ConvTranspose3d

Applies a 3D transposed convolution operator over an input image.

Abstract Signature:

ConvTranspose3d(input: Tensor, weight: Tensor, bias: Tensor, stride: Union[int, Tuple[int, int, int]] = 1, padding: Union[int, Tuple[int, int, int]] = 0, output_padding: Union[int, Tuple[int, int, int]] = 0, groups: int = 1, dilation: Union[int, Tuple[int, int, int]] = 1)

PyTorchJAX (Core)KerasTensorFlowApple MLXFlax NNXPaxML / Praxis

PyTorch

API: torch.nn.functional.conv_transpose3d

Strategy: Direct Mapping

Official Docs ↗

JAX (Core)

API: —

Strategy: Custom / Partial

Keras

API: keras.ops.conv_transpose

Strategy: Direct Mapping

Official Docs ↗

TensorFlow

API: tf.keras.layers.Conv3DTranspose

Strategy: Direct Mapping

Official Docs ↗

Apple MLX

API: mlx.nn.ConvTranspose3d

Strategy: Direct Mapping

Official Docs ↗

Flax NNX

API: flax.nnx.ConvTranspose

Strategy: Direct Mapping

Official Docs ↗

PaxML / Praxis

API: praxis.layers.Conv3DTranspose

Strategy: Direct Mapping

Official Docs ↗