wolterlw

/* 
parameter JSON
{
  "num_layers": 5,
  "min_scale": 0.1171875,
  "max_scale": 0.75,
  "input_size_height": 256,
  "input_size_width": 256,
  "anchor_offset_x": 0.5,
  "anchor_offset_y": 0.5,

JohanAR

#ifndef _POLYNOMIAL_REGRESSION_H
#define _POLYNOMIAL_REGRESSION_H  __POLYNOMIAL_REGRESSION_H
/**
 * PURPOSE:
 *
 *  Polynomial Regression aims to fit a non-linear relationship to a set of
 *  points. It approximates this by solving a series of linear equations using 
 *  a least-squares approach.
 *
 *  We can model the expected value y as an nth degree polynomial, yielding

sonots

# A trick to embed preprocessors in cython
cdef extern from *:
     cdef void EMIT_IF_PYTHON_VERSION_HEX_LT_37 "#if PY_VERSION_HEX < 0x03070000 //" ()
     cdef void EMIT_ELSE "#else //" ()
     cdef void EMIT_ENDIF "#endif //" ()

EMIT_IF_PYTHON_VERSION_HEX_LT_37()

EMIT_ELSE()

wassname

from keras import backend as K

def jaccard_distance_loss(y_true, y_pred, smooth=100):
    """
    Jaccard = (|X & Y|)/ (|X|+ |Y| - |X & Y|)
            = sum(|A*B|)/(sum(|A|)+sum(|B|)-sum(|A*B|))
    
    The jaccard distance loss is usefull for unbalanced datasets. This has been
    shifted so it converges on 0 and is smoothed to avoid exploding or disapearing
    gradient.

chrisengelsma

#ifndef _POLYNOMIAL_REGRESSION_H
#define _POLYNOMIAL_REGRESSION_H  __POLYNOMIAL_REGRESSION_H
/**
 * PURPOSE:
 *
 *  Polynomial Regression aims to fit a non-linear relationship to a set of
 *  points. It approximates this by solving a series of linear equations using 
 *  a least-squares approach.
 *
 *  We can model the expected value y as an nth degree polynomial, yielding

wsargent

Windows 10 Development Environment for Scala

This is a guide for Scala and Java development on Windows, using Windows Subsystem for Linux, although a bunch of it is applicable to a VirtualBox / Vagrant / Docker subsystem environment. This is not complete, but is intended to be as step by step as possible.

Harden Windows 10

Read the entire Decent Security guide, and follow the instructions, especially:

• Set UAC to full
• Enable Drive Encryption

wassname

"""
Here is a dice loss for keras which is smoothed to approximate a linear (L1) loss.
It ranges from 1 to 0 (no error), and returns results similar to binary crossentropy
"""

# define custom loss and metric functions 

from keras import backend as K

def dice_coef(y_true, y_pred, smooth=1):

shagunsodhani

The Batch Normalization paper describes a method to address the various issues related to training of Deep Neural Networks. It makes normalization a part of the architecture itself and reports significant improvements in terms of the number of iterations required to train the network.

Issues With Training Deep Neural Networks

Internal Covariate shift

Covariate shift refers to the change in the input distribution to a learning system. In the case of deep networks, the input to each layer is affected by parameters in all the input layers. So even small changes to the network get amplified down the network. This leads to change in the input distribution to internal layers of the deep network and is known as internal covariate shift.

It is well established that networks converge faster if the inputs have been whitened (ie zero mean, unit variances) and are uncorrelated and internal covariate shift leads to just the opposite.

kingjr

import numpy as np
import matplotlib.pyplot as plt
from nilearn.plotting.img_plotting import _load_anat
fname = '/home/jrking/nilearn_data/haxby2001/subj1/anat.nii.gz'


class MRI_viewer():
    def __init__(self, fname):
        # setup figure
        fig, axes = plt.subplots(1, 3)

baraldilorenzo

##VGG16 model for Keras

This is the Keras model of the 16-layer network used by the VGG team in the ILSVRC-2014 competition.

It has been obtained by directly converting the Caffe model provived by the authors.

Details about the network architecture can be found in the following arXiv paper:

Very Deep Convolutional Networks for Large-Scale Image Recognition

K. Simonyan, A. Zisserman