ConvTranspose2d

Applies a 2D transposed convolution operator.

Abstract Signature:

ConvTranspose2d(input: Tensor, weight: Tensor, bias: Tensor, stride: int = 1, padding: int = 0, output_padding: int = 0, groups: int = 1, dilation: int = 1)

PyTorchJAX (Core)KerasTensorFlowApple MLXFlax NNXPaxML / Praxis

PyTorch

API: torch.nn.functional.conv_transpose2d

Strategy: Direct Mapping

Official Docs ↗

JAX (Core)

API: jax.lax.conv_transpose

Strategy: Plugin (jax_conv_transpose_adapter)

Keras

API: keras.layers.Conv2DTranspose

Strategy: Direct Mapping

Official Docs ↗

TensorFlow

API: tf.keras.layers.Convolution2DTranspose

Strategy: Direct Mapping

Official Docs ↗

Apple MLX

API: mlx.nn.layers.convolution_transpose.ConvTranspose2d

Strategy: Direct Mapping

Official Docs ↗

Flax NNX

API: flax.nnx.ConvTranspose

Strategy: Direct Mapping

Official Docs ↗

PaxML / Praxis

API: praxis.layers.Conv2DTranspose

Strategy: Direct Mapping

Official Docs ↗