mickypaganini

def set_reproducible_seed(seed):
    import torch
    import numpy as np
    import random
    import os

    torch.manual_seed(seed)
    if torch.cuda.is_available():
        torch.cuda.manual_seed(seed)
        torch.cuda.manual_seed_all(seed)

mickypaganini

mickypaganini

# model is a keras Model
weights = model.weights # weight tensors
gradients = model.optimizer.get_gradients(model.total_loss, weights) # gradient tensors

import keras.backend as K
input_tensors = [model.inputs[0], # input data
                 model.sample_weights[0], # sample weights
                 model.targets[0], # labels
                 K.learning_phase(), # train or test mode
]

mickypaganini

mickypaganini

d = io.load('yourfile.hdf5')
#ix = [random.sample(range(4), 4) for _ in xrange(d['X'].shape[0])]
ix = np.argsort(d['X'][:, :4])[:, ::-1]

def _pairwise(iterable):
        '''s -> (s0, s1), (s2, s3), (s4, s5), ...'''
        a = iter(iterable)
        return izip(a, a)

cols = list(_pairwise(range(d['X'].shape[-1])[::4])) # or you can just type [(0, 4), (8, 12), (16, 20), (24, 28)]

mickypaganini

mickypaganini

#!/usr/bin/env bash

# ** TO USE ROOT, type load_root after all of this has been installed **

# GENERAL SETUP
################

# env usefulness
PYTHON_VERSION="2.7.10"
PY_PAYLOAD="Python-${PYTHON_VERSION}.tgz"

mickypaganini

mickypaganini

mickypaganini