conv2DTranspose(filters, kernel_size, strides=(1, 1), padding='valid', output_padding=None, data_format=None, dilation_rate=(1, 1), activation=None, use_bias=True, kernel_initializer='glorot_uniform', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, bias_constraint=None, **kwargs)

In-depth API docs are only for subscribers: parameters, examples, common mistakes and interview practice.

Subscribe
  • tf.keras.layers.Conv2D
  • tf.keras.layers.UpSampling2D
  • tf.keras.layers.Conv1DTranspose
  • tf.keras.layers.Conv3DTranspose
  • tf.keras.layers.Convolution2DTranspose

Source: tf.keras.layers.Conv2DTranspose | TensorFlow v2.21.0. Checked 2026-11-03.