Warvito

import torch
from torch import nn
from monai.utils import optional_import

xformers, has_xformers = optional_import("xformers", name="xformers")


class SelfAttentionBlock(nn.Module):
    def __init__(
        self,

Warvito

class ResidualBlock(keras.Model):
    """Residual blocks that compose pixelCNN

    Blocks of layers with 3 convolutional layers and one residual connection.
    Based on Figure 5 from [1] where h indicates number of filters.

    Refs:
    [1] - Oord, A. V. D., Kalchbrenner, N., & Kavukcuoglu, K. (2016). Pixel
     recurrent neural networks. arXiv preprint arXiv:1601.06759.
    """

Warvito

class MaskedConv2D(keras.layers.Layer):
    """Convolutional layers with masks.

    Convolutional layers with simple implementation of masks type A and B for
    autoregressive models.

    Arguments:
    mask_type: one of `"A"` or `"B".`
    filters: Integer, the dimensionality of the output space
        (i.e. the number of output filters in the convolution).

Warvito

# -*- coding: utf-8 -*-
"""
This module creates an optimization of hyper-parameters of a DBN using hyperopt library
Check out the library here: https://github.com/hyperopt/hyperopt).
example run:
python hyperopt_exampleMNIST.py --trainSize=10000 --path=...

REFERENCES
[1] - Bergstra, James, Dan Yamins, and David D. Cox. "Hyperopt: A python library for optimizing the hyperparameters of machine learning algorithms." (2013).