Tensorflow implementation of Neural Process family
- Full code and experiment is based on deepmind repository [GIT, LICENSE]
- This repository aims to write more generic code and split model from experiment.
- Paper:
Jupyter notebook sample is here.
Model definition [GIT]
encoder_output_sizes = [128, 128, 128, 128]
decoder_output_sizes = [128, 128, 1]
model = neural_process.ConditionalNP(encoder_output_sizes, decoder_output_sizes)
Sample image
Model definition [GIT]
z_output_sizes = [128, 128, 128, 128]
enc_output_sizes = [128, 128, 128, 128]
dec_output_sizes = [128, 128, 1]
model = neural_process.NeuralProcess(z_output_sizes, enc_output_sizes, dec_output_sizes)
Sample image
Model definition [GIT]
z_output_sizes = [128, 128, 128, 128]
enc_output_sizes = [128, 128, 128, 128]
cross_output_sizes = [128, 128, 128, 128]
dec_output_sizes = [128, 128, 1]
self_attention = neural_process.Attention(attention_type='multihead', proj=[128, 128])
cross_attention = neural_process.Attention(attention_type='multihead', proj=[128, 128])
model = neural_process.AttentiveNP(z_output_sizes,
enc_output_sizes,
cross_output_sizes,
dec_output_sizes,
self_attention,
cross_attention)
Sample image